{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/continuous-control-with-deep-reinforcement","title":"Continuous control with deep reinforcement learning","arxiv_id":"1509.02971","date":"2015-09-09","proceeding":null,"authors":["Timothy P. Lillicrap","Jonathan J. Hunt","Alexander Pritzel","Nicolas Heess","Tom Erez","Yuval Tassa","David Silver","Daan Wierstra"],"abstract":"We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain. We present an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces. Using the same learning algorithm, network architecture and hyper-parameters, our algorithm robustly solves more than 20 simulated physics tasks, including classic problems such as cartpole swing-up, dexterous manipulation, legged locomotion and car driving. Our algorithm is able to find policies whose performance is competitive with those found by a planning algorithm with full access to the dynamics of the domain and its derivatives. We further demonstrate that for many of the tasks the algorithm can learn policies end-to-end: directly from raw pixel inputs.","url_abs":"https://arxiv.org/abs/1509.02971v6","url_pdf":"https://arxiv.org/pdf/1509.02971v6.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/AgrawalAmey/safe-explorer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/AlexandraFilimokhina/MountainCarConrinious_DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/Brook1711/RIS_components","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/Crevass/Hybrid-Agent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/DanielLSM/safe-rl-tutorial","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/Dekki-Aero/DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/EyaRhouma/collaboration-competition-MADDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/FlyienSHaDOw/continuous_control","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/FlyienSHaDOw/project_2_continuous_control","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/Gouet/DDPG_PendulumV1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/HJDQN/HJQ","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/InSpaceAI/RL-Zoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/IvanVigor/MADDPG-Unity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/J93T/TP4-DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/JL321/mujo-2DHalf-Cheetah","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/JL321/mujo-2DWalker","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/JonasRSV/DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/JonasRSV/PGTensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/KAIST-AILab/deeprl_practice_colab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/KelvinYang0320/deepbots-panda","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/Kikumu/Reinforcement-Learning-repo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/LM095/DDPG-implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/MLCS-Yonsei/ddpg-control","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/MathPhysSim/PER-NAF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/Medabid1/RL_Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/MrSyee/pg-is-all-you-need","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/NOHYC/autonomous_driving_car_project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/NervanaSystems/coach","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/Pechckin/MountainCar","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/PeterJochem/Deep_RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/PeterJochem/Double_Deep_QLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/Philori22/DDPG-aigym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/SaminYeasar/off_policy_ac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/SergiPonsa/Reinforcement-Learning-Sergi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/Sheldonmao/Learning-To-walk","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/SimonRamstedt/ddpg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/Souphis/mobile_robot_rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/T3chy/DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/TheInfamousWayne/ddpg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/VasaKiDD/TD3-deep-rl-research","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/WittmannF/quadcopter-best-practices","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/YangRui2015/Modular_HER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/YoUNG824/DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/ZainRaza14/deepRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/ZiyangY/IndProject-RL-in-Supply-chain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/abbadka/quadcopter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/ai-winter/python_motion_planning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/ailab-pku/rl-framework","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/alathiya/RL-Quadcoptor-Flying","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/alhabk/SGEE--pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/andreidi/AC_DDPG_walker","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/anita-hu/TF2-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/avivelor/UnityMachineLearningForProjectButterfly","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/b06b01073/continuous-control","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/bacdavid/HER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/backgom2357/Recommender_system_via_deep_RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/baturaysaglam/RIS-MISO-Deep-Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/baturaysaglam/ac-off-poc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/baturaysaglam/dase","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/bidimensional/Tennis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/biemann/Continuous-Control","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/bitterbloom/Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/bmeyers/VirtualMicrogridSegmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/chainer/chainerrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/claudeHifly/BipedalWalker-v3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/dan-lennox/ml-udacity-quadcopter-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/darkrush/meta_learn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/dchetelat/acer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/denizmguen/IANNWTF2019-Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/dfki-ric-underactuated-lab/torque_limited_simple_pendulum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/dpoulopoulos/drl_collaborate_compete","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/dpoulopoulos/drl_continuous_control","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/dyth/doublegum","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/facebookresearch/Horizon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/fdcl-gwu/gym-rotor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/feruxhi/thoughts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/fhbzc/FishAgentSimulation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/fiberleif/nc_ddpg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/flavioschneider/ml_papers_presentations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/floodsung/DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/flowersteam/curious","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/fshamshirdar/pytorch-rdpg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/georgkruse/cleanqrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/ghliu/pytorch-ddpg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/guillaumeboniface/reacher","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/gwthomas/gtml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/h-aboutalebi/SparceReward","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/halajadallah/RL-Quadcopter_project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/hamishs/JAX-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/hemilpanchiwala/Hindsight-Experience-Replay","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/iDataist/Tennis-With-Multi-Agent-Reinforcement","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/krasing/DRLearningCollaboration","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/krasing/DRLearningContinuousControl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/kushagra06/DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/liampetti/DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/liuyuezhang/pyrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/luke-bhan/TwitterSentimentAnalysisTool","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/lukebhan/TwitterSentimentAnalysisTool","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/madhur-tandon/RL-Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/madvn/DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/majercakdavid/gym-virtual-quant-trading","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/marload/DeepRL-TensorFlow2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/massquantity/DBRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/mathformoso/RL-playground---ddpg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/matthewsparr/Reinforcement-Learning-Lesson","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/montaserFath/Reinforcement-Learning-for-Prosthetics","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/nav74neet/ddpg4biped","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/nav74neet/ddpg_biped","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/nav74neet/rl4biped","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/parilo/rl-server","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/petsol/ContinuousControl_UnityAgent_DDPG_Udacity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/prajwalgatti/DRL-Collaboration-and-Competition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/prajwalgatti/DRL-Continuous-Control","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/rikluost/RL_DQN_Pong","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/rk1998/robot-sac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/s-sd/task-amenability","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/samiranrl/ODSC_2019_RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/samuelmat19/DDPG-tf2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/saoudh/Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/sayantanauddy/hierarchical_bipedal_controller","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/schatty/D4PG-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/seungjaeryanlee/osim-rl-helper","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/shahabi8/Deep-Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/shahin-01/vqa-ad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/shakedzy/warehouse","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/shehrum/RL_Continous-Control","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/siyuofzhou/DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/songrotek/DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/soumik12345/DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/stevenpjg/ddpg-aigym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/susan-amin/SparseBaseline1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/taku-y/20181125-pybullet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/tegg89/DLCamp_Jeju2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/tegg89/magnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/tegg89/magnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/tegg89/mann","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/tensorlayer/RLzoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/thainv0212/re-ddpg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/tilkb/thermoai","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/wassname/rl-portfolio-management","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/wpiszlogin/driver_critic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/wwydmanski/rl_tennis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/xtma/simple-pytorch-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/xuyuandong/simple-ddpg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/xyshadow/baseline_ddpg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/yukezhu/tensorflow-reinforce","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/yusme/DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/2023-MindSpore-1/ms-code-210/tree/main/DDAG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/DLR-RM/stable-baselines3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/JorgeA-RD/Reinforcement-Learning-Agents/tree/main/DDPG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/arnomoonens/yarll","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/facebookresearch/rl/blob/main/examples/ddpg/ddpg.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/hill-a/stable-baselines","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/jakegrigsby/deep_control/blob/master/deep_control/ddpg.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/ray-project/ray/tree/master/rllib","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"continuous-control-with-deep-reinforcement","repo_url":"https://github.com/toni-sm/skrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"openai-gym","task_name":"OpenAI Gym"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"speech-emotion-recognition","task_name":"Speech Emotion Recognition"},{"task_slug":"continuous-control","task_name":"continuous-control"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"ddpg","method_name":"DDPG"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"q-learning","method_name":"Q-Learning"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"ddpg","name":"DDPG","full_name":"Deep Deterministic Policy Gradient"}],"results":[{"leaderboard":"/sota/continuous-control-on-lunar-lander-openai-gym","task":"Continuous Control","dataset":"Lunar Lander (OpenAI Gym)","model":"DDPG","rank_in_archive_order":3,"of":5,"metrics":{"Score":"256.98±14.38"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-ant-v4","task":"OpenAI Gym","dataset":"Ant-v4","model":"DDPG","rank_in_archive_order":4,"of":5,"metrics":{"Average Return":"1712.12"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-halfcheetah-v4","task":"OpenAI Gym","dataset":"HalfCheetah-v4","model":"DDPG","rank_in_archive_order":2,"of":5,"metrics":{"Average Return":"14934.86"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-hopper-v4","task":"OpenAI Gym","dataset":"Hopper-v4","model":"DDPG","rank_in_archive_order":4,"of":5,"metrics":{"Average Return":"1290.24"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-humanoid-v4","task":"OpenAI Gym","dataset":"Humanoid-v4","model":"DDPG","rank_in_archive_order":5,"of":5,"metrics":{"Average Return":"139.14"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-walker2d-v4","task":"OpenAI Gym","dataset":"Walker2d-v4","model":"DDPG","rank_in_archive_order":3,"of":5,"metrics":{"Average Return":"2994.54"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1509.02971","atlas_url":"https://app.syntology.ai/?focus=1509.02971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1509.02971"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1509.02971"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1509.02971"},"call":"get_harvested_code_for_paper(arxiv_id=\"1509.02971\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"1509.02971"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1509.02971\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1509.02971"},"call":"get_concepts_for_paper(arxiv_id=\"1509.02971\")"}],"by_repo":[{"repo":"AgrawalAmey/safe-explorer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"AlexandraFilimokhina/MountainCarConrinious_DDPG","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Brook1711/RIS_components","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Crevass/Hybrid-Agent","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"DanielLSM/safe-rl-tutorial","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"Dekki-Aero/DDPG","kind":"listed","samples":5,"ran":4,"instrument":0,"unverified":1},{"repo":"EyaRhouma/collaboration-competition-MADDPG","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"FlyienSHaDOw/continuous_control","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"FlyienSHaDOw/project_2_continuous_control","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Gouet/DDPG_PendulumV1","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"HJDQN/HJQ","kind":"listed","samples":10,"ran":6,"instrument":1,"unverified":4},{"repo":"InSpaceAI/RL-Zoo","kind":"listed","samples":4,"ran":1,"instrument":0,"unverified":3},{"repo":"IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env","kind":"listed","samples":4,"ran":3,"instrument":0,"unverified":1},{"repo":"IvanVigor/MADDPG-Unity","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"J93T/TP4-DDPG","kind":"listed","samples":5,"ran":4,"instrument":0,"unverified":1},{"repo":"JL321/mujo-2DHalf-Cheetah","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"JL321/mujo-2DWalker","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"JonasRSV/DDPG","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"JonasRSV/PGTensorflow","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"KAIST-AILab/deeprl_practice_colab","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1511.05952","1606.03476"],"harvested_for_calls":[{"arxiv_id":"1511.05952","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1511.05952"},"call":"get_harvested_code_for_paper(arxiv_id=\"1511.05952\")"},{"arxiv_id":"1606.03476","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1606.03476"},"call":"get_harvested_code_for_paper(arxiv_id=\"1606.03476\")"}]},{"repo":"KelvinYang0320/deepbots-panda","kind":"listed","samples":3,"ran":2,"instrument":0,"unverified":1},{"repo":"Kikumu/Reinforcement-Learning-repo","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"LM095/DDPG-implementation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MLCS-Yonsei/ddpg-control","kind":"listed","samples":7,"ran":0,"instrument":0,"unverified":7},{"repo":"MathPhysSim/PER-NAF","kind":"listed","samples":4,"ran":1,"instrument":0,"unverified":3},{"repo":"Medabid1/RL_Project","kind":"listed","samples":3,"ran":2,"instrument":0,"unverified":1},{"repo":"MrSyee/pg-is-all-you-need","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"NOHYC/autonomous_driving_car_project","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1908.00821"],"harvested_for_calls":[{"arxiv_id":"1908.00821","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1908.00821"},"call":"get_harvested_code_for_paper(arxiv_id=\"1908.00821\")"}]},{"repo":"NervanaSystems/coach","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Pechckin/MountainCar","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"PeterJochem/Deep_RL","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"PeterJochem/Double_Deep_QLearning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Philori22/DDPG-aigym","kind":"listed","samples":4,"ran":2,"instrument":0,"unverified":2},{"repo":"Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1602.01783"],"harvested_for_calls":[{"arxiv_id":"1602.01783","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1602.01783"},"call":"get_harvested_code_for_paper(arxiv_id=\"1602.01783\")"}]},{"repo":"SaminYeasar/off_policy_ac","kind":"listed","samples":3,"ran":2,"instrument":0,"unverified":1},{"repo":"SergiPonsa/Reinforcement-Learning-Sergi","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"Sheldonmao/Learning-To-walk","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"SimonRamstedt/ddpg","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"Souphis/mobile_robot_rl","kind":"listed","samples":15,"ran":11,"instrument":2,"unverified":4},{"repo":"T3chy/DDPG","kind":"listed","samples":5,"ran":4,"instrument":0,"unverified":1},{"repo":"TheInfamousWayne/ddpg","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"VasaKiDD/TD3-deep-rl-research","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"WittmannF/quadcopter-best-practices","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"YangRui2015/Modular_HER","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1707.01495"],"harvested_for_calls":[{"arxiv_id":"1707.01495","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1707.01495"},"call":"get_harvested_code_for_paper(arxiv_id=\"1707.01495\")"}]},{"repo":"YoUNG824/DDPG","kind":"listed","samples":5,"ran":2,"instrument":0,"unverified":3},{"repo":"ZainRaza14/deepRL","kind":"listed","samples":4,"ran":3,"instrument":0,"unverified":1},{"repo":"ZiyangY/IndProject-RL-in-Supply-chain","kind":"listed","samples":3,"ran":3,"instrument":0,"unverified":0},{"repo":"abbadka/quadcopter","kind":"listed","samples":3,"ran":0,"instrument":0,"unverified":3},{"repo":"ai-winter/python_motion_planning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ailab-pku/rl-framework","kind":"listed","samples":3,"ran":0,"instrument":0,"unverified":3},{"repo":"alathiya/RL-Quadcoptor-Flying","kind":"listed","samples":4,"ran":1,"instrument":0,"unverified":3},{"repo":"alhabk/SGEE--pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1806.05635"],"harvested_for_calls":[{"arxiv_id":"1806.05635","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1806.05635"},"call":"get_harvested_code_for_paper(arxiv_id=\"1806.05635\")"}]},{"repo":"andreidi/AC_DDPG_walker","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"anita-hu/TF2-RL","kind":"listed","samples":8,"ran":4,"instrument":2,"unverified":4},{"repo":"avivelor/UnityMachineLearningForProjectButterfly","kind":"listed","samples":10,"ran":0,"instrument":0,"unverified":10},{"repo":"b06b01073/continuous-control","kind":"listed","samples":3,"ran":3,"instrument":0,"unverified":0},{"repo":"bacdavid/HER","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1707.01495"],"harvested_for_calls":[{"arxiv_id":"1707.01495","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1707.01495"},"call":"get_harvested_code_for_paper(arxiv_id=\"1707.01495\")"}]},{"repo":"backgom2357/Recommender_system_via_deep_RL","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"baturaysaglam/RIS-MISO-Deep-Reinforcement-Learning","kind":"listed","samples":3,"ran":3,"instrument":0,"unverified":0},{"repo":"baturaysaglam/ac-off-poc","kind":"listed","samples":3,"ran":3,"instrument":0,"unverified":0},{"repo":"baturaysaglam/dase","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"bidimensional/Tennis","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"biemann/Continuous-Control","kind":"listed","samples":4,"ran":3,"instrument":0,"unverified":1},{"repo":"bitterbloom/Reinforcement-Learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"bmeyers/VirtualMicrogridSegmentation","kind":"listed","samples":8,"ran":4,"instrument":0,"unverified":4},{"repo":"chainer/chainerrl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1912.03905"],"harvested_for_calls":[{"arxiv_id":"1912.03905","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1912.03905"},"call":"get_harvested_code_for_paper(arxiv_id=\"1912.03905\")"}]},{"repo":"claudeHifly/BipedalWalker-v3","kind":"listed","samples":4,"ran":4,"instrument":0,"unverified":0},{"repo":"dan-lennox/ml-udacity-quadcopter-rl","kind":"listed","samples":5,"ran":2,"instrument":0,"unverified":3},{"repo":"darkrush/meta_learn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"dchetelat/acer","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"denizmguen/IANNWTF2019-Project","kind":"listed","samples":3,"ran":0,"instrument":0,"unverified":3},{"repo":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","kind":"listed","samples":11,"ran":9,"instrument":3,"unverified":2},{"repo":"dpoulopoulos/drl_collaborate_compete","kind":"listed","samples":4,"ran":4,"instrument":0,"unverified":0},{"repo":"dpoulopoulos/drl_continuous_control","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"dyth/doublegum","kind":"listed","samples":5,"ran":1,"instrument":0,"unverified":4},{"repo":"facebookresearch/Horizon","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"fdcl-gwu/gym-rotor","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1910.01465"],"harvested_for_calls":[{"arxiv_id":"1910.01465","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1910.01465"},"call":"get_harvested_code_for_paper(arxiv_id=\"1910.01465\")"}]},{"repo":"feruxhi/thoughts","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"fhbzc/FishAgentSimulation","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"fiberleif/nc_ddpg","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"flavioschneider/ml_papers_presentations","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"floodsung/DDPG","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"flowersteam/curious","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1707.01495"],"harvested_for_calls":[{"arxiv_id":"1707.01495","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1707.01495"},"call":"get_harvested_code_for_paper(arxiv_id=\"1707.01495\")"}]},{"repo":"fshamshirdar/pytorch-rdpg","kind":"listed","samples":13,"ran":10,"instrument":1,"unverified":3},{"repo":"georgkruse/cleanqrl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ghliu/pytorch-ddpg","kind":"listed","samples":6,"ran":5,"instrument":0,"unverified":1},{"repo":"guillaumeboniface/reacher","kind":"listed","samples":4,"ran":3,"instrument":0,"unverified":1},{"repo":"gwthomas/gtml","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"h-aboutalebi/SparceReward","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1801.01290"],"harvested_for_calls":[{"arxiv_id":"1801.01290","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1801.01290"},"call":"get_harvested_code_for_paper(arxiv_id=\"1801.01290\")"}]},{"repo":"halajadallah/RL-Quadcopter_project","kind":"listed","samples":3,"ran":0,"instrument":0,"unverified":3},{"repo":"hamishs/JAX-RL","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"hemilpanchiwala/Hindsight-Experience-Replay","kind":"listed","samples":4,"ran":3,"instrument":0,"unverified":1},{"repo":"iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient","kind":"listed","samples":5,"ran":4,"instrument":0,"unverified":1},{"repo":"iDataist/Tennis-With-Multi-Agent-Reinforcement","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"krasing/DRLearningCollaboration","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"krasing/DRLearningContinuousControl","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"kushagra06/DDPG","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"liampetti/DDPG","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"liuyuezhang/pyrl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1602.01783","1707.06347"],"harvested_for_calls":[{"arxiv_id":"1602.01783","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1602.01783"},"call":"get_harvested_code_for_paper(arxiv_id=\"1602.01783\")"},{"arxiv_id":"1707.06347","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1707.06347"},"call":"get_harvested_code_for_paper(arxiv_id=\"1707.06347\")"}]},{"repo":"luke-bhan/TwitterSentimentAnalysisTool","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lukebhan/TwitterSentimentAnalysisTool","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"madhur-tandon/RL-Project","kind":"listed","samples":5,"ran":4,"instrument":0,"unverified":1},{"repo":"madvn/DDPG","kind":"listed","samples":3,"ran":0,"instrument":0,"unverified":3},{"repo":"majercakdavid/gym-virtual-quant-trading","kind":"listed","samples":6,"ran":3,"instrument":0,"unverified":3},{"repo":"marload/DeepRL-TensorFlow2","kind":"listed","samples":4,"ran":1,"instrument":0,"unverified":3},{"repo":"massquantity/DBRL","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"mathformoso/RL-playground---ddpg","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"matthewsparr/Reinforcement-Learning-Lesson","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"montaserFath/Reinforcement-Learning-for-Prosthetics","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"nav74neet/ddpg4biped","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"nav74neet/ddpg_biped","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"nav74neet/rl4biped","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"parilo/rl-server","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"petsol/ContinuousControl_UnityAgent_DDPG_Udacity","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"prajwalgatti/DRL-Collaboration-and-Competition","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"prajwalgatti/DRL-Continuous-Control","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"rikluost/RL_DQN_Pong","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"rk1998/robot-sac","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"s-sd/task-amenability","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"samiranrl/ODSC_2019_RL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"samuelmat19/DDPG-tf2","kind":"listed","samples":5,"ran":2,"instrument":1,"unverified":3},{"repo":"saoudh/Reinforcement-Learning","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"sayantanauddy/hierarchical_bipedal_controller","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"schatty/D4PG-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"seungjaeryanlee/osim-rl-helper","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"shahabi8/Deep-Reinforcement-Learning","kind":"listed","samples":3,"ran":0,"instrument":0,"unverified":3},{"repo":"shahin-01/vqa-ad","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"shakedzy/warehouse","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1702.08165"],"harvested_for_calls":[{"arxiv_id":"1702.08165","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1702.08165"},"call":"get_harvested_code_for_paper(arxiv_id=\"1702.08165\")"}]},{"repo":"shehrum/RL_Continous-Control","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"siyuofzhou/DDPG","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3","kind":"listed","samples":3,"ran":2,"instrument":0,"unverified":1},{"repo":"songrotek/DDPG","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"soumik12345/DDPG","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"stevenpjg/ddpg-aigym","kind":"listed","samples":4,"ran":0,"instrument":0,"unverified":4},{"repo":"susan-amin/SparseBaseline1","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"taku-y/20181125-pybullet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tegg89/DLCamp_Jeju2018","kind":"listed","samples":7,"ran":1,"instrument":0,"unverified":6},{"repo":"tegg89/magnet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1811.12557"],"harvested_for_calls":[{"arxiv_id":"1811.12557","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1811.12557"},"call":"get_harvested_code_for_paper(arxiv_id=\"1811.12557\")"}]},{"repo":"tegg89/magnn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tegg89/mann","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"tensorlayer/RLzoo","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"thainv0212/re-ddpg","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"tilkb/thermoai","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"wassname/rl-portfolio-management","kind":"listed","samples":4,"ran":2,"instrument":0,"unverified":2},{"repo":"wpiszlogin/driver_critic","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"wwydmanski/rl_tennis","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"xtma/simple-pytorch-rl","kind":"listed","samples":4,"ran":4,"instrument":0,"unverified":0},{"repo":"xuyuandong/simple-ddpg","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"xyshadow/baseline_ddpg","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"yukezhu/tensorflow-reinforce","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"yusme/DDPG","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"2023-MindSpore-1/ms-code-210","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"DLR-RM/stable-baselines3","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2603.01771"],"harvested_for_calls":[{"arxiv_id":"2603.01771","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2603.01771"},"call":"get_harvested_code_for_paper(arxiv_id=\"2603.01771\")"}]},{"repo":"JorgeA-RD/Reinforcement-Learning-Agents","kind":"listed","samples":3,"ran":3,"instrument":0,"unverified":0},{"repo":"arnomoonens/yarll","kind":"listed","samples":3,"ran":3,"instrument":0,"unverified":0},{"repo":"facebookresearch/rl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2306.17100"],"harvested_for_calls":[{"arxiv_id":"2306.17100","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2306.17100"},"call":"get_harvested_code_for_paper(arxiv_id=\"2306.17100\")"}]},{"repo":"hill-a/stable-baselines","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1509.06461","1511.05952"],"harvested_for_calls":[{"arxiv_id":"1509.06461","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1509.06461"},"call":"get_harvested_code_for_paper(arxiv_id=\"1509.06461\")"},{"arxiv_id":"1511.05952","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1511.05952"},"call":"get_harvested_code_for_paper(arxiv_id=\"1511.05952\")"}]},{"repo":"jakegrigsby/deep_control","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2106.08918"],"harvested_for_calls":[{"arxiv_id":"2106.08918","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.08918"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.08918\")"}]},{"repo":"ray-project/ray","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"toni-sm/skrl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","assemblies":[{"assembly_sha256":"014471cd2234f3f4","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"BaseSolution","entry_sha256":"746b1c49c2b69b79","n_bricks":1,"bricks":[{"entry":"BaseSolution","code_sha256":"746b1c49c2b69b79","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"042dd9e9176954eb","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"9f83c78d8022ed75","n_bricks":7,"bricks":[{"entry":"DDPG","code_sha256":"9f83c78d8022ed75","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActorNet","code_sha256":"36fb14c831b75e4f","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"ActorNet_bn","code_sha256":"883fbd58c181e487","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"CriticNet","code_sha256":"42be45cafdda9bc6","role":"model","order":3,"level":0,"status":"unverified"},{"entry":"CriticNet_bn","code_sha256":"2961cc94350daaae","role":"helper","order":4,"level":0,"status":"unverified"},{"entry":"grad_inverter","code_sha256":"ff560a45eef0d026","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"batch_norm","code_sha256":"7484fd6def5722c7","role":"helper","order":6,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"0fe228f97c750fd9","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"ContinuousActorCritic","entry_sha256":"53c5f2f2df73a0e0","n_bricks":2,"bricks":[{"entry":"ContinuousActorCritic","code_sha256":"53c5f2f2df73a0e0","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActorCritic","code_sha256":"26052e22d5d45a91","role":"model","order":1,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"14a213be39fc4d33","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, as proposed in the paper.","centrality":"contribution","entry":"DeepDeterministicPolicyGradient","entry_sha256":"ff673a112b0d8acd","n_bricks":2,"bricks":[{"entry":"DeepDeterministicPolicyGradient","code_sha256":"ff673a112b0d8acd","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ReplayBuffer","code_sha256":"3c7178cf937ba425","role":"helper","order":1,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"16df799befa89075","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"RDPG","entry_sha256":"66f422ab00f28663","n_bricks":13,"bricks":[{"entry":"RDPG","code_sha256":"66f422ab00f28663","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Agent","code_sha256":"f21df3758ed39418","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"EpisodicMemory","code_sha256":"07b241d4ab8ac0cb","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"Evaluator","code_sha256":"ff0baff75d5cb615","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"958765de0feeec56","role":"model","order":4,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"060c46e5cc508cc5","role":"model","order":5,"level":1,"status":"ran"},{"entry":"OrnsteinUhlenbeckProcess","code_sha256":"37ebaf510f179bf4","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"Memory","code_sha256":"a5e014313403ae12","role":"helper","order":7,"level":1,"status":"ran"},{"entry":"RingBuffer","code_sha256":"3f3476b061f68f18","role":"helper","order":8,"level":1,"status":"ran"},{"entry":"fanin_init","code_sha256":"0d0842514b1844a1","role":"helper","order":9,"level":1,"status":"ran_fixture"},{"entry":"AnnealedGaussianProcess","code_sha256":"3ad5029d3ca03531","role":"helper","order":10,"level":1,"status":"ran"},{"entry":"zeroed_observation","code_sha256":"b5cc72675b688b00","role":"helper","order":11,"level":1,"status":"ran_honours"},{"entry":"RandomProcess","code_sha256":"ab1c58fa8208bfec","role":"helper","order":12,"level":1,"status":"ran"}],"ran_individually":10,"ran_individually_constructed":8,"ran_individually_by_status":{"ran":8,"ran_fixture":1,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"1860bac79d379492","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Agent","entry_sha256":"7167793e1651d552","n_bricks":4,"bricks":[{"entry":"Agent","code_sha256":"7167793e1651d552","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"ActorNet","code_sha256":"1e7906d3e94a41ce","role":"model","order":1,"level":1,"status":"ran"},{"entry":"CriticNet","code_sha256":"fa4e45cc6c3c6500","role":"model","order":2,"level":1,"status":"ran"},{"entry":"Memory","code_sha256":"dc27eb092679d1d2","role":"sampler","order":3,"level":1,"status":"ran"}],"ran_individually":4,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"192705a305cf407b","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPGAgent","entry_sha256":"037ce510df007080","n_bricks":4,"bricks":[{"entry":"DDPGAgent","code_sha256":"037ce510df007080","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"4210d97aa24222d8","role":"model","order":1,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"e47034c4a39da307","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"1a3c5297309ff7b3","role":"helper","order":3,"level":1,"status":"ran"}],"ran_individually":4,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"1a123d5d6a10efe9","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, as proposed in the paper.","centrality":"contribution","entry":"DDPG","entry_sha256":"ced83557bfb5a383","n_bricks":5,"bricks":[{"entry":"DDPG","code_sha256":"ced83557bfb5a383","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActorNetwork","code_sha256":"18c75ab6a06581a4","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"CriticNetwork","code_sha256":"ebdd58004bdf82fd","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"OUNoise","code_sha256":"85896c6b57d5891f","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"cbd6d4cba3c8f7b0","role":"helper","order":4,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"23425bc3067b1f80","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, implemented as the DDPG class.","centrality":"contribution","entry":"DDPG","entry_sha256":"5145b262fcd6a876","n_bricks":12,"bricks":[{"entry":"DDPG","code_sha256":"5145b262fcd6a876","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"fb986aef8cb19dcb","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"f93619eb32cfaf3d","role":"model","order":2,"level":1,"status":"ran"},{"entry":"OrnsteinUhlenbeckProcess","code_sha256":"37ebaf510f179bf4","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"SequentialMemory","code_sha256":"980051699184bfdd","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"fanin_init","code_sha256":"0d0842514b1844a1","role":"helper","order":5,"level":1,"status":"ran_fixture"},{"entry":"AnnealedGaussianProcess","code_sha256":"3ad5029d3ca03531","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"Memory","code_sha256":"a5e014313403ae12","role":"helper","order":7,"level":1,"status":"ran"},{"entry":"RingBuffer","code_sha256":"a3c118a9e035f7e4","role":"helper","order":8,"level":1,"status":"ran"},{"entry":"sample_batch_indexes","code_sha256":"6298e4cee53206cd","role":"helper","order":9,"level":1,"status":"ran_honours"},{"entry":"zeroed_observation","code_sha256":"b5cc72675b688b00","role":"helper","order":10,"level":1,"status":"ran_honours"},{"entry":"RandomProcess","code_sha256":"ab1c58fa8208bfec","role":"helper","order":11,"level":1,"status":"ran"}],"ran_individually":11,"ran_individually_constructed":8,"ran_individually_by_status":{"ran":8,"ran_fixture":1,"ran_honours":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"23abff1817f744af","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This class implements the Deep Deterministic Policy Gradient algorithm, an actor-critic model-free algorithm based on deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"a6abf3bfff439ec4","n_bricks":7,"bricks":[{"entry":"DDPG","code_sha256":"a6abf3bfff439ec4","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActorNet","code_sha256":"0d7cb0b9cab3eb74","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"ActorNet_bn","code_sha256":"883fbd58c181e487","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"CriticNet","code_sha256":"b616451b9c41d0be","role":"model","order":3,"level":0,"status":"unverified"},{"entry":"CriticNet_bn","code_sha256":"2961cc94350daaae","role":"helper","order":4,"level":0,"status":"unverified"},{"entry":"grad_inverter","code_sha256":"88db7be53206704c","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"batch_norm","code_sha256":"7484fd6def5722c7","role":"helper","order":6,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"28d7b860afb86a7d","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims this code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"train","entry_sha256":"7f073c276baecc11","n_bricks":2,"bricks":[{"entry":"train","code_sha256":"7f073c276baecc11","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ReplayBuffer","code_sha256":"532a74ad7f880104","role":"sampler","order":1,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"2af4d8a1de8e2b7a","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Agent","entry_sha256":"40c191818d46c0c5","n_bricks":2,"bricks":[{"entry":"Agent","code_sha256":"40c191818d46c0c5","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"normal_dist","code_sha256":"54074d019aff0495","role":"sampler","order":1,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"2c8427e0e63a41d1","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"eb9e7e016a76b1f8","n_bricks":1,"bricks":[{"entry":"DDPG","code_sha256":"eb9e7e016a76b1f8","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"2f139426e32a47a5","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Ddpg","entry_sha256":"95b0927e10c3dd78","n_bricks":2,"bricks":[{"entry":"Ddpg","code_sha256":"95b0927e10c3dd78","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Memory","code_sha256":"ccb0aa1ef035eb8e","role":"helper","order":1,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"3744f25c31de7afe","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, using target and local networks for both actor and critic.","centrality":"contribution","entry":"MADDPG_Agent","entry_sha256":"ed80a9cbb590756d","n_bricks":3,"bricks":[{"entry":"MADDPG_Agent","code_sha256":"ed80a9cbb590756d","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActorNetwork","code_sha256":"5869ee9ef41338a4","role":"model","order":1,"level":1,"status":"ran"},{"entry":"CriticNetwork","code_sha256":"b796e48c52beebc5","role":"model","order":2,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"3dee32cadc45408f","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Agent","entry_sha256":"beb77bbddb9714ae","n_bricks":6,"bricks":[{"entry":"Agent","code_sha256":"beb77bbddb9714ae","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"64db7b42a6e83850","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"b6d3efae859b7b5b","role":"model","order":2,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"f0163af304a40792","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"6258582b31c25005","role":"sampler","order":4,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":5,"level":1,"status":"ran_honours"}],"ran_individually":5,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"3e06a8c7ab5e471e","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"8fadcc5f80d1e9b5","n_bricks":3,"bricks":[{"entry":"DDPG","code_sha256":"8fadcc5f80d1e9b5","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"a4c895a75dcac04b","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"db5f4c6c0d3a50b4","role":"model","order":2,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"3f652ce5d4326917","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"d09f9c9f2dc485f8","n_bricks":7,"bricks":[{"entry":"DDPG","code_sha256":"d09f9c9f2dc485f8","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActorNet","code_sha256":"0d7cb0b9cab3eb74","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"ActorNet_bn","code_sha256":"883fbd58c181e487","role":"helper","order":2,"level":0,"status":"unverified"},{"entry":"CriticNet","code_sha256":"b616451b9c41d0be","role":"model","order":3,"level":0,"status":"unverified"},{"entry":"CriticNet_bn","code_sha256":"2961cc94350daaae","role":"helper","order":4,"level":0,"status":"unverified"},{"entry":"grad_inverter","code_sha256":"ff560a45eef0d026","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"batch_norm","code_sha256":"7484fd6def5722c7","role":"helper","order":6,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"3f776ca0f59565ee","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"dcb47558604bda70","n_bricks":12,"bricks":[{"entry":"DDPG","code_sha256":"dcb47558604bda70","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"976480803a792876","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"f93619eb32cfaf3d","role":"model","order":2,"level":1,"status":"ran"},{"entry":"OrnsteinUhlenbeckProcess","code_sha256":"37ebaf510f179bf4","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"SequentialMemory","code_sha256":"980051699184bfdd","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"fanin_init","code_sha256":"0d0842514b1844a1","role":"helper","order":5,"level":1,"status":"ran_fixture"},{"entry":"AnnealedGaussianProcess","code_sha256":"3ad5029d3ca03531","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"Memory","code_sha256":"a5e014313403ae12","role":"helper","order":7,"level":1,"status":"ran"},{"entry":"RingBuffer","code_sha256":"a3c118a9e035f7e4","role":"helper","order":8,"level":1,"status":"ran"},{"entry":"sample_batch_indexes","code_sha256":"6298e4cee53206cd","role":"helper","order":9,"level":1,"status":"ran_honours"},{"entry":"zeroed_observation","code_sha256":"b5cc72675b688b00","role":"helper","order":10,"level":1,"status":"ran_honours"},{"entry":"RandomProcess","code_sha256":"ab1c58fa8208bfec","role":"helper","order":11,"level":1,"status":"ran"}],"ran_individually":11,"ran_individually_constructed":8,"ran_individually_by_status":{"ran":8,"ran_fixture":1,"ran_honours":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"4324d10d32827a86","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPGAgent","entry_sha256":"d96fe6b321763c14","n_bricks":6,"bricks":[{"entry":"DDPGAgent","code_sha256":"d96fe6b321763c14","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"6d718c5a05a53b10","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"5029b7b1380f0988","role":"model","order":2,"level":1,"status":"ran"},{"entry":"OrnsteinUhlenbeckProcess","code_sha256":"ef85fd5d912b3855","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"79dfb108cab48c77","role":"sampler","order":4,"level":1,"status":"ran"},{"entry":"fanin_init","code_sha256":"825ecb6732e9fc31","role":"helper","order":5,"level":1,"status":"ran_fixture"}],"ran_individually":5,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4,"ran_fixture":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"4846ad338fbde244","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"51208e609141fcee","n_bricks":5,"bricks":[{"entry":"DDPG","code_sha256":"51208e609141fcee","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"8bd7d62053fbfae5","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"42b59cfab688e3f5","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"OUNoise","code_sha256":"046c7d82e0f35a06","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"48908dfdd43f1c2f","role":"sampler","order":4,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"4b601e5f92f24f81","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"run_ddpg","entry_sha256":"14b6d9e3982a117c","n_bricks":10,"bricks":[{"entry":"run_ddpg","code_sha256":"14b6d9e3982a117c","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"DDPGAgent","code_sha256":"b51369036ab5a352","role":"model","order":1,"level":1,"status":"ran"},{"entry":"get_env_spec","code_sha256":"cf7f0fe0d3ac16d9","role":"helper","order":2,"level":1,"status":"ran_draft_wrong"},{"entry":"set_log_dir","code_sha256":"e58c3a477f895e6c","role":"helper","order":3,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"4ea2dabac66df07c","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"a51e802f97dc5850","role":"helper","order":5,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"a15460ad3a6b391e","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"freeze","code_sha256":"a6b3153326abaddd","role":"helper","order":7,"level":0,"status":"unverified"},{"entry":"unfreeze","code_sha256":"24c0dee0fb0fec39","role":"helper","order":8,"level":0,"status":"unverified"},{"entry":"CircularBuffer","code_sha256":"59f7f71edc829572","role":"helper","order":9,"level":1,"status":"ran"}],"ran_individually":6,"ran_individually_constructed":5,"ran_individually_by_status":{"ran":5,"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"4d632ac3c373957c","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Agent","entry_sha256":"8950c65039fc4fe3","n_bricks":6,"bricks":[{"entry":"Agent","code_sha256":"8950c65039fc4fe3","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"2233e3bf2203e01d","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"7a433b7591cb1ad7","role":"model","order":2,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"d7af24edd798e11c","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"6258582b31c25005","role":"sampler","order":4,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":5,"level":1,"status":"ran_honours"}],"ran_individually":5,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"52dbca10bd4dd1b5","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"NAF","entry_sha256":"c3b2071edfe94da7","n_bricks":7,"bricks":[{"entry":"NAF","code_sha256":"c3b2071edfe94da7","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ReplayBuffer","code_sha256":"d8fadcf1cbc892d5","role":"sampler","order":1,"level":1,"status":"ran"},{"entry":"ReplayBufferPER","code_sha256":"05a3439d18f70f4b","role":"sampler","order":2,"level":0,"status":"unverified"},{"entry":"PrioritizedReplayBuffer","code_sha256":"b34e1d14d05b3345","role":"helper","order":3,"level":0,"status":"unverified"},{"entry":"MinSegmentTree","code_sha256":"7a8ccb9efbfef877","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"SumSegmentTree","code_sha256":"06dc39c20552ec26","role":"helper","order":5,"level":1,"status":"ran"},{"entry":"SegmentTree","code_sha256":"3d07d5a92b97866f","role":"helper","order":6,"level":1,"status":"ran"}],"ran_individually":4,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"56e4aae9562efa8c","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"AC_Off_POC_DDPG","entry_sha256":"f13dfb890ccc97a8","n_bricks":3,"bricks":[{"entry":"AC_Off_POC_DDPG","code_sha256":"f13dfb890ccc97a8","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"024ce7deaed96813","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"f2987dfa659c5d53","role":"model","order":2,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"5858e61727190ae7","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims this code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"8190363f4546bfd1","n_bricks":5,"bricks":[{"entry":"DDPG","code_sha256":"8190363f4546bfd1","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"75b2da574221eee2","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"c5b393b179d8d497","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"OUNoise","code_sha256":"046c7d82e0f35a06","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"48908dfdd43f1c2f","role":"sampler","order":4,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"5a98dbf6b7df4dab","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"An actor-critic, model-free algorithm based on the deterministic policy gradient that operates over continuous action spaces","centrality":"contribution","entry":"DDPG","entry_sha256":"dc719785d5a0b9f7","n_bricks":2,"bricks":[{"entry":"DDPG","code_sha256":"dc719785d5a0b9f7","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"0562ed655f21cba8","role":"sampler","order":1,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"5df767b245e70484","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Agent","entry_sha256":"684ee98628f58937","n_bricks":1,"bricks":[{"entry":"Agent","code_sha256":"684ee98628f58937","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"619824e8214c2b89","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPGAgent","entry_sha256":"4b11a27451c374cd","n_bricks":4,"bricks":[{"entry":"DDPGAgent","code_sha256":"4b11a27451c374cd","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"8afc63f093262b83","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"a36fc940a0f3eb1b","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"OU_noise","code_sha256":"e76268df8017c794","role":"sampler","order":3,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"6a36d557787ed8fb","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"ae6be9eb7b4764c8","n_bricks":5,"bricks":[{"entry":"DDPG","code_sha256":"ae6be9eb7b4764c8","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Prioritized_experience_replay","code_sha256":"b07dfe06f4498bba","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"Replay_Buffer","code_sha256":"66d85c7900951847","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"_actor_network","code_sha256":"ca95bd1bfa26d31f","role":"model","order":3,"level":1,"status":"ran"},{"entry":"_critic_network","code_sha256":"fe8293ee7abbf8aa","role":"model","order":4,"level":1,"status":"ran"}],"ran_individually":4,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"6a4d238888f8f3fa","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, as proposed in the paper.","centrality":"contribution","entry":"DDPG","entry_sha256":"28eeee629d33c0ad","n_bricks":1,"bricks":[{"entry":"DDPG","code_sha256":"28eeee629d33c0ad","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"6c13343efa1f8ffd","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Agent","entry_sha256":"b5564eaf87a00dd7","n_bricks":7,"bricks":[{"entry":"Agent","code_sha256":"b5564eaf87a00dd7","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"b7b4ba4db14ceff3","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"ba54cbfa6390641d","role":"model","order":2,"level":1,"status":"ran"},{"entry":"OrnsteinUhlenbeckProcess","code_sha256":"37ebaf510f179bf4","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"fanin_init","code_sha256":"825ecb6732e9fc31","role":"helper","order":4,"level":1,"status":"ran_fixture"},{"entry":"AnnealedGaussianProcess","code_sha256":"3ad5029d3ca03531","role":"helper","order":5,"level":1,"status":"ran"},{"entry":"RandomProcess","code_sha256":"ab1c58fa8208bfec","role":"helper","order":6,"level":1,"status":"ran"}],"ran_individually":7,"ran_individually_constructed":6,"ran_individually_by_status":{"ran":6,"ran_fixture":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"7467f26bf299b48f","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Actor","entry_sha256":"4abb7a0681b9f8e3","n_bricks":1,"bricks":[{"entry":"Actor","code_sha256":"4abb7a0681b9f8e3","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"75b425e7455741dc","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"397b92de9510f2f3","n_bricks":3,"bricks":[{"entry":"DDPG","code_sha256":"397b92de9510f2f3","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"b9b27fa7acc7c73f","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"d5cb870eb8408c73","role":"model","order":2,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"773437a2fdc4169a","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous control.","centrality":"contribution","entry":"DDPG","entry_sha256":"c328a2f2ee939de2","n_bricks":1,"bricks":[{"entry":"DDPG","code_sha256":"c328a2f2ee939de2","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"782c1a473cb79310","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This class implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, as proposed in the paper.","centrality":"contribution","entry":"ActorCriticNetworkContinuous","entry_sha256":"5223341b731ed4cb","n_bricks":3,"bricks":[{"entry":"ActorCriticNetworkContinuous","code_sha256":"5223341b731ed4cb","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"ActorCriticNetwork","code_sha256":"491a0ea3930828b7","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"NormalDistrLayer","code_sha256":"4fcd027380e5ca56","role":"model","order":2,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"7a29d8f92c8e0151","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, as proposed in the paper.","centrality":"contribution","entry":"Agent","entry_sha256":"caf348a3362776fb","n_bricks":6,"bricks":[{"entry":"Agent","code_sha256":"caf348a3362776fb","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"8062e958090e2e1f","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"2cee98e5475e680a","role":"model","order":2,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"21303179927140a0","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"6258582b31c25005","role":"sampler","order":4,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":5,"level":1,"status":"ran_honours"}],"ran_individually":5,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"7c28372ca99ab535","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, implemented in this code as the DDPG class.","centrality":"contribution","entry":"DDPG","entry_sha256":"499a19e5cb3d719d","n_bricks":5,"bricks":[{"entry":"DDPG","code_sha256":"499a19e5cb3d719d","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"ef0c12a6692597db","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"0872133cc6e7eee2","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"OUNoise","code_sha256":"046c7d82e0f35a06","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"48908dfdd43f1c2f","role":"helper","order":4,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"7db9923735b49314","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims this code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"ddpg_trainer","entry_sha256":"fa624e896014aa19","n_bricks":11,"bricks":[{"entry":"ddpg_trainer","code_sha256":"fa624e896014aa19","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Agent","code_sha256":"d7979806fed71eee","role":"model","order":1,"level":1,"status":"ran"},{"entry":"OUActionNoise","code_sha256":"ed77765a89c3c5ba","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"PendulumPlant","code_sha256":"eb1ba8dec1905c59","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"3869ba95ec3a2e1a","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"SimplePendulumEnv","code_sha256":"837dcd3ff834a51f","role":"helper","order":5,"level":1,"status":"ran"},{"entry":"Simulator","code_sha256":"1d2fffeddc2ad914","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"get_actor","code_sha256":"5f358d33ffd43ed3","role":"model","order":7,"level":1,"status":"ran_fixture"},{"entry":"get_critic","code_sha256":"a143a950a76e3523","role":"model","order":8,"level":1,"status":"ran_fixture"},{"entry":"get_arrow","code_sha256":"57f92caea351b30b","role":"helper","order":9,"level":1,"status":"ran_draft_wrong"},{"entry":"set_arrow_properties","code_sha256":"c6840dd2ce1ed774","role":"helper","order":10,"level":0,"status":"unverified"}],"ran_individually":9,"ran_individually_constructed":6,"ran_individually_by_status":{"ran":6,"ran_draft_wrong":1,"ran_fixture":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"7dc40ea6e071b1ad","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"77ca3b0e41fef94a","n_bricks":2,"bricks":[{"entry":"DDPG","code_sha256":"77ca3b0e41fef94a","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ExperienceReplay","code_sha256":"e60542a6e12b3525","role":"sampler","order":1,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"7f99fd231fb9ce40","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Agent","entry_sha256":"661322009d0d9169","n_bricks":6,"bricks":[{"entry":"Agent","code_sha256":"661322009d0d9169","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"c3081f2569beb64e","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"6e1fded857f54d7a","role":"model","order":2,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"7e2a8290108cb3ea","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"87674610395558bb","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":5,"level":1,"status":"ran_honours"}],"ran_individually":5,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"825277bfb421a534","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims this code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Agent","entry_sha256":"364b3433ab267478","n_bricks":6,"bricks":[{"entry":"Agent","code_sha256":"364b3433ab267478","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"59b451ca369c1de8","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"b78a712913941f90","role":"model","order":2,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"06e140e447cd7fb3","role":"sampler","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"6258582b31c25005","role":"sampler","order":4,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":5,"level":1,"status":"ran_honours"}],"ran_individually":5,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"829120e2e772e992","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Agents","entry_sha256":"dcf4d6df3ff30ac0","n_bricks":6,"bricks":[{"entry":"Agents","code_sha256":"dcf4d6df3ff30ac0","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"dc8d86e2dc6fd389","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"9af882c88cb87dda","role":"model","order":2,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"a169b2555a871836","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"6258582b31c25005","role":"sampler","order":4,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":5,"level":1,"status":"ran_honours"}],"ran_individually":5,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"83325fcb0085d203","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"84cb9968a76ef8e6","n_bricks":3,"bricks":[{"entry":"DDPG","code_sha256":"84cb9968a76ef8e6","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"6eca632bf823e7db","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"65567268c56c2f46","role":"model","order":2,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"83fe5afc7604b5ca","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"SAC","entry_sha256":"1be47476efdc31c1","n_bricks":15,"bricks":[{"entry":"SAC","code_sha256":"1be47476efdc31c1","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"BaseOffPolicy","code_sha256":"c836b46b3c210e6a","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"DoubleCritic","code_sha256":"8f17f70a798c9257","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"GaussianActor","code_sha256":"5b62ad877a674563","role":"model","order":3,"level":1,"status":"ran"},{"entry":"mse_loss","code_sha256":"d08ac0b87604485e","role":"helper","order":4,"level":1,"status":"ran_draft_wrong"},{"entry":"Logger","code_sha256":"416bd507555ea4fa","role":"helper","order":5,"level":1,"status":"ran"},{"entry":"ReplayMemory","code_sha256":"0d87c7101b2953f2","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"Rollout","code_sha256":"4618f3f110556784","role":"helper","order":7,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"40513685bd8b8200","role":"model","order":8,"level":1,"status":"ran"},{"entry":"GaussianPolicyHead","code_sha256":"d702970461989ce2","role":"model","order":9,"level":0,"status":"unverified"},{"entry":"Reduction","code_sha256":"adb269cf9b74e9a6","role":"helper","order":10,"level":0,"status":"unverified"},{"entry":"ValueHead","code_sha256":"1d6614860f0f4b57","role":"model","order":11,"level":1,"status":"ran"},{"entry":"_get_layer","code_sha256":"34bfe74d89d0491d","role":"helper","order":12,"level":1,"status":"ran_draft_wrong"},{"entry":"FactorizedNoisyLinear","code_sha256":"a75c153872d7f256","role":"helper","order":13,"level":1,"status":"ran"},{"entry":"IndependentNoisyLinear","code_sha256":"98596830b8e76bd9","role":"helper","order":14,"level":1,"status":"ran"}],"ran_individually":11,"ran_individually_constructed":8,"ran_individually_by_status":{"ran":9,"ran_draft_wrong":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"86052d13d9afa404","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, and this class implements the actor network component of that algorithm.","centrality":"component","entry":"MLPActor","entry_sha256":"6b17610b667cbc34","n_bricks":2,"bricks":[{"entry":"MLPActor","code_sha256":"6b17610b667cbc34","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"FCBody","code_sha256":"44abfcb21806cc13","role":"helper","order":1,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"86d8f385621f0bce","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This function implements the actor network of an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"policy","entry_sha256":"698f442074344c97","n_bricks":2,"bricks":[{"entry":"policy","code_sha256":"698f442074344c97","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"hist_summaries","code_sha256":"e78231c9f4eb9c2f","role":"helper","order":1,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"935f276f542f0be0","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, implemented here as the Actor class.","centrality":"contribution","entry":"Actor","entry_sha256":"da2a0693988d4238","n_bricks":2,"bricks":[{"entry":"Actor","code_sha256":"da2a0693988d4238","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":1,"level":1,"status":"ran_honours"}],"ran_individually":2,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"94002b2f6ce6ae77","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"ActorCriticDeterministic","entry_sha256":"c9b4479f17459322","n_bricks":3,"bricks":[{"entry":"ActorCriticDeterministic","code_sha256":"c9b4479f17459322","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"init_weights","code_sha256":"269f19cc9358c590","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"to_tensor","code_sha256":"f0945ef1933b173a","role":"helper","order":2,"level":1,"status":"ran_honours"}],"ran_individually":2,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"94194bb75c843d8f","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous control.","centrality":"contribution","entry":"DDPGAgent","entry_sha256":"76a41f814d76f5c0","n_bricks":5,"bricks":[{"entry":"DDPGAgent","code_sha256":"76a41f814d76f5c0","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"00d63e51f73faefb","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"55f075a92d493d35","role":"model","order":2,"level":1,"status":"ran"},{"entry":"HindsightExperienceReplayMemory","code_sha256":"cee4c46cd21980ff","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"OrnsteinUhlenbeckActionNoise","code_sha256":"642df90cf8f1851a","role":"helper","order":4,"level":1,"status":"ran"}],"ran_individually":4,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"99316fac409eb89b","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Agent","entry_sha256":"513584b85fd46561","n_bricks":5,"bricks":[{"entry":"Agent","code_sha256":"513584b85fd46561","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActorNetwork","code_sha256":"39110b4bbc0661d2","role":"model","order":1,"level":1,"status":"ran"},{"entry":"CriticNetwork","code_sha256":"c64a46f5ad45b01a","role":"model","order":2,"level":1,"status":"ran"},{"entry":"OUActionNoise","code_sha256":"ef632145448c9d94","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"7ebcb237f3ac8b6b","role":"sampler","order":4,"level":1,"status":"ran"}],"ran_individually":4,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"9aace1eddd6d2474","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims this code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPGController","entry_sha256":"078c84de4438f91b","n_bricks":4,"bricks":[{"entry":"DDPGController","code_sha256":"078c84de4438f91b","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"AgentMemory","code_sha256":"259742c65c2d6559","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"e48c1f362301c6a8","role":"model","order":2,"level":1,"status":"ran"},{"entry":"Policy","code_sha256":"4e16ab1aa52fc01f","role":"model","order":3,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"9d08d08e65db0120","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper proposes an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, implemented here as the Actor class which defines the policy network.","centrality":"contribution","entry":"Actor","entry_sha256":"b0866a4da4a62415","n_bricks":2,"bricks":[{"entry":"Actor","code_sha256":"b0866a4da4a62415","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":1,"level":1,"status":"ran_honours"}],"ran_individually":2,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"9d9628b94754b8fb","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous control.","centrality":"contribution","entry":"DDPG","entry_sha256":"1853e9d1db43078d","n_bricks":5,"bricks":[{"entry":"DDPG","code_sha256":"1853e9d1db43078d","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"f6231123b603e20f","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"cf0cfca323e5c3c4","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"OUNoise","code_sha256":"046c7d82e0f35a06","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"a1866c0223c9dca1","role":"sampler","order":4,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"9fb996564f47be5d","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Agent","entry_sha256":"584aca50891286f5","n_bricks":5,"bricks":[{"entry":"Agent","code_sha256":"584aca50891286f5","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"328c50f6e3095851","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"6e0920a743c03903","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"OUNoise","code_sha256":"affd388fecde62eb","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"6258582b31c25005","role":"sampler","order":4,"level":1,"status":"ran"}],"ran_individually":5,"ran_individually_constructed":5,"ran_individually_by_status":{"ran":5},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"a4abcc678a41282d","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims this code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPGAgent","entry_sha256":"5b513793c76f96d8","n_bricks":3,"bricks":[{"entry":"DDPGAgent","code_sha256":"5b513793c76f96d8","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"OrnsteinUhlenbeck","code_sha256":"cd47b224d263fba6","role":"data_transform","order":1,"level":0,"status":"unverified"},{"entry":"ReplayBuffer","code_sha256":"49ac8c4b2338f149","role":"sampler","order":2,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"a6b0c01430274b83","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"7c027fdd3a59bfb8","n_bricks":5,"bricks":[{"entry":"DDPG","code_sha256":"7c027fdd3a59bfb8","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"c5cbbbbfdd3a367c","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"6040d49d762613d7","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"PRNGKeys","code_sha256":"f6a31a3f71f0c87a","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"sn","code_sha256":"0374c56639501f7a","role":"helper","order":4,"level":0,"status":"unverified"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"a7eb3fe8dadcce7f","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, as proposed in the paper.","centrality":"contribution","entry":"ContinuousDeepQ","entry_sha256":"749aa0dd2a4c1d09","n_bricks":1,"bricks":[{"entry":"ContinuousDeepQ","code_sha256":"749aa0dd2a4c1d09","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ab3d4becf5043afe","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG_Agent","entry_sha256":"61958a4594b078dd","n_bricks":3,"bricks":[{"entry":"DDPG_Agent","code_sha256":"61958a4594b078dd","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"actor_netw","code_sha256":"417fff584ab90a11","role":"model","order":1,"level":1,"status":"ran"},{"entry":"critic_netw","code_sha256":"90cab8ba8631c2f8","role":"model","order":2,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ad26f00e02136613","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Actor","entry_sha256":"462527aca7c44cd5","n_bricks":2,"bricks":[{"entry":"Actor","code_sha256":"462527aca7c44cd5","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":1,"level":1,"status":"ran_honours"}],"ran_individually":2,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"b15fe936990cb2cb","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Agent","entry_sha256":"f3ea6018cdcc0b04","n_bricks":4,"bricks":[{"entry":"Agent","code_sha256":"f3ea6018cdcc0b04","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"8f5f60d9f1d5e30f","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"7f050e7ce4583465","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"ReplayBuffer","code_sha256":"031efd28ccd13e08","role":"sampler","order":3,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"b1c6a909072dc8f5","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"An actor-critic, model-free algorithm based on the deterministic policy gradient that operates over continuous action spaces","centrality":"contribution","entry":"DDPGAgent","entry_sha256":"fb2a2e6b4cc0d551","n_bricks":1,"bricks":[{"entry":"DDPGAgent","code_sha256":"fb2a2e6b4cc0d551","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"b258d6ccfb363b8e","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims this code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"4343e52712fa663d","n_bricks":3,"bricks":[{"entry":"DDPG","code_sha256":"4343e52712fa663d","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"1f1a916ff3cde3a5","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"111a712bc883469d","role":"model","order":2,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"b297b68b54988f2b","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper proposes an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"e8dad0570efe7ab9","n_bricks":5,"bricks":[{"entry":"DDPG","code_sha256":"e8dad0570efe7ab9","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"ef0c12a6692597db","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"0872133cc6e7eee2","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"OUNoise","code_sha256":"6d50e581fbec00bb","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"48908dfdd43f1c2f","role":"sampler","order":4,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"b5827c6082d2d907","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous control.","centrality":"contribution","entry":"DDPGAgent","entry_sha256":"c0e725d5bf9fb153","n_bricks":5,"bricks":[{"entry":"DDPGAgent","code_sha256":"c0e725d5bf9fb153","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActorNetwork","code_sha256":"375a3ee63ca7c68d","role":"model","order":1,"level":1,"status":"ran"},{"entry":"CriticNetwork","code_sha256":"6429748a5267bb8a","role":"model","order":2,"level":1,"status":"ran"},{"entry":"OUActionNoise","code_sha256":"ef632145448c9d94","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"7ebcb237f3ac8b6b","role":"sampler","order":4,"level":1,"status":"ran"}],"ran_individually":4,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"b65359aff4f7ea73","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims this code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG_agent","entry_sha256":"af8a78d9208cc109","n_bricks":1,"bricks":[{"entry":"DDPG_agent","code_sha256":"af8a78d9208cc109","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"baa02ded8155d9e6","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This code implements the actor part of an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"ActorNetwork","entry_sha256":"9c01f30e9f1052e8","n_bricks":1,"bricks":[{"entry":"ActorNetwork","code_sha256":"9c01f30e9f1052e8","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"bbd849fd1c40fc30","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, implemented as the DDPG agent.","centrality":"contribution","entry":"DDPG","entry_sha256":"ae000ab63f993f26","n_bricks":5,"bricks":[{"entry":"DDPG","code_sha256":"ae000ab63f993f26","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"017ef34f0499756e","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"4080c577fc710255","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"OUNoise","code_sha256":"046c7d82e0f35a06","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"48908dfdd43f1c2f","role":"helper","order":4,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"bf6e355f91e80d55","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, as proposed in the paper.","centrality":"contribution","entry":"DDPG","entry_sha256":"42c7eae4db28a7cb","n_bricks":8,"bricks":[{"entry":"DDPG","code_sha256":"42c7eae4db28a7cb","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActorNetwork","code_sha256":"fbe0975fffcc8005","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"CriticNetwork","code_sha256":"4644458fd0a4374e","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"LinearSchedule","code_sha256":"8496458fca8ba950","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"LogSchedule","code_sha256":"cada5e0bd569171d","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"88607f875726a410","role":"helper","order":5,"level":1,"status":"ran"},{"entry":"export_plot","code_sha256":"dfd2f69c5bd6bd73","role":"helper","order":6,"level":0,"status":"unverified"},{"entry":"get_logger","code_sha256":"0132cf6a5e04f2ad","role":"helper","order":7,"level":1,"status":"ran"}],"ran_individually":4,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"c051f003e5e54ca9","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"This code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, as proposed in the paper.","centrality":"contribution","entry":"Agent","entry_sha256":"2216995588e06169","n_bricks":1,"bricks":[{"entry":"Agent","code_sha256":"2216995588e06169","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"c46e5f0ceb121cf3","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, implemented in the Brain class which orchestrates the ActorNetwork and CriticNetwork.","centrality":"contribution","entry":"Brain","entry_sha256":"5fe982c3dc2394d3","n_bricks":5,"bricks":[{"entry":"Brain","code_sha256":"5fe982c3dc2394d3","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActorNetwork","code_sha256":"dff03781c5d0b378","role":"model","order":1,"level":1,"status":"ran_draft_wrong"},{"entry":"CriticNetwork","code_sha256":"6bb81ff3c30fb32a","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"OUActionNoise","code_sha256":"35d7e5f360ca6981","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"0d2b4efe0274fc66","role":"helper","order":4,"level":0,"status":"unverified"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1,"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"cd3c0f24c5b6f2ee","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"caf935ecdc9a432e","n_bricks":8,"bricks":[{"entry":"DDPG","code_sha256":"caf935ecdc9a432e","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Memory","code_sha256":"84a671ee7bad8513","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"NormalNoise","code_sha256":"d4f94d4568e6a3f3","role":"sampler","order":2,"level":1,"status":"ran"},{"entry":"OrnsteinUhlenbeckNoise","code_sha256":"132cdd71f41a5c43","role":"sampler","order":3,"level":1,"status":"ran"},{"entry":"actor","code_sha256":"dceb05d9d5cc7ee5","role":"model","order":4,"level":1,"status":"ran_fixture"},{"entry":"critic","code_sha256":"edb5292361905292","role":"model","order":5,"level":1,"status":"ran_fixture"},{"entry":"update_target_weights","code_sha256":"ac16f6e8f09e31bc","role":"update_rule","order":6,"level":0,"status":"unverified"},{"entry":"SumTree","code_sha256":"97e32fd094fe28c9","role":"helper","order":7,"level":0,"status":"unverified"}],"ran_individually":4,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":2,"ran_fixture":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"cfad4b4472ed9dcb","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"752f0cadbbfe89a3","n_bricks":4,"bricks":[{"entry":"DDPG","code_sha256":"752f0cadbbfe89a3","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"AbstractAgent","code_sha256":"424bf06f8d8eb998","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"a4c895a75dcac04b","role":"model","order":2,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"db5f4c6c0d3a50b4","role":"model","order":3,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d68837aaed5c6dca","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"cf91990d28ccf56a","n_bricks":5,"bricks":[{"entry":"DDPG","code_sha256":"cf91990d28ccf56a","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"BaseAgent","code_sha256":"2dd687e050a61476","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"TrajectoryBuffer","code_sha256":"58ee12a76b1fd1a1","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"Transition","code_sha256":"1652d7453e55d633","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"Buffer","code_sha256":"6f2b092fd868a348","role":"helper","order":4,"level":0,"status":"unverified"}],"ran_individually":3,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d72a8e9b303a30cb","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"a8bd327c1c912a9d","n_bricks":2,"bricks":[{"entry":"DDPG","code_sha256":"a8bd327c1c912a9d","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"ReplayMemory","code_sha256":"9d5ea952455199bc","role":"helper","order":1,"level":0,"status":"unverified"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d75ebed945db5b3a","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, as proposed in the paper.","centrality":"contribution","entry":"DDPG","entry_sha256":"3355949c0d857a6e","n_bricks":6,"bricks":[{"entry":"DDPG","code_sha256":"3355949c0d857a6e","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"BaseAgent","code_sha256":"ddcc51cfeb97e2a4","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"DDPGActor","code_sha256":"a5d631b897e1acb6","role":"model","order":2,"level":1,"status":"ran"},{"entry":"DDPGCritic","code_sha256":"7869f0d6349f369b","role":"model","order":3,"level":1,"status":"ran"},{"entry":"LinearLN","code_sha256":"83a88d1e71ef2df5","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"fan_in_uniform_init","code_sha256":"af08b37858b1dd07","role":"helper","order":5,"level":0,"status":"unverified"}],"ran_individually":3,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"df8ea20614f74358","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims this code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG_model","entry_sha256":"b2fbe2ad70b688a2","n_bricks":3,"bricks":[{"entry":"DDPG_model","code_sha256":"b2fbe2ad70b688a2","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor_network","code_sha256":"5c21d19fa9ff6b4b","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Critic_network","code_sha256":"e8ec892b92d9062e","role":"model","order":2,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"e05dd8378b51e5ad","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims this code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Actor","entry_sha256":"d96d6110c00ab9d4","n_bricks":2,"bricks":[{"entry":"Actor","code_sha256":"d96d6110c00ab9d4","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":1,"level":1,"status":"ran_honours"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1,"ran_honours":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"e0db7cd24aba773c","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"e88bf23758633506","n_bricks":3,"bricks":[{"entry":"DDPG","code_sha256":"e88bf23758633506","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Buffer","code_sha256":"96855c8d20a0088b","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"OUActionNoise","code_sha256":"ed77765a89c3c5ba","role":"helper","order":2,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"e2985836f7078e60","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"ActorNetwork","entry_sha256":"abffeadabe12af6b","n_bricks":1,"bricks":[{"entry":"ActorNetwork","code_sha256":"abffeadabe12af6b","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"e9a07a0089b67d54","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper proposes an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"Actor","entry_sha256":"0d51c1e5212918ec","n_bricks":1,"bricks":[{"entry":"Actor","code_sha256":"0d51c1e5212918ec","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ebc550f5cc7160fb","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The code implements an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces.","centrality":"contribution","entry":"DDPG","entry_sha256":"b861cffa858f460c","n_bricks":4,"bricks":[{"entry":"DDPG","code_sha256":"b861cffa858f460c","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"8f5c14d98d39f3b9","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"4c5d9db3e7d648c9","role":"model","order":2,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"1229a5d8dea62487","role":"sampler","order":3,"level":0,"status":"unverified"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"f0c588b70084933d","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"The paper claims an actor-critic, model-free algorithm based on the deterministic policy gradient for continuous action spaces, which this code implements as the Soft Actor-Critic (SAC) algorithm.","centrality":"contribution","entry":"SACModel","entry_sha256":"7b82c41b5ad0e056","n_bricks":10,"bricks":[{"entry":"SACModel","code_sha256":"7b82c41b5ad0e056","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"EncoderType","code_sha256":"9c10e0c8cad8f8a1","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"LearningModel","code_sha256":"c3809b45fe3af363","role":"helper","order":2,"level":0,"status":"unverified"},{"entry":"LearningRateSchedule","code_sha256":"709bf3140064269c","role":"helper","order":3,"level":0,"status":"unverified"},{"entry":"SACPolicyNetwork","code_sha256":"8a1d8ca5ca9e0472","role":"model","order":4,"level":0,"status":"unverified"},{"entry":"SACTargetNetwork","code_sha256":"ac81a4e465c9a89b","role":"model","order":5,"level":0,"status":"unverified"},{"entry":"CameraResolution","code_sha256":"222a72ff1d084586","role":"helper","order":6,"level":0,"status":"unverified"},{"entry":"UnityTrainerException","code_sha256":"28af75dd1e756e4d","role":"helper","order":7,"level":0,"status":"unverified"},{"entry":"SACNetwork","code_sha256":"338005115fd3efac","role":"helper","order":8,"level":0,"status":"unverified"},{"entry":"UnityException","code_sha256":"2d6179a73f14ca5e","role":"helper","order":9,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"f397dc4ab99713eb","source_kind":"harvested","method_name":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","graph_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","realizes_severed":false,"claim":"An actor-critic, model-free algorithm based on the deterministic policy gradient that operates over continuous action spaces","centrality":"contribution","entry":"DDPG","entry_sha256":"a7f923df06fb12c2","n_bricks":3,"bricks":[{"entry":"DDPG","code_sha256":"a7f923df06fb12c2","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"200b44ea7ead9ab6","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"daeec7442740e76e","role":"model","order":2,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"d26da227b9b6","n_siblings":83,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"}],"assembly_sibling_groups":[{"group":"d26da227b9b6","realizes_method":"actor-critic, model-free algorithm based on the deterministic policy gradient","source_kind":"harvested","batch_at":"2026-09-09T22:44:46+00:00","members":["014471cd2234f3f4","042dd9e9176954eb","0fe228f97c750fd9","14a213be39fc4d33","16df799befa89075","1860bac79d379492","192705a305cf407b","1a123d5d6a10efe9","23425bc3067b1f80","23abff1817f744af","28d7b860afb86a7d","2af4d8a1de8e2b7a","2c8427e0e63a41d1","2f139426e32a47a5","3744f25c31de7afe","3dee32cadc45408f","3e06a8c7ab5e471e","3f652ce5d4326917","3f776ca0f59565ee","4324d10d32827a86","4846ad338fbde244","4b601e5f92f24f81","4d632ac3c373957c","52dbca10bd4dd1b5","56e4aae9562efa8c","5858e61727190ae7","5a98dbf6b7df4dab","5df767b245e70484","619824e8214c2b89","6a36d557787ed8fb","6a4d238888f8f3fa","6c13343efa1f8ffd","7467f26bf299b48f","75b425e7455741dc","773437a2fdc4169a","782c1a473cb79310","7a29d8f92c8e0151","7c28372ca99ab535","7db9923735b49314","7dc40ea6e071b1ad","7f99fd231fb9ce40","825277bfb421a534","829120e2e772e992","83325fcb0085d203","83fe5afc7604b5ca","86052d13d9afa404","86d8f385621f0bce","935f276f542f0be0","94002b2f6ce6ae77","94194bb75c843d8f","99316fac409eb89b","9aace1eddd6d2474","9d08d08e65db0120","9d9628b94754b8fb","9fb996564f47be5d","a4abcc678a41282d","a6b0c01430274b83","a7eb3fe8dadcce7f","ab3d4becf5043afe","ad26f00e02136613","b15fe936990cb2cb","b1c6a909072dc8f5","b258d6ccfb363b8e","b297b68b54988f2b","b5827c6082d2d907","b65359aff4f7ea73","baa02ded8155d9e6","bbd849fd1c40fc30","bf6e355f91e80d55","c051f003e5e54ca9","c46e5f0ceb121cf3","cd3c0f24c5b6f2ee","cfad4b4472ed9dcb","d68837aaed5c6dca","d72a8e9b303a30cb","d75ebed945db5b3a","df8ea20614f74358","e05dd8378b51e5ad","e0db7cd24aba773c","e2985836f7078e60","e9a07a0089b67d54","ebc550f5cc7160fb","f0c588b70084933d","f397dc4ab99713eb"]}],"assemblies_is":{"about":"What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results.","harvested":"assembled from code harvested from a repository linked to the paper","generated":"generated from the paper text, not the repository's code","end_to_end":"for a harvested assembly, the assembly has not been run end-to-end; for a generated one, end_to_end.level is the assembly's own level and against_independent_peer says whether it ran against a peer: an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists","bricks_level":"each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level","ran_individually":"a COUNT of bricks that ran on their own on a fixture (split by status in ran_individually_by_status), not a level; instrument statuses are failures of Syntology's instrument, not of the code","siblings":"assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another","judged":"Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as \"by construction\" or \"not judged by a model\"","level_lowered":"a generated assembly whose level Syntology's graph lowered, with the level it had, the recorded reason and when","retention":"Syntology's spending triage for further verification, not a verdict","claim_match":"the claim_match vote: IMPLEMENTS, COMPONENT or UNCLEAR. Where claim_match_basis is \"judge:<model>\", it is one model's judgement of the assembly's label against the paper's claim (claim_match_rule single_judge, the model in claim_match_judges): not a verification and not a run. Where it is \"construction\", the value was set when the code was generated for this method and no model judged it, whatever claim_match_rule says. The page prints no claim match for any assembly","label_verdict":"whether the assembly's code is the method it is labelled with: matches, cannot_tell, mislabelled (suggested_method names what it looks like instead) or not_the_method; label_verdict_judged is true only when a model read the code (claim_match_basis \"judge:<model>\")","label_verdict_judged":"where true (claim_match_basis \"judge:<model>\"), label_verdict is a single model's judgement; not calibrated; not printed on the page; where false, it was set by construction, and the page prints it unless the node is shared with another paper (node_properties_written_for)","claim":"the claim text stored on the assembly node: for a harvested assembly, what the paper claims the code implements, as the lifting model wrote it; for a generated one, the specification the code was generated from. Not verified text","centrality":"how central the lifted method is to the paper, as the lifting step recorded it: contribution, component or incidental","v3_tests_passed_both_sides":"end_to_end.v3_tests_passed_both_sides: the number of property tests derived from the paper that passed on both implementations, as the attached report lists them; a level 3 card with 0 says its report lists none","ran_individually_constructed":"ran_individually_constructed: of the bricks counted in ran_individually, how many constructed an object rather than computing a result (Syntology's RAN record's rule, read from the graph-layer sample with the brick's code_sha256); a part of ran_individually, never subtracted from it and never a failure; null where a brick that ran has no sample in the graph layer this build read, so the figure was not counted"},"assemblies_call":{"tool":"assembly","arguments":{"arxiv_id":"1509.02971"},"call":"assembly(arxiv_id=\"1509.02971\")"},"read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/1509.02971.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/1509.02971.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hill-a/stable-baselines","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DLR-RM/stable-baselines3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/prajwalgatti/DRL-Continuous-Control","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/Horizon","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IvanVigor/MADDPG-Unity","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/b06b01073/continuous-control","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MathPhysSim/PER-NAF","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/majercakdavid/gym-virtual-quant-trading","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/s-sd/task-amenability","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KAIST-AILab/deeprl_practice_colab","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nav74neet/ddpg_biped","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YangRui2015/Modular_HER","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/flavioschneider/ml_papers_presentations","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nav74neet/rl4biped","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/T3chy/DDPG","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gwthomas/gtml","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SaminYeasar/off_policy_ac","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tegg89/magnn","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/siyuofzhou/DDPG","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/abbadka/quadcopter","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ray-project/ray/tree/master/rllib","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Sheldonmao/Learning-To-walk","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jakegrigsby/deep_control/blob/master/deep_control/ddpg.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/toni-sm/skrl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/krasing/DRLearningCollaboration","reach":null}],"summary":{"ran":149,"ran_draft_wrong":5,"ran_fixture":6,"ran_honours":3,"unverified":143},"n_samples":306,"n_ran":163,"n_constructed":126,"n_ran_checked":152,"n_instrument":11,"n_unverified":143,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"listed":{"samples":305,"ran":162,"n_ran_checked":152,"n_instrument":10,"repositories":87},"unlocated":{"samples":1,"ran":1,"n_ran_checked":0,"n_instrument":1,"repositories":0,"is":"identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded"}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":163,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing","signature_not_shown":"the graph records a signature for this sample and it is not shown; signature_not_shown_because names why, as the export's field-exclusion reason","signature_not_shown_because":{"signature_is_harness_probe_not_fixture_args":"for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments"}},"n_ran_with_level_date":163,"n_ran_without_level_date":0,"n_ran_signature_not_shown":22,"levels_written_between":{"first":"2026-09-22","last":"2026-09-26","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","census_is":"Syntology's function-name census ran implementations with this entry name on one shared input per bucket (the positional rank, kind and dtype of each array argument) and counted the distinct output digests (sha256 of the output rounded to 6 decimals). implementations and papers count the compared samples; distinct_outputs counts digests across all buckets; n_buckets is how many shared inputs were used. It is not a statement that any two samples compute one thing, and the name is a string, not an identity.","samples":[{"code_sha256":"f13dfb890ccc97a8","code_sha256_prefix":"f13dfb890ccc97a8","entry":"AC_Off_POC_DDPG","repo":"baturaysaglam/ac-off-poc","repo_kind":"listed","path":"DDPG & TD3/AC_Off_POC_DDPG.py","file_url":"https://github.com/baturaysaglam/ac-off-poc/blob/HEAD/DDPG%20%26%20TD3/AC_Off_POC_DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"AC_Off_POC_DDPG","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f13dfb890ccc97a8"}},{"code_sha256":"fb986aef8cb19dcb","code_sha256_prefix":"fb986aef8cb19dcb","entry":"Actor","repo":"ghliu/pytorch-ddpg","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/ghliu/pytorch-ddpg/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"fb986aef8cb19dcb"},"code_page":"/code/actor","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"fb986aef8cb19dcb"}},{"code_sha256":"64db7b42a6e83850","code_sha256_prefix":"64db7b42a6e83850","entry":"Actor","repo":"iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"64db7b42a6e83850"},"code_page":"/code/actor","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"64db7b42a6e83850"}},{"code_sha256":"976480803a792876","code_sha256_prefix":"976480803a792876","entry":"Actor","repo":"TheInfamousWayne/ddpg","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/TheInfamousWayne/ddpg/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"976480803a792876"},"code_page":"/code/actor","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"976480803a792876"}},{"code_sha256":"6d718c5a05a53b10","code_sha256_prefix":"6d718c5a05a53b10","entry":"Actor","repo":"J93T/TP4-DDPG","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/J93T/TP4-DDPG/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, J93T/TP4-DDPG when it was checked","mcp_get_code":{"code_sha256":"6d718c5a05a53b10"}},{"code_sha256":"4ea2dabac66df07c","code_sha256_prefix":"4ea2dabac66df07c","entry":"Actor","repo":"HJDQN/HJQ","repo_kind":"listed","path":"algorithms/ddpg/ddpg.py","file_url":"https://github.com/HJDQN/HJQ/blob/HEAD/algorithms/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"4ea2dabac66df07c"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, HJDQN/HJQ when it was checked","mcp_get_code":{"code_sha256":"4ea2dabac66df07c"}},{"code_sha256":"2233e3bf2203e01d","code_sha256_prefix":"2233e3bf2203e01d","entry":"Actor","repo":"IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"2233e3bf2203e01d"},"code_page":"/code/actor","census":null,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"2233e3bf2203e01d"}},{"code_sha256":"024ce7deaed96813","code_sha256_prefix":"024ce7deaed96813","entry":"Actor","repo":"baturaysaglam/ac-off-poc","repo_kind":"listed","path":"DDPG & TD3/AC_Off_POC_DDPG.py","file_url":"https://github.com/baturaysaglam/ac-off-poc/blob/HEAD/DDPG%20%26%20TD3/AC_Off_POC_DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"024ce7deaed96813"},"code_page":"/code/actor","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"024ce7deaed96813"}},{"code_sha256":"b7b4ba4db14ceff3","code_sha256_prefix":"b7b4ba4db14ceff3","entry":"Actor","repo":"b06b01073/continuous-control","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/b06b01073/continuous-control/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, b06b01073/continuous-control when it was checked","mcp_get_code":{"code_sha256":"b7b4ba4db14ceff3"}},{"code_sha256":"8062e958090e2e1f","code_sha256_prefix":"8062e958090e2e1f","entry":"Actor","repo":"ZainRaza14/deepRL","repo_kind":"listed","path":"DDPG/ddpg_agent.py","file_url":"https://github.com/ZainRaza14/deepRL/blob/HEAD/DDPG/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"8062e958090e2e1f"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZainRaza14/deepRL when it was checked","mcp_get_code":{"code_sha256":"8062e958090e2e1f"}},{"code_sha256":"c3081f2569beb64e","code_sha256_prefix":"c3081f2569beb64e","entry":"Actor","repo":"madhur-tandon/RL-Project","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/madhur-tandon/RL-Project/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, madhur-tandon/RL-Project when it was checked","mcp_get_code":{"code_sha256":"c3081f2569beb64e"}},{"code_sha256":"59b451ca369c1de8","code_sha256_prefix":"59b451ca369c1de8","entry":"Actor","repo":"biemann/Continuous-Control","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/biemann/Continuous-Control/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"59b451ca369c1de8"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, biemann/Continuous-Control when it was checked","mcp_get_code":{"code_sha256":"59b451ca369c1de8"}},{"code_sha256":"dc8d86e2dc6fd389","code_sha256_prefix":"dc8d86e2dc6fd389","entry":"Actor","repo":"krasing/DRLearningContinuousControl","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/krasing/DRLearningContinuousControl/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"dc8d86e2dc6fd389"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, krasing/DRLearningContinuousControl when it was checked","mcp_get_code":{"code_sha256":"dc8d86e2dc6fd389"}},{"code_sha256":"6eca632bf823e7db","code_sha256_prefix":"6eca632bf823e7db","entry":"Actor","repo":"baturaysaglam/RIS-MISO-Deep-Reinforcement-Learning","repo_kind":"listed","path":"DDPG.py","file_url":"https://github.com/baturaysaglam/RIS-MISO-Deep-Reinforcement-Learning/blob/HEAD/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"6eca632bf823e7db"},"code_page":"/code/actor","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6eca632bf823e7db"}},{"code_sha256":"da2a0693988d4238","code_sha256_prefix":"da2a0693988d4238","entry":"Actor","repo":"SergiPonsa/Reinforcement-Learning-Sergi","repo_kind":"listed","path":"ddpg pendulum/model_comented.py","file_url":"https://github.com/SergiPonsa/Reinforcement-Learning-Sergi/blob/HEAD/ddpg%20pendulum/model_comented.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/actor","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"da2a0693988d4238"}},{"code_sha256":"00d63e51f73faefb","code_sha256_prefix":"00d63e51f73faefb","entry":"Actor","repo":"hemilpanchiwala/Hindsight-Experience-Replay","repo_kind":"listed","path":"ddpg_with_her/DDPGAgent.py","file_url":"https://github.com/hemilpanchiwala/Hindsight-Experience-Replay/blob/HEAD/ddpg_with_her/DDPGAgent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hemilpanchiwala/Hindsight-Experience-Replay when it was checked","mcp_get_code":{"code_sha256":"00d63e51f73faefb"}},{"code_sha256":"b0866a4da4a62415","code_sha256_prefix":"b0866a4da4a62415","entry":"Actor","repo":"krasing/DRLearningCollaboration","repo_kind":"listed","path":"model.py","file_url":"https://github.com/krasing/DRLearningCollaboration/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"b0866a4da4a62415"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, krasing/DRLearningCollaboration when it was checked","mcp_get_code":{"code_sha256":"b0866a4da4a62415"}},{"code_sha256":"328c50f6e3095851","code_sha256_prefix":"328c50f6e3095851","entry":"Actor","repo":"claudeHifly/BipedalWalker-v3","repo_kind":"listed","path":"DDPG/ddpg_agent.py","file_url":"https://github.com/claudeHifly/BipedalWalker-v3/blob/HEAD/DDPG/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"328c50f6e3095851"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, claudeHifly/BipedalWalker-v3 when it was checked","mcp_get_code":{"code_sha256":"328c50f6e3095851"}},{"code_sha256":"462527aca7c44cd5","code_sha256_prefix":"462527aca7c44cd5","entry":"Actor","repo":"wwydmanski/rl_tennis","repo_kind":"listed","path":"brain/model.py","file_url":"https://github.com/wwydmanski/rl_tennis/blob/HEAD/brain/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"462527aca7c44cd5"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, wwydmanski/rl_tennis when it was checked","mcp_get_code":{"code_sha256":"462527aca7c44cd5"}},{"code_sha256":"1f1a916ff3cde3a5","code_sha256_prefix":"1f1a916ff3cde3a5","entry":"Actor","repo":"ZiyangY/IndProject-RL-in-Supply-chain","repo_kind":"listed","path":"DDPG-based RNN/DDPG.py","file_url":"https://github.com/ZiyangY/IndProject-RL-in-Supply-chain/blob/HEAD/DDPG-based%20RNN/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZiyangY/IndProject-RL-in-Supply-chain when it was checked","mcp_get_code":{"code_sha256":"1f1a916ff3cde3a5"}},{"code_sha256":"d96d6110c00ab9d4","code_sha256_prefix":"d96d6110c00ab9d4","entry":"Actor","repo":"iDataist/Tennis-With-Multi-Agent-Reinforcement","repo_kind":"listed","path":"model.py","file_url":"https://github.com/iDataist/Tennis-With-Multi-Agent-Reinforcement/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"state:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"d96d6110c00ab9d4"},"code_page":"/code/actor","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d96d6110c00ab9d4"}},{"code_sha256":"8f5c14d98d39f3b9","code_sha256_prefix":"8f5c14d98d39f3b9","entry":"Actor","repo":"Philori22/DDPG-aigym","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/Philori22/DDPG-aigym/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"x:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"8f5c14d98d39f3b9"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Philori22/DDPG-aigym when it was checked","mcp_get_code":{"code_sha256":"8f5c14d98d39f3b9"}},{"code_sha256":"200b44ea7ead9ab6","code_sha256_prefix":"200b44ea7ead9ab6","entry":"Actor","repo":"SaminYeasar/off_policy_ac","repo_kind":"listed","path":"DDPG/DDPG.py","file_url":"https://github.com/SaminYeasar/off_policy_ac/blob/HEAD/DDPG/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"x:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"200b44ea7ead9ab6"},"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, SaminYeasar/off_policy_ac when it was checked","mcp_get_code":{"code_sha256":"200b44ea7ead9ab6"}},{"code_sha256":"c9b4479f17459322","code_sha256_prefix":"c9b4479f17459322","entry":"ActorCriticDeterministic","repo":"Medabid1/RL_Project","repo_kind":"listed","path":"network/Networks.py","file_url":"https://github.com/Medabid1/RL_Project/blob/HEAD/network/Networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ActorCriticDeterministic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Medabid1/RL_Project when it was checked","mcp_get_code":{"code_sha256":"c9b4479f17459322"}},{"code_sha256":"491a0ea3930828b7","code_sha256_prefix":"491a0ea3930828b7","entry":"ActorCriticNetwork","repo":"arnomoonens/yarll","repo_kind":"listed","path":"yarll/agents/tf2/actorcritic/actor_critic.py","file_url":"https://github.com/arnomoonens/yarll/blob/HEAD/yarll/agents/tf2/actorcritic/actor_critic.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ActorCriticNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/actorcriticnetwork","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"491a0ea3930828b7"}},{"code_sha256":"5223341b731ed4cb","code_sha256_prefix":"5223341b731ed4cb","entry":"ActorCriticNetworkContinuous","repo":"arnomoonens/yarll","repo_kind":"listed","path":"yarll/agents/tf2/actorcritic/actor_critic.py","file_url":"https://github.com/arnomoonens/yarll/blob/HEAD/yarll/agents/tf2/actorcritic/actor_critic.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ActorCriticNetworkContinuous","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5223341b731ed4cb"}},{"code_sha256":"1e7906d3e94a41ce","code_sha256_prefix":"1e7906d3e94a41ce","entry":"ActorNet","repo":"xtma/simple-pytorch-rl","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/xtma/simple-pytorch-rl/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"ActorNet","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xtma/simple-pytorch-rl when it was checked","mcp_get_code":{"code_sha256":"1e7906d3e94a41ce"}},{"code_sha256":"5869ee9ef41338a4","code_sha256_prefix":"5869ee9ef41338a4","entry":"ActorNetwork","repo":"sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3","repo_kind":"listed","path":"maddpgAgent.py","file_url":"https://github.com/sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3/blob/HEAD/maddpgAgent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"ActorNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3 when it was checked","mcp_get_code":{"code_sha256":"5869ee9ef41338a4"}},{"code_sha256":"39110b4bbc0661d2","code_sha256_prefix":"39110b4bbc0661d2","entry":"ActorNetwork","repo":"T3chy/DDPG","repo_kind":"listed","path":"ddpg_torch.py","file_url":"https://github.com/T3chy/DDPG/blob/HEAD/ddpg_torch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"ActorNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"39110b4bbc0661d2"},"code_page":null,"census":null,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, T3chy/DDPG, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"39110b4bbc0661d2"}},{"code_sha256":"375a3ee63ca7c68d","code_sha256_prefix":"375a3ee63ca7c68d","entry":"ActorNetwork","repo":"KelvinYang0320/deepbots-panda","repo_kind":"listed","path":"Panda_RL/controllers/robot_supervisor_manager/agent/ddpg.py","file_url":"https://github.com/KelvinYang0320/deepbots-panda/blob/HEAD/Panda_RL/controllers/robot_supervisor_manager/agent/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"ActorNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"375a3ee63ca7c68d"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"375a3ee63ca7c68d"}},{"code_sha256":"dff03781c5d0b378","code_sha256_prefix":"dff03781c5d0b378","entry":"ActorNetwork","repo":"samuelmat19/DDPG-tf2","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/samuelmat19/DDPG-tf2/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"num_states:int/0/int, num_actions:int/0/int, action_high:int/0/int","fixture_out_type":"Functional","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"dff03781c5d0b378"}},{"code_sha256":"7167793e1651d552","code_sha256_prefix":"7167793e1651d552","entry":"Agent","repo":"xtma/simple-pytorch-rl","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/xtma/simple-pytorch-rl/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Agent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xtma/simple-pytorch-rl when it was checked","mcp_get_code":{"code_sha256":"7167793e1651d552"}},{"code_sha256":"b5564eaf87a00dd7","code_sha256_prefix":"b5564eaf87a00dd7","entry":"Agent","repo":"b06b01073/continuous-control","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/b06b01073/continuous-control/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Agent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, b06b01073/continuous-control when it was checked","mcp_get_code":{"code_sha256":"b5564eaf87a00dd7"}},{"code_sha256":"d7979806fed71eee","code_sha256_prefix":"d7979806fed71eee","entry":"Agent","repo":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","repo_kind":"listed","path":"software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","file_url":"https://github.com/dfki-ric-underactuated-lab/torque_limited_simple_pendulum/blob/HEAD/software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Agent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/agent","census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d7979806fed71eee"}},{"code_sha256":"584aca50891286f5","code_sha256_prefix":"584aca50891286f5","entry":"Agent","repo":"claudeHifly/BipedalWalker-v3","repo_kind":"listed","path":"DDPG/ddpg_agent.py","file_url":"https://github.com/claudeHifly/BipedalWalker-v3/blob/HEAD/DDPG/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Agent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, claudeHifly/BipedalWalker-v3 when it was checked","mcp_get_code":{"code_sha256":"584aca50891286f5"}},{"code_sha256":"259742c65c2d6559","code_sha256_prefix":"259742c65c2d6559","entry":"AgentMemory","repo":"guillaumeboniface/reacher","repo_kind":"listed","path":"ddpg_controller.py","file_url":"https://github.com/guillaumeboniface/reacher/blob/HEAD/ddpg_controller.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"AgentMemory","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, guillaumeboniface/reacher when it was checked","mcp_get_code":{"code_sha256":"259742c65c2d6559"}},{"code_sha256":"3ad5029d3ca03531","code_sha256_prefix":"3ad5029d3ca03531","entry":"AnnealedGaussianProcess","repo":"fshamshirdar/pytorch-rdpg","repo_kind":"listed","path":"rdpg.py","file_url":"https://github.com/fshamshirdar/pytorch-rdpg/blob/HEAD/rdpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"AnnealedGaussianProcess","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, fshamshirdar/pytorch-rdpg when it was checked","mcp_get_code":{"code_sha256":"3ad5029d3ca03531"}},{"code_sha256":"59f7f71edc829572","code_sha256_prefix":"59f7f71edc829572","entry":"CircularBuffer","repo":"HJDQN/HJQ","repo_kind":"listed","path":"algorithms/ddpg/ddpg.py","file_url":"https://github.com/HJDQN/HJQ/blob/HEAD/algorithms/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"CircularBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, HJDQN/HJQ when it was checked","mcp_get_code":{"code_sha256":"59f7f71edc829572"}},{"code_sha256":"060c46e5cc508cc5","code_sha256_prefix":"060c46e5cc508cc5","entry":"Critic","repo":"fshamshirdar/pytorch-rdpg","repo_kind":"listed","path":"rdpg.py","file_url":"https://github.com/fshamshirdar/pytorch-rdpg/blob/HEAD/rdpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, fshamshirdar/pytorch-rdpg when it was checked","mcp_get_code":{"code_sha256":"060c46e5cc508cc5"}},{"code_sha256":"4210d97aa24222d8","code_sha256_prefix":"4210d97aa24222d8","entry":"Critic","repo":"dpoulopoulos/drl_collaborate_compete","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/dpoulopoulos/drl_collaborate_compete/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dpoulopoulos/drl_collaborate_compete when it was checked","mcp_get_code":{"code_sha256":"4210d97aa24222d8"}},{"code_sha256":"f93619eb32cfaf3d","code_sha256_prefix":"f93619eb32cfaf3d","entry":"Critic","repo":"ghliu/pytorch-ddpg","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/ghliu/pytorch-ddpg/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f93619eb32cfaf3d"}},{"code_sha256":"b6d3efae859b7b5b","code_sha256_prefix":"b6d3efae859b7b5b","entry":"Critic","repo":"iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b6d3efae859b7b5b"}},{"code_sha256":"db5f4c6c0d3a50b4","code_sha256_prefix":"db5f4c6c0d3a50b4","entry":"Critic","repo":"VasaKiDD/TD3-deep-rl-research","repo_kind":"listed","path":"agent/DDPG.py","file_url":"https://github.com/VasaKiDD/TD3-deep-rl-research/blob/HEAD/agent/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"db5f4c6c0d3a50b4"}},{"code_sha256":"5029b7b1380f0988","code_sha256_prefix":"5029b7b1380f0988","entry":"Critic","repo":"J93T/TP4-DDPG","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/J93T/TP4-DDPG/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, J93T/TP4-DDPG when it was checked","mcp_get_code":{"code_sha256":"5029b7b1380f0988"}},{"code_sha256":"a51e802f97dc5850","code_sha256_prefix":"a51e802f97dc5850","entry":"Critic","repo":"HJDQN/HJQ","repo_kind":"listed","path":"algorithms/ddpg/ddpg.py","file_url":"https://github.com/HJDQN/HJQ/blob/HEAD/algorithms/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, HJDQN/HJQ when it was checked","mcp_get_code":{"code_sha256":"a51e802f97dc5850"}},{"code_sha256":"7a433b7591cb1ad7","code_sha256_prefix":"7a433b7591cb1ad7","entry":"Critic","repo":"IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"7a433b7591cb1ad7"}},{"code_sha256":"f2987dfa659c5d53","code_sha256_prefix":"f2987dfa659c5d53","entry":"Critic","repo":"baturaysaglam/ac-off-poc","repo_kind":"listed","path":"DDPG & TD3/AC_Off_POC_DDPG.py","file_url":"https://github.com/baturaysaglam/ac-off-poc/blob/HEAD/DDPG%20%26%20TD3/AC_Off_POC_DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f2987dfa659c5d53"}},{"code_sha256":"ba54cbfa6390641d","code_sha256_prefix":"ba54cbfa6390641d","entry":"Critic","repo":"b06b01073/continuous-control","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/b06b01073/continuous-control/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, b06b01073/continuous-control when it was checked","mcp_get_code":{"code_sha256":"ba54cbfa6390641d"}},{"code_sha256":"2cee98e5475e680a","code_sha256_prefix":"2cee98e5475e680a","entry":"Critic","repo":"ZainRaza14/deepRL","repo_kind":"listed","path":"DDPG/ddpg_agent.py","file_url":"https://github.com/ZainRaza14/deepRL/blob/HEAD/DDPG/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZainRaza14/deepRL when it was checked","mcp_get_code":{"code_sha256":"2cee98e5475e680a"}},{"code_sha256":"6e1fded857f54d7a","code_sha256_prefix":"6e1fded857f54d7a","entry":"Critic","repo":"madhur-tandon/RL-Project","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/madhur-tandon/RL-Project/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, madhur-tandon/RL-Project when it was checked","mcp_get_code":{"code_sha256":"6e1fded857f54d7a"}},{"code_sha256":"b78a712913941f90","code_sha256_prefix":"b78a712913941f90","entry":"Critic","repo":"biemann/Continuous-Control","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/biemann/Continuous-Control/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, biemann/Continuous-Control when it was checked","mcp_get_code":{"code_sha256":"b78a712913941f90"}},{"code_sha256":"65567268c56c2f46","code_sha256_prefix":"65567268c56c2f46","entry":"Critic","repo":"baturaysaglam/RIS-MISO-Deep-Reinforcement-Learning","repo_kind":"listed","path":"DDPG.py","file_url":"https://github.com/baturaysaglam/RIS-MISO-Deep-Reinforcement-Learning/blob/HEAD/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"65567268c56c2f46"}},{"code_sha256":"40513685bd8b8200","code_sha256_prefix":"40513685bd8b8200","entry":"Critic","repo":"Souphis/mobile_robot_rl","repo_kind":"listed","path":"mobile_robot_rl/agents/sac.py","file_url":"https://github.com/Souphis/mobile_robot_rl/blob/HEAD/mobile_robot_rl/agents/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"40513685bd8b8200"},"code_page":"/code/critic","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"40513685bd8b8200"}},{"code_sha256":"55f075a92d493d35","code_sha256_prefix":"55f075a92d493d35","entry":"Critic","repo":"hemilpanchiwala/Hindsight-Experience-Replay","repo_kind":"listed","path":"ddpg_with_her/DDPGAgent.py","file_url":"https://github.com/hemilpanchiwala/Hindsight-Experience-Replay/blob/HEAD/ddpg_with_her/DDPGAgent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hemilpanchiwala/Hindsight-Experience-Replay when it was checked","mcp_get_code":{"code_sha256":"55f075a92d493d35"}},{"code_sha256":"e48c1f362301c6a8","code_sha256_prefix":"e48c1f362301c6a8","entry":"Critic","repo":"guillaumeboniface/reacher","repo_kind":"listed","path":"ddpg_controller.py","file_url":"https://github.com/guillaumeboniface/reacher/blob/HEAD/ddpg_controller.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, guillaumeboniface/reacher when it was checked","mcp_get_code":{"code_sha256":"e48c1f362301c6a8"}},{"code_sha256":"6e0920a743c03903","code_sha256_prefix":"6e0920a743c03903","entry":"Critic","repo":"claudeHifly/BipedalWalker-v3","repo_kind":"listed","path":"DDPG/ddpg_agent.py","file_url":"https://github.com/claudeHifly/BipedalWalker-v3/blob/HEAD/DDPG/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, claudeHifly/BipedalWalker-v3 when it was checked","mcp_get_code":{"code_sha256":"6e0920a743c03903"}},{"code_sha256":"111a712bc883469d","code_sha256_prefix":"111a712bc883469d","entry":"Critic","repo":"ZiyangY/IndProject-RL-in-Supply-chain","repo_kind":"listed","path":"DDPG-based RNN/DDPG.py","file_url":"https://github.com/ZiyangY/IndProject-RL-in-Supply-chain/blob/HEAD/DDPG-based%20RNN/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZiyangY/IndProject-RL-in-Supply-chain when it was checked","mcp_get_code":{"code_sha256":"111a712bc883469d"}},{"code_sha256":"4c5d9db3e7d648c9","code_sha256_prefix":"4c5d9db3e7d648c9","entry":"Critic","repo":"Philori22/DDPG-aigym","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/Philori22/DDPG-aigym/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"x:Tensor/2/float, u:Tensor/2/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"4c5d9db3e7d648c9"},"code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Philori22/DDPG-aigym when it was checked","mcp_get_code":{"code_sha256":"4c5d9db3e7d648c9"}},{"code_sha256":"daeec7442740e76e","code_sha256_prefix":"daeec7442740e76e","entry":"Critic","repo":"SaminYeasar/off_policy_ac","repo_kind":"listed","path":"DDPG/DDPG.py","file_url":"https://github.com/SaminYeasar/off_policy_ac/blob/HEAD/DDPG/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"x:Tensor/2/float, u:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, SaminYeasar/off_policy_ac when it was checked","mcp_get_code":{"code_sha256":"daeec7442740e76e"}},{"code_sha256":"fa4e45cc6c3c6500","code_sha256_prefix":"fa4e45cc6c3c6500","entry":"CriticNet","repo":"xtma/simple-pytorch-rl","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/xtma/simple-pytorch-rl/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"s:Tensor/2/float, a:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xtma/simple-pytorch-rl when it was checked","mcp_get_code":{"code_sha256":"fa4e45cc6c3c6500"}},{"code_sha256":"b796e48c52beebc5","code_sha256_prefix":"b796e48c52beebc5","entry":"CriticNetwork","repo":"sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3","repo_kind":"listed","path":"maddpgAgent.py","file_url":"https://github.com/sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3/blob/HEAD/maddpgAgent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"CriticNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/criticnetwork","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3 when it was checked","mcp_get_code":{"code_sha256":"b796e48c52beebc5"}},{"code_sha256":"c64a46f5ad45b01a","code_sha256_prefix":"c64a46f5ad45b01a","entry":"CriticNetwork","repo":"T3chy/DDPG","repo_kind":"listed","path":"ddpg_torch.py","file_url":"https://github.com/T3chy/DDPG/blob/HEAD/ddpg_torch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"CriticNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/criticnetwork","census":null,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, T3chy/DDPG, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"c64a46f5ad45b01a"}},{"code_sha256":"6429748a5267bb8a","code_sha256_prefix":"6429748a5267bb8a","entry":"CriticNetwork","repo":"KelvinYang0320/deepbots-panda","repo_kind":"listed","path":"Panda_RL/controllers/robot_supervisor_manager/agent/ddpg.py","file_url":"https://github.com/KelvinYang0320/deepbots-panda/blob/HEAD/Panda_RL/controllers/robot_supervisor_manager/agent/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"CriticNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/criticnetwork","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6429748a5267bb8a"}},{"code_sha256":"8fadcc5f80d1e9b5","code_sha256_prefix":"8fadcc5f80d1e9b5","entry":"DDPG","repo":"VasaKiDD/TD3-deep-rl-research","repo_kind":"listed","path":"agent/DDPG.py","file_url":"https://github.com/VasaKiDD/TD3-deep-rl-research/blob/HEAD/agent/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"DDPG","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8fadcc5f80d1e9b5"}},{"code_sha256":"dc719785d5a0b9f7","code_sha256_prefix":"dc719785d5a0b9f7","entry":"DDPG","repo":"EyaRhouma/collaboration-competition-MADDPG","repo_kind":"listed","path":"MADDPG_agent.py","file_url":"https://github.com/EyaRhouma/collaboration-competition-MADDPG/blob/HEAD/MADDPG_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"DDPG","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, EyaRhouma/collaboration-competition-MADDPG when it was checked","mcp_get_code":{"code_sha256":"dc719785d5a0b9f7"}},{"code_sha256":"28eeee629d33c0ad","code_sha256_prefix":"28eeee629d33c0ad","entry":"DDPG","repo":"massquantity/DBRL","repo_kind":"listed","path":"dbrl/models/ddpg.py","file_url":"https://github.com/massquantity/DBRL/blob/HEAD/dbrl/models/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"DDPG","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, massquantity/DBRL when it was checked","mcp_get_code":{"code_sha256":"28eeee629d33c0ad"}},{"code_sha256":"84cb9968a76ef8e6","code_sha256_prefix":"84cb9968a76ef8e6","entry":"DDPG","repo":"baturaysaglam/RIS-MISO-Deep-Reinforcement-Learning","repo_kind":"listed","path":"DDPG.py","file_url":"https://github.com/baturaysaglam/RIS-MISO-Deep-Reinforcement-Learning/blob/HEAD/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"DDPG","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"84cb9968a76ef8e6"}},{"code_sha256":"4343e52712fa663d","code_sha256_prefix":"4343e52712fa663d","entry":"DDPG","repo":"ZiyangY/IndProject-RL-in-Supply-chain","repo_kind":"listed","path":"DDPG-based RNN/DDPG.py","file_url":"https://github.com/ZiyangY/IndProject-RL-in-Supply-chain/blob/HEAD/DDPG-based%20RNN/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"DDPG","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZiyangY/IndProject-RL-in-Supply-chain when it was checked","mcp_get_code":{"code_sha256":"4343e52712fa663d"}},{"code_sha256":"cf91990d28ccf56a","code_sha256_prefix":"cf91990d28ccf56a","entry":"DDPG","repo":"hamishs/JAX-RL","repo_kind":"listed","path":"src/jax_rl/algorithms/ddpg.py","file_url":"https://github.com/hamishs/JAX-RL/blob/HEAD/src/jax_rl/algorithms/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"batch_size:int/0/int","fixture_out_type":"NoneType","level_recorded_at":"2026-09-24T15:47:56.641058+00:00","retrieve_with":{"tool":"get_code","code_sha256":"cf91990d28ccf56a"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"cf91990d28ccf56a"}},{"code_sha256":"a8bd327c1c912a9d","code_sha256_prefix":"a8bd327c1c912a9d","entry":"DDPG","repo":"tilkb/thermoai","repo_kind":"listed","path":"controller/RL/DDPG.py","file_url":"https://github.com/tilkb/thermoai/blob/HEAD/controller/RL/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"dataset:_TensorSliceDataset/0/?, epoch:int/0/int, objective:str/0/str","fixture_out_type":"NoneType","level_recorded_at":"2026-09-24T20:53:36.805180+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, tilkb/thermoai when it was checked","mcp_get_code":{"code_sha256":"a8bd327c1c912a9d"}},{"code_sha256":"a5d631b897e1acb6","code_sha256_prefix":"a5d631b897e1acb6","entry":"DDPGActor","repo":"majercakdavid/gym-virtual-quant-trading","repo_kind":"listed","path":"agents/DDPG.py","file_url":"https://github.com/majercakdavid/gym-virtual-quant-trading/blob/HEAD/agents/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"x:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, majercakdavid/gym-virtual-quant-trading (NOASSERTION)","mcp_get_code":{"code_sha256":"a5d631b897e1acb6"}},{"code_sha256":"037ce510df007080","code_sha256_prefix":"037ce510df007080","entry":"DDPGAgent","repo":"dpoulopoulos/drl_collaborate_compete","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/dpoulopoulos/drl_collaborate_compete/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"DDPGAgent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ddpgagent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dpoulopoulos/drl_collaborate_compete when it was checked","mcp_get_code":{"code_sha256":"037ce510df007080"}},{"code_sha256":"b51369036ab5a352","code_sha256_prefix":"b51369036ab5a352","entry":"DDPGAgent","repo":"HJDQN/HJQ","repo_kind":"listed","path":"algorithms/ddpg/ddpg.py","file_url":"https://github.com/HJDQN/HJQ/blob/HEAD/algorithms/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"DDPGAgent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ddpgagent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, HJDQN/HJQ when it was checked","mcp_get_code":{"code_sha256":"b51369036ab5a352"}},{"code_sha256":"7869f0d6349f369b","code_sha256_prefix":"7869f0d6349f369b","entry":"DDPGCritic","repo":"majercakdavid/gym-virtual-quant-trading","repo_kind":"listed","path":"agents/DDPG.py","file_url":"https://github.com/majercakdavid/gym-virtual-quant-trading/blob/HEAD/agents/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"x:Tensor/2/float, actions:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, majercakdavid/gym-virtual-quant-trading (NOASSERTION)","mcp_get_code":{"code_sha256":"7869f0d6349f369b"}},{"code_sha256":"61958a4594b078dd","code_sha256_prefix":"61958a4594b078dd","entry":"DDPG_Agent","repo":"JorgeA-RD/Reinforcement-Learning-Agents","repo_kind":"listed","path":"DDPG/DDPG_Agent.py","file_url":"https://github.com/JorgeA-RD/Reinforcement-Learning-Agents/blob/HEAD/DDPG/DDPG_Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"DDPG_Agent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, JorgeA-RD/Reinforcement-Learning-Agents when it was checked","mcp_get_code":{"code_sha256":"61958a4594b078dd"}},{"code_sha256":"8f17f70a798c9257","code_sha256_prefix":"8f17f70a798c9257","entry":"DoubleCritic","repo":"Souphis/mobile_robot_rl","repo_kind":"listed","path":"mobile_robot_rl/agents/sac.py","file_url":"https://github.com/Souphis/mobile_robot_rl/blob/HEAD/mobile_robot_rl/agents/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"DoubleCritic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8f17f70a798c9257"}},{"code_sha256":"07b241d4ab8ac0cb","code_sha256_prefix":"07b241d4ab8ac0cb","entry":"EpisodicMemory","repo":"fshamshirdar/pytorch-rdpg","repo_kind":"listed","path":"rdpg.py","file_url":"https://github.com/fshamshirdar/pytorch-rdpg/blob/HEAD/rdpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"EpisodicMemory","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, fshamshirdar/pytorch-rdpg when it was checked","mcp_get_code":{"code_sha256":"07b241d4ab8ac0cb"}},{"code_sha256":"ff0baff75d5cb615","code_sha256_prefix":"ff0baff75d5cb615","entry":"Evaluator","repo":"fshamshirdar/pytorch-rdpg","repo_kind":"listed","path":"rdpg.py","file_url":"https://github.com/fshamshirdar/pytorch-rdpg/blob/HEAD/rdpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Evaluator","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/evaluator","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, fshamshirdar/pytorch-rdpg when it was checked","mcp_get_code":{"code_sha256":"ff0baff75d5cb615"}},{"code_sha256":"e60542a6e12b3525","code_sha256_prefix":"e60542a6e12b3525","entry":"ExperienceReplay","repo":"JonasRSV/DDPG","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/JonasRSV/DDPG/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ExperienceReplay","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/experiencereplay","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, JonasRSV/DDPG when it was checked","mcp_get_code":{"code_sha256":"e60542a6e12b3525"}},{"code_sha256":"44abfcb21806cc13","code_sha256_prefix":"44abfcb21806cc13","entry":"FCBody","repo":"andreidi/AC_DDPG_walker","repo_kind":"listed","path":"keras_models.py","file_url":"https://github.com/andreidi/AC_DDPG_walker/blob/HEAD/keras_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"FCBody","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, andreidi/AC_DDPG_walker when it was checked","mcp_get_code":{"code_sha256":"44abfcb21806cc13"}},{"code_sha256":"a75c153872d7f256","code_sha256_prefix":"a75c153872d7f256","entry":"FactorizedNoisyLinear","repo":"Souphis/mobile_robot_rl","repo_kind":"listed","path":"mobile_robot_rl/agents/sac.py","file_url":"https://github.com/Souphis/mobile_robot_rl/blob/HEAD/mobile_robot_rl/agents/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"FactorizedNoisyLinear","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a75c153872d7f256"}},{"code_sha256":"5b62ad877a674563","code_sha256_prefix":"5b62ad877a674563","entry":"GaussianActor","repo":"Souphis/mobile_robot_rl","repo_kind":"listed","path":"mobile_robot_rl/agents/sac.py","file_url":"https://github.com/Souphis/mobile_robot_rl/blob/HEAD/mobile_robot_rl/agents/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"x:Tensor/2/float, raw_action:NoneType/0/?, deterministic:bool/0/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5b62ad877a674563"}},{"code_sha256":"98596830b8e76bd9","code_sha256_prefix":"98596830b8e76bd9","entry":"IndependentNoisyLinear","repo":"Souphis/mobile_robot_rl","repo_kind":"listed","path":"mobile_robot_rl/agents/sac.py","file_url":"https://github.com/Souphis/mobile_robot_rl/blob/HEAD/mobile_robot_rl/agents/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"IndependentNoisyLinear","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"98596830b8e76bd9"}},{"code_sha256":"83a88d1e71ef2df5","code_sha256_prefix":"83a88d1e71ef2df5","entry":"LinearLN","repo":"majercakdavid/gym-virtual-quant-trading","repo_kind":"listed","path":"agents/DDPG.py","file_url":"https://github.com/majercakdavid/gym-virtual-quant-trading/blob/HEAD/agents/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"x:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, majercakdavid/gym-virtual-quant-trading (NOASSERTION)","mcp_get_code":{"code_sha256":"83a88d1e71ef2df5"}},{"code_sha256":"8496458fca8ba950","code_sha256_prefix":"8496458fca8ba950","entry":"LinearSchedule","repo":"bmeyers/VirtualMicrogridSegmentation","repo_kind":"listed","path":"virtual_microgrids/algorithms/ddpg.py","file_url":"https://github.com/bmeyers/VirtualMicrogridSegmentation/blob/HEAD/virtual_microgrids/algorithms/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"t:int/0/int","fixture_out_type":"NoneType","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"8496458fca8ba950"},"code_page":null,"census":null,"licence":"BSD-2-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8496458fca8ba950"}},{"code_sha256":"cada5e0bd569171d","code_sha256_prefix":"cada5e0bd569171d","entry":"LogSchedule","repo":"bmeyers/VirtualMicrogridSegmentation","repo_kind":"listed","path":"virtual_microgrids/algorithms/ddpg.py","file_url":"https://github.com/bmeyers/VirtualMicrogridSegmentation/blob/HEAD/virtual_microgrids/algorithms/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"t:int/0/int","fixture_out_type":"NoneType","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"cada5e0bd569171d"},"code_page":null,"census":null,"licence":"BSD-2-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"cada5e0bd569171d"}},{"code_sha256":"416bd507555ea4fa","code_sha256_prefix":"416bd507555ea4fa","entry":"Logger","repo":"Souphis/mobile_robot_rl","repo_kind":"listed","path":"mobile_robot_rl/agents/sac.py","file_url":"https://github.com/Souphis/mobile_robot_rl/blob/HEAD/mobile_robot_rl/agents/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Logger","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/logger","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"416bd507555ea4fa"}},{"code_sha256":"b2a68c19e99020f6","code_sha256_prefix":"b2a68c19e99020f6","entry":"MDD","repo":"wassname/rl-portfolio-management","repo_kind":"listed","path":"rl_portfolio_management/util.py","file_url":"https://github.com/wassname/rl-portfolio-management/blob/HEAD/rl_portfolio_management/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"X:list/1/float","fixture_out_type":"float","level_recorded_at":"2026-09-26T04:29:16.584584+00:00","retrieve_with":{"tool":"get_code","code_sha256":"b2a68c19e99020f6"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b2a68c19e99020f6"}},{"code_sha256":"6b17610b667cbc34","code_sha256_prefix":"6b17610b667cbc34","entry":"MLPActor","repo":"andreidi/AC_DDPG_walker","repo_kind":"listed","path":"keras_models.py","file_url":"https://github.com/andreidi/AC_DDPG_walker/blob/HEAD/keras_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"MLPActor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, andreidi/AC_DDPG_walker when it was checked","mcp_get_code":{"code_sha256":"6b17610b667cbc34"}},{"code_sha256":"a5e014313403ae12","code_sha256_prefix":"a5e014313403ae12","entry":"Memory","repo":"fshamshirdar/pytorch-rdpg","repo_kind":"listed","path":"rdpg.py","file_url":"https://github.com/fshamshirdar/pytorch-rdpg/blob/HEAD/rdpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Memory","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/memory","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, fshamshirdar/pytorch-rdpg when it was checked","mcp_get_code":{"code_sha256":"a5e014313403ae12"}},{"code_sha256":"dc27eb092679d1d2","code_sha256_prefix":"dc27eb092679d1d2","entry":"Memory","repo":"xtma/simple-pytorch-rl","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/xtma/simple-pytorch-rl/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Memory","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/memory","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xtma/simple-pytorch-rl when it was checked","mcp_get_code":{"code_sha256":"dc27eb092679d1d2"}},{"code_sha256":"ccb0aa1ef035eb8e","code_sha256_prefix":"ccb0aa1ef035eb8e","entry":"Memory","repo":"mathformoso/RL-playground---ddpg","repo_kind":"listed","path":"DDPG.py","file_url":"https://github.com/mathformoso/RL-playground---ddpg/blob/HEAD/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Memory","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/memory","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ccb0aa1ef035eb8e"}},{"code_sha256":"4fcd027380e5ca56","code_sha256_prefix":"4fcd027380e5ca56","entry":"NormalDistrLayer","repo":"arnomoonens/yarll","repo_kind":"listed","path":"yarll/agents/tf2/actorcritic/actor_critic.py","file_url":"https://github.com/arnomoonens/yarll/blob/HEAD/yarll/agents/tf2/actorcritic/actor_critic.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"NormalDistrLayer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4fcd027380e5ca56"}},{"code_sha256":"d4f94d4568e6a3f3","code_sha256_prefix":"d4f94d4568e6a3f3","entry":"NormalNoise","repo":"anita-hu/TF2-RL","repo_kind":"listed","path":"DDPG/TF2_DDPG_Basic.py","file_url":"https://github.com/anita-hu/TF2-RL/blob/HEAD/DDPG/TF2_DDPG_Basic.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"fixture_out_type":"ndarray","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d4f94d4568e6a3f3"}},{"code_sha256":"ed77765a89c3c5ba","code_sha256_prefix":"ed77765a89c3c5ba","entry":"OUActionNoise","repo":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","repo_kind":"listed","path":"software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","file_url":"https://github.com/dfki-ric-underactuated-lab/torque_limited_simple_pendulum/blob/HEAD/software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUActionNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ed77765a89c3c5ba"}},{"code_sha256":"ef632145448c9d94","code_sha256_prefix":"ef632145448c9d94","entry":"OUActionNoise","repo":"T3chy/DDPG","repo_kind":"listed","path":"ddpg_torch.py","file_url":"https://github.com/T3chy/DDPG/blob/HEAD/ddpg_torch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUActionNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, T3chy/DDPG, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"ef632145448c9d94"}},{"code_sha256":"35d7e5f360ca6981","code_sha256_prefix":"35d7e5f360ca6981","entry":"OUActionNoise","repo":"samuelmat19/DDPG-tf2","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/samuelmat19/DDPG-tf2/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"fixture_out_type":"ndarray","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"35d7e5f360ca6981"}},{"code_sha256":"e47034c4a39da307","code_sha256_prefix":"e47034c4a39da307","entry":"OUNoise","repo":"dpoulopoulos/drl_collaborate_compete","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/dpoulopoulos/drl_collaborate_compete/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ounoise","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dpoulopoulos/drl_collaborate_compete when it was checked","mcp_get_code":{"code_sha256":"e47034c4a39da307"}},{"code_sha256":"85896c6b57d5891f","code_sha256_prefix":"85896c6b57d5891f","entry":"OUNoise","repo":"YoUNG824/DDPG","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/YoUNG824/DDPG/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ounoise","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"85896c6b57d5891f"}},{"code_sha256":"f0163af304a40792","code_sha256_prefix":"f0163af304a40792","entry":"OUNoise","repo":"iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ounoise","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f0163af304a40792"}},{"code_sha256":"046c7d82e0f35a06","code_sha256_prefix":"046c7d82e0f35a06","entry":"OUNoise","repo":"dan-lennox/ml-udacity-quadcopter-rl","repo_kind":"listed","path":"agents/agent.py","file_url":"https://github.com/dan-lennox/ml-udacity-quadcopter-rl/blob/HEAD/agents/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ounoise","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dan-lennox/ml-udacity-quadcopter-rl when it was checked","mcp_get_code":{"code_sha256":"046c7d82e0f35a06"}},{"code_sha256":"d7af24edd798e11c","code_sha256_prefix":"d7af24edd798e11c","entry":"OUNoise","repo":"IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ounoise","census":null,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"d7af24edd798e11c"}},{"code_sha256":"0562ed655f21cba8","code_sha256_prefix":"0562ed655f21cba8","entry":"OUNoise","repo":"EyaRhouma/collaboration-competition-MADDPG","repo_kind":"listed","path":"MADDPG_agent.py","file_url":"https://github.com/EyaRhouma/collaboration-competition-MADDPG/blob/HEAD/MADDPG_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ounoise","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, EyaRhouma/collaboration-competition-MADDPG when it was checked","mcp_get_code":{"code_sha256":"0562ed655f21cba8"}},{"code_sha256":"21303179927140a0","code_sha256_prefix":"21303179927140a0","entry":"OUNoise","repo":"ZainRaza14/deepRL","repo_kind":"listed","path":"DDPG/ddpg_agent.py","file_url":"https://github.com/ZainRaza14/deepRL/blob/HEAD/DDPG/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ounoise","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZainRaza14/deepRL when it was checked","mcp_get_code":{"code_sha256":"21303179927140a0"}},{"code_sha256":"7e2a8290108cb3ea","code_sha256_prefix":"7e2a8290108cb3ea","entry":"OUNoise","repo":"madhur-tandon/RL-Project","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/madhur-tandon/RL-Project/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ounoise","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, madhur-tandon/RL-Project when it was checked","mcp_get_code":{"code_sha256":"7e2a8290108cb3ea"}},{"code_sha256":"06e140e447cd7fb3","code_sha256_prefix":"06e140e447cd7fb3","entry":"OUNoise","repo":"biemann/Continuous-Control","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/biemann/Continuous-Control/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ounoise","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, biemann/Continuous-Control when it was checked","mcp_get_code":{"code_sha256":"06e140e447cd7fb3"}},{"code_sha256":"affd388fecde62eb","code_sha256_prefix":"affd388fecde62eb","entry":"OUNoise","repo":"claudeHifly/BipedalWalker-v3","repo_kind":"listed","path":"DDPG/ddpg_agent.py","file_url":"https://github.com/claudeHifly/BipedalWalker-v3/blob/HEAD/DDPG/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ounoise","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, claudeHifly/BipedalWalker-v3 when it was checked","mcp_get_code":{"code_sha256":"affd388fecde62eb"}},{"code_sha256":"6d50e581fbec00bb","code_sha256_prefix":"6d50e581fbec00bb","entry":"OUNoise","repo":"WittmannF/quadcopter-best-practices","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/WittmannF/quadcopter-best-practices/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OUNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ounoise","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, WittmannF/quadcopter-best-practices when it was checked","mcp_get_code":{"code_sha256":"6d50e581fbec00bb"}},{"code_sha256":"e76268df8017c794","code_sha256_prefix":"e76268df8017c794","entry":"OU_noise","repo":"InSpaceAI/RL-Zoo","repo_kind":"listed","path":"DDPG.py","file_url":"https://github.com/InSpaceAI/RL-Zoo/blob/HEAD/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OU_noise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, InSpaceAI/RL-Zoo when it was checked","mcp_get_code":{"code_sha256":"e76268df8017c794"}},{"code_sha256":"642df90cf8f1851a","code_sha256_prefix":"642df90cf8f1851a","entry":"OrnsteinUhlenbeckActionNoise","repo":"hemilpanchiwala/Hindsight-Experience-Replay","repo_kind":"listed","path":"ddpg_with_her/DDPGAgent.py","file_url":"https://github.com/hemilpanchiwala/Hindsight-Experience-Replay/blob/HEAD/ddpg_with_her/DDPGAgent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OrnsteinUhlenbeckActionNoise","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hemilpanchiwala/Hindsight-Experience-Replay when it was checked","mcp_get_code":{"code_sha256":"642df90cf8f1851a"}},{"code_sha256":"132cdd71f41a5c43","code_sha256_prefix":"132cdd71f41a5c43","entry":"OrnsteinUhlenbeckNoise","repo":"anita-hu/TF2-RL","repo_kind":"listed","path":"DDPG/TF2_DDPG_Basic.py","file_url":"https://github.com/anita-hu/TF2-RL/blob/HEAD/DDPG/TF2_DDPG_Basic.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"fixture_out_type":"ndarray","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"132cdd71f41a5c43"}},{"code_sha256":"37ebaf510f179bf4","code_sha256_prefix":"37ebaf510f179bf4","entry":"OrnsteinUhlenbeckProcess","repo":"fshamshirdar/pytorch-rdpg","repo_kind":"listed","path":"rdpg.py","file_url":"https://github.com/fshamshirdar/pytorch-rdpg/blob/HEAD/rdpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OrnsteinUhlenbeckProcess","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, fshamshirdar/pytorch-rdpg when it was checked","mcp_get_code":{"code_sha256":"37ebaf510f179bf4"}},{"code_sha256":"ef85fd5d912b3855","code_sha256_prefix":"ef85fd5d912b3855","entry":"OrnsteinUhlenbeckProcess","repo":"J93T/TP4-DDPG","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/J93T/TP4-DDPG/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"OrnsteinUhlenbeckProcess","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, J93T/TP4-DDPG when it was checked","mcp_get_code":{"code_sha256":"ef85fd5d912b3855"}},{"code_sha256":"f6a31a3f71f0c87a","code_sha256_prefix":"f6a31a3f71f0c87a","entry":"PRNGKeys","repo":"dyth/doublegum","repo_kind":"listed","path":"policies_cont/agents/DDPG.py","file_url":"https://github.com/dyth/doublegum/blob/HEAD/policies_cont/agents/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"PRNGKeys","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f6a31a3f71f0c87a"}},{"code_sha256":"eb1ba8dec1905c59","code_sha256_prefix":"eb1ba8dec1905c59","entry":"PendulumPlant","repo":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","repo_kind":"listed","path":"software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","file_url":"https://github.com/dfki-ric-underactuated-lab/torque_limited_simple_pendulum/blob/HEAD/software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"PendulumPlant","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"eb1ba8dec1905c59"}},{"code_sha256":"4e16ab1aa52fc01f","code_sha256_prefix":"4e16ab1aa52fc01f","entry":"Policy","repo":"guillaumeboniface/reacher","repo_kind":"listed","path":"ddpg_controller.py","file_url":"https://github.com/guillaumeboniface/reacher/blob/HEAD/ddpg_controller.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"Policy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"4e16ab1aa52fc01f"},"code_page":"/code/policy","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, guillaumeboniface/reacher when it was checked","mcp_get_code":{"code_sha256":"4e16ab1aa52fc01f"}},{"code_sha256":"b07dfe06f4498bba","code_sha256_prefix":"b07dfe06f4498bba","entry":"Prioritized_experience_replay","repo":"Dekki-Aero/DDPG","repo_kind":"listed","path":"DDPG-TF/ddpg/ddpg.py","file_url":"https://github.com/Dekki-Aero/DDPG/blob/HEAD/DDPG-TF/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Prioritized_experience_replay","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Dekki-Aero/DDPG when it was checked","mcp_get_code":{"code_sha256":"b07dfe06f4498bba"}},{"code_sha256":"ab1c58fa8208bfec","code_sha256_prefix":"ab1c58fa8208bfec","entry":"RandomProcess","repo":"fshamshirdar/pytorch-rdpg","repo_kind":"listed","path":"rdpg.py","file_url":"https://github.com/fshamshirdar/pytorch-rdpg/blob/HEAD/rdpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"RandomProcess","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, fshamshirdar/pytorch-rdpg when it was checked","mcp_get_code":{"code_sha256":"ab1c58fa8208bfec"}},{"code_sha256":"3c7178cf937ba425","code_sha256_prefix":"3c7178cf937ba425","entry":"ReplayBuffer","repo":"yukezhu/tensorflow-reinforce","repo_kind":"listed","path":"rl/pg_ddpg.py","file_url":"https://github.com/yukezhu/tensorflow-reinforce/blob/HEAD/rl/pg_ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3c7178cf937ba425"}},{"code_sha256":"1a3c5297309ff7b3","code_sha256_prefix":"1a3c5297309ff7b3","entry":"ReplayBuffer","repo":"dpoulopoulos/drl_collaborate_compete","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/dpoulopoulos/drl_collaborate_compete/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dpoulopoulos/drl_collaborate_compete when it was checked","mcp_get_code":{"code_sha256":"1a3c5297309ff7b3"}},{"code_sha256":"cbd6d4cba3c8f7b0","code_sha256_prefix":"cbd6d4cba3c8f7b0","entry":"ReplayBuffer","repo":"YoUNG824/DDPG","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/YoUNG824/DDPG/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"cbd6d4cba3c8f7b0"}},{"code_sha256":"532a74ad7f880104","code_sha256_prefix":"532a74ad7f880104","entry":"ReplayBuffer","repo":"liampetti/DDPG","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/liampetti/DDPG/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, liampetti/DDPG when it was checked","mcp_get_code":{"code_sha256":"532a74ad7f880104"}},{"code_sha256":"6258582b31c25005","code_sha256_prefix":"6258582b31c25005","entry":"ReplayBuffer","repo":"iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6258582b31c25005"}},{"code_sha256":"79dfb108cab48c77","code_sha256_prefix":"79dfb108cab48c77","entry":"ReplayBuffer","repo":"J93T/TP4-DDPG","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/J93T/TP4-DDPG/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, J93T/TP4-DDPG when it was checked","mcp_get_code":{"code_sha256":"79dfb108cab48c77"}},{"code_sha256":"48908dfdd43f1c2f","code_sha256_prefix":"48908dfdd43f1c2f","entry":"ReplayBuffer","repo":"dan-lennox/ml-udacity-quadcopter-rl","repo_kind":"listed","path":"agents/agent.py","file_url":"https://github.com/dan-lennox/ml-udacity-quadcopter-rl/blob/HEAD/agents/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dan-lennox/ml-udacity-quadcopter-rl when it was checked","mcp_get_code":{"code_sha256":"48908dfdd43f1c2f"}},{"code_sha256":"a15460ad3a6b391e","code_sha256_prefix":"a15460ad3a6b391e","entry":"ReplayBuffer","repo":"HJDQN/HJQ","repo_kind":"listed","path":"algorithms/ddpg/ddpg.py","file_url":"https://github.com/HJDQN/HJQ/blob/HEAD/algorithms/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, HJDQN/HJQ when it was checked","mcp_get_code":{"code_sha256":"a15460ad3a6b391e"}},{"code_sha256":"d8fadcf1cbc892d5","code_sha256_prefix":"d8fadcf1cbc892d5","entry":"ReplayBuffer","repo":"MathPhysSim/PER-NAF","repo_kind":"listed","path":"pernaf/pernaf/naf.py","file_url":"https://github.com/MathPhysSim/PER-NAF/blob/HEAD/pernaf/pernaf/naf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d8fadcf1cbc892d5"}},{"code_sha256":"3869ba95ec3a2e1a","code_sha256_prefix":"3869ba95ec3a2e1a","entry":"ReplayBuffer","repo":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","repo_kind":"listed","path":"software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","file_url":"https://github.com/dfki-ric-underactuated-lab/torque_limited_simple_pendulum/blob/HEAD/software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3869ba95ec3a2e1a"}},{"code_sha256":"87674610395558bb","code_sha256_prefix":"87674610395558bb","entry":"ReplayBuffer","repo":"madhur-tandon/RL-Project","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/madhur-tandon/RL-Project/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, madhur-tandon/RL-Project when it was checked","mcp_get_code":{"code_sha256":"87674610395558bb"}},{"code_sha256":"7ebcb237f3ac8b6b","code_sha256_prefix":"7ebcb237f3ac8b6b","entry":"ReplayBuffer","repo":"T3chy/DDPG","repo_kind":"listed","path":"ddpg_torch.py","file_url":"https://github.com/T3chy/DDPG/blob/HEAD/ddpg_torch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, T3chy/DDPG, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"7ebcb237f3ac8b6b"}},{"code_sha256":"a1866c0223c9dca1","code_sha256_prefix":"a1866c0223c9dca1","entry":"ReplayBuffer","repo":"alathiya/RL-Quadcoptor-Flying","repo_kind":"listed","path":"agents/agent.py","file_url":"https://github.com/alathiya/RL-Quadcoptor-Flying/blob/HEAD/agents/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, alathiya/RL-Quadcoptor-Flying when it was checked","mcp_get_code":{"code_sha256":"a1866c0223c9dca1"}},{"code_sha256":"031efd28ccd13e08","code_sha256_prefix":"031efd28ccd13e08","entry":"ReplayBuffer","repo":"marload/DeepRL-TensorFlow2","repo_kind":"listed","path":"DDPG/DDPG_Continuous.py","file_url":"https://github.com/marload/DeepRL-TensorFlow2/blob/HEAD/DDPG/DDPG_Continuous.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaybuffer","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"031efd28ccd13e08"}},{"code_sha256":"88607f875726a410","code_sha256_prefix":"88607f875726a410","entry":"ReplayBuffer","repo":"bmeyers/VirtualMicrogridSegmentation","repo_kind":"listed","path":"virtual_microgrids/algorithms/ddpg.py","file_url":"https://github.com/bmeyers/VirtualMicrogridSegmentation/blob/HEAD/virtual_microgrids/algorithms/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"batch_size:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"88607f875726a410"},"code_page":"/code/replaybuffer","census":null,"licence":"BSD-2-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"88607f875726a410"}},{"code_sha256":"0d87c7101b2953f2","code_sha256_prefix":"0d87c7101b2953f2","entry":"ReplayMemory","repo":"Souphis/mobile_robot_rl","repo_kind":"listed","path":"mobile_robot_rl/agents/sac.py","file_url":"https://github.com/Souphis/mobile_robot_rl/blob/HEAD/mobile_robot_rl/agents/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayMemory","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaymemory","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0d87c7101b2953f2"}},{"code_sha256":"66d85c7900951847","code_sha256_prefix":"66d85c7900951847","entry":"Replay_Buffer","repo":"Dekki-Aero/DDPG","repo_kind":"listed","path":"DDPG-TF/ddpg/ddpg.py","file_url":"https://github.com/Dekki-Aero/DDPG/blob/HEAD/DDPG-TF/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Replay_Buffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Dekki-Aero/DDPG when it was checked","mcp_get_code":{"code_sha256":"66d85c7900951847"}},{"code_sha256":"3f3476b061f68f18","code_sha256_prefix":"3f3476b061f68f18","entry":"RingBuffer","repo":"fshamshirdar/pytorch-rdpg","repo_kind":"listed","path":"rdpg.py","file_url":"https://github.com/fshamshirdar/pytorch-rdpg/blob/HEAD/rdpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"RingBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, fshamshirdar/pytorch-rdpg when it was checked","mcp_get_code":{"code_sha256":"3f3476b061f68f18"}},{"code_sha256":"a3c118a9e035f7e4","code_sha256_prefix":"a3c118a9e035f7e4","entry":"RingBuffer","repo":"ghliu/pytorch-ddpg","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/ghliu/pytorch-ddpg/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"RingBuffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a3c118a9e035f7e4"}},{"code_sha256":"4618f3f110556784","code_sha256_prefix":"4618f3f110556784","entry":"Rollout","repo":"Souphis/mobile_robot_rl","repo_kind":"listed","path":"mobile_robot_rl/agents/sac.py","file_url":"https://github.com/Souphis/mobile_robot_rl/blob/HEAD/mobile_robot_rl/agents/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Rollout","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4618f3f110556784"}},{"code_sha256":"980051699184bfdd","code_sha256_prefix":"980051699184bfdd","entry":"SequentialMemory","repo":"ghliu/pytorch-ddpg","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/ghliu/pytorch-ddpg/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"SequentialMemory","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"980051699184bfdd"}},{"code_sha256":"837dcd3ff834a51f","code_sha256_prefix":"837dcd3ff834a51f","entry":"SimplePendulumEnv","repo":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","repo_kind":"listed","path":"software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","file_url":"https://github.com/dfki-ric-underactuated-lab/torque_limited_simple_pendulum/blob/HEAD/software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"SimplePendulumEnv","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"837dcd3ff834a51f"}},{"code_sha256":"1d2fffeddc2ad914","code_sha256_prefix":"1d2fffeddc2ad914","entry":"Simulator","repo":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","repo_kind":"listed","path":"software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","file_url":"https://github.com/dfki-ric-underactuated-lab/torque_limited_simple_pendulum/blob/HEAD/software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Simulator","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1d2fffeddc2ad914"}},{"code_sha256":"1d6614860f0f4b57","code_sha256_prefix":"1d6614860f0f4b57","entry":"ValueHead","repo":"Souphis/mobile_robot_rl","repo_kind":"listed","path":"mobile_robot_rl/agents/sac.py","file_url":"https://github.com/Souphis/mobile_robot_rl/blob/HEAD/mobile_robot_rl/agents/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"ValueHead","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1d6614860f0f4b57"}},{"code_sha256":"ca95bd1bfa26d31f","code_sha256_prefix":"ca95bd1bfa26d31f","entry":"_actor_network","repo":"Dekki-Aero/DDPG","repo_kind":"listed","path":"DDPG-TF/ddpg/ddpg.py","file_url":"https://github.com/Dekki-Aero/DDPG/blob/HEAD/DDPG-TF/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"_actor_network","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Dekki-Aero/DDPG when it was checked","mcp_get_code":{"code_sha256":"ca95bd1bfa26d31f"}},{"code_sha256":"fe8293ee7abbf8aa","code_sha256_prefix":"fe8293ee7abbf8aa","entry":"_critic_network","repo":"Dekki-Aero/DDPG","repo_kind":"listed","path":"DDPG-TF/ddpg/ddpg.py","file_url":"https://github.com/Dekki-Aero/DDPG/blob/HEAD/DDPG-TF/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"_critic_network","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Dekki-Aero/DDPG when it was checked","mcp_get_code":{"code_sha256":"fe8293ee7abbf8aa"}},{"code_sha256":"34bfe74d89d0491d","code_sha256_prefix":"34bfe74d89d0491d","entry":"_get_layer","repo":"Souphis/mobile_robot_rl","repo_kind":"listed","path":"mobile_robot_rl/agents/sac.py","file_url":"https://github.com/Souphis/mobile_robot_rl/blob/HEAD/mobile_robot_rl/agents/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"layer_type:str/0/str, input_dim:int/0/int, output_dim:int/0/int, sigma_init:float/0/float","fixture_out_type":"FactorizedNoisyLinear","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"34bfe74d89d0491d"}},{"code_sha256":"dceb05d9d5cc7ee5","code_sha256_prefix":"dceb05d9d5cc7ee5","entry":"actor","repo":"anita-hu/TF2-RL","repo_kind":"listed","path":"DDPG/TF2_DDPG_Basic.py","file_url":"https://github.com/anita-hu/TF2-RL/blob/HEAD/DDPG/TF2_DDPG_Basic.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"state_shape:tuple/1/int, action_dim:int/0/int, action_bound:float/0/float, action_shift:ndarray/1/float, units:tuple/1/int","fixture_out_type":"Functional","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"dceb05d9d5cc7ee5"}},{"code_sha256":"417fff584ab90a11","code_sha256_prefix":"417fff584ab90a11","entry":"actor_netw","repo":"JorgeA-RD/Reinforcement-Learning-Agents","repo_kind":"listed","path":"DDPG/DDPG_Agent.py","file_url":"https://github.com/JorgeA-RD/Reinforcement-Learning-Agents/blob/HEAD/DDPG/DDPG_Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"actor_netw","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, JorgeA-RD/Reinforcement-Learning-Agents when it was checked","mcp_get_code":{"code_sha256":"417fff584ab90a11"}},{"code_sha256":"5a5eafa2c20fcefe","code_sha256_prefix":"5a5eafa2c20fcefe","entry":"concat_states","repo":"wassname/rl-portfolio-management","repo_kind":"listed","path":"rl_portfolio_management/wrappers/concat_states.py","file_url":"https://github.com/wassname/rl-portfolio-management/blob/HEAD/rl_portfolio_management/wrappers/concat_states.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"state:dict/0/?","fixture_out_type":"ndarray","level_recorded_at":"2026-09-26T04:29:16.584584+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5a5eafa2c20fcefe"}},{"code_sha256":"edb5292361905292","code_sha256_prefix":"edb5292361905292","entry":"critic","repo":"anita-hu/TF2-RL","repo_kind":"listed","path":"DDPG/TF2_DDPG_Basic.py","file_url":"https://github.com/anita-hu/TF2-RL/blob/HEAD/DDPG/TF2_DDPG_Basic.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"state_shape:tuple/1/int, action_dim:int/0/int, units:tuple/1/int","fixture_out_type":"Functional","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"edb5292361905292"}},{"code_sha256":"90cab8ba8631c2f8","code_sha256_prefix":"90cab8ba8631c2f8","entry":"critic_netw","repo":"JorgeA-RD/Reinforcement-Learning-Agents","repo_kind":"listed","path":"DDPG/DDPG_Agent.py","file_url":"https://github.com/JorgeA-RD/Reinforcement-Learning-Agents/blob/HEAD/DDPG/DDPG_Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"critic_netw","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, JorgeA-RD/Reinforcement-Learning-Agents when it was checked","mcp_get_code":{"code_sha256":"90cab8ba8631c2f8"}},{"code_sha256":"825ecb6732e9fc31","code_sha256_prefix":"825ecb6732e9fc31","entry":"fanin_init","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"size:tuple/1/int, fanin:int/0/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"825ecb6732e9fc31"},"code_page":"/code/fanin-init","census":null,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"825ecb6732e9fc31"}},{"code_sha256":"0d0842514b1844a1","code_sha256_prefix":"0d0842514b1844a1","entry":"fanin_init","repo":"fshamshirdar/pytorch-rdpg","repo_kind":"listed","path":"rdpg.py","file_url":"https://github.com/fshamshirdar/pytorch-rdpg/blob/HEAD/rdpg.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"size:tuple/1/int, fanin:NoneType/0/?","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"0d0842514b1844a1"},"code_page":"/code/fanin-init","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, fshamshirdar/pytorch-rdpg when it was checked","mcp_get_code":{"code_sha256":"0d0842514b1844a1"}},{"code_sha256":"5f358d33ffd43ed3","code_sha256_prefix":"5f358d33ffd43ed3","entry":"get_actor","repo":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","repo_kind":"listed","path":"software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","file_url":"https://github.com/dfki-ric-underactuated-lab/torque_limited_simple_pendulum/blob/HEAD/software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"state_shape:tuple/1/int, upper_bound:float/0/float, verbose:bool/0/bool","fixture_out_type":"Functional","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5f358d33ffd43ed3"}},{"code_sha256":"57f92caea351b30b","code_sha256_prefix":"57f92caea351b30b","entry":"get_arrow","repo":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","repo_kind":"listed","path":"software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","file_url":"https://github.com/dfki-ric-underactuated-lab/torque_limited_simple_pendulum/blob/HEAD/software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"radius:float/0/float, centX:float/0/float, centY:float/0/float, angle_:float/0/float, theta2_:float/0/float, color_:str/0/str","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"57f92caea351b30b"}},{"code_sha256":"a143a950a76e3523","code_sha256_prefix":"a143a950a76e3523","entry":"get_critic","repo":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","repo_kind":"listed","path":"software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","file_url":"https://github.com/dfki-ric-underactuated-lab/torque_limited_simple_pendulum/blob/HEAD/software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"state_shape:tuple/1/int, n_actions:int/0/int, verbose:bool/0/bool","fixture_out_type":"Functional","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a143a950a76e3523"}},{"code_sha256":"cf7f0fe0d3ac16d9","code_sha256_prefix":"cf7f0fe0d3ac16d9","entry":"get_env_spec","repo":"HJDQN/HJQ","repo_kind":"listed","path":"algorithms/ddpg/ddpg.py","file_url":"https://github.com/HJDQN/HJQ/blob/HEAD/algorithms/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"env:MockEnv/0/?","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, HJDQN/HJQ when it was checked","mcp_get_code":{"code_sha256":"cf7f0fe0d3ac16d9"}},{"code_sha256":"0132cf6a5e04f2ad","code_sha256_prefix":"0132cf6a5e04f2ad","entry":"get_logger","repo":"bmeyers/VirtualMicrogridSegmentation","repo_kind":"listed","path":"virtual_microgrids/algorithms/ddpg.py","file_url":"https://github.com/bmeyers/VirtualMicrogridSegmentation/blob/HEAD/virtual_microgrids/algorithms/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"filename:str/0/str","fixture_out_type":"Logger","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/get-logger","census":null,"licence":"BSD-2-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0132cf6a5e04f2ad"}},{"code_sha256":"d108d1b5ff426750","code_sha256_prefix":"d108d1b5ff426750","entry":"init_list_of_vertex","repo":"tegg89/DLCamp_Jeju2018","repo_kind":"listed","path":"env_processing/shaping.py","file_url":"https://github.com/tegg89/DLCamp_Jeju2018/blob/HEAD/env_processing/shaping.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"board:ndarray/2/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T10:37:12.143382+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d108d1b5ff426750"}},{"code_sha256":"f39751e02169b745","code_sha256_prefix":"f39751e02169b745","entry":"makeFilteredEnv","repo":"floodsung/DDPG","repo_kind":"listed","path":"filter_env.py","file_url":"https://github.com/floodsung/DDPG/blob/HEAD/filter_env.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"env:SimpleEnv/0/?","fixture_out_type":"FilteredEnv","level_recorded_at":"2026-09-26T05:30:53.715539+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f39751e02169b745"}},{"code_sha256":"d08ac0b87604485e","code_sha256_prefix":"d08ac0b87604485e","entry":"mse_loss","repo":"Souphis/mobile_robot_rl","repo_kind":"listed","path":"mobile_robot_rl/agents/sac.py","file_url":"https://github.com/Souphis/mobile_robot_rl/blob/HEAD/mobile_robot_rl/agents/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"prediction:Tensor/2/float, target:Tensor/2/float, reduction:Reduction/0/?","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/mse-loss","census":{"url":"/census/mse-loss","implementations":8,"papers":12,"distinct_outputs":6,"n_buckets":4,"bucket_key":[[2,"float","float32"],[2,"float","float32"]],"bucket_index":1,"bucket_label":"arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32"},"census_bucket_fragment":"bucket-1","licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d08ac0b87604485e"}},{"code_sha256":"6298e4cee53206cd","code_sha256_prefix":"6298e4cee53206cd","entry":"sample_batch_indexes","repo":"ghliu/pytorch-ddpg","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/ghliu/pytorch-ddpg/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"low:int/0/int, high:int/0/int, size:int/0/int","fixture_out_type":"list","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"6298e4cee53206cd"},"code_page":"/code/sample-batch-indexes","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6298e4cee53206cd"}},{"code_sha256":"f0945ef1933b173a","code_sha256_prefix":"f0945ef1933b173a","entry":"to_tensor","repo":"Medabid1/RL_Project","repo_kind":"listed","path":"network/Networks.py","file_url":"https://github.com/Medabid1/RL_Project/blob/HEAD/network/Networks.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"x:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"f0945ef1933b173a"},"code_page":"/code/to-tensor","census":{"url":"/census/to-tensor","implementations":8,"papers":8,"distinct_outputs":3,"n_buckets":3,"bucket_key":[[2,"float","float32"]],"bucket_index":1,"bucket_label":"arg 1: rank 2, kind float, dtype float32"},"census_bucket_fragment":"bucket-1","licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Medabid1/RL_Project when it was checked","mcp_get_code":{"code_sha256":"f0945ef1933b173a"}},{"code_sha256":"b5cc72675b688b00","code_sha256_prefix":"b5cc72675b688b00","entry":"zeroed_observation","repo":"fshamshirdar/pytorch-rdpg","repo_kind":"listed","path":"rdpg.py","file_url":"https://github.com/fshamshirdar/pytorch-rdpg/blob/HEAD/rdpg.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"observation:ndarray/2/float","fixture_out_type":"ndarray","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"b5cc72675b688b00"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, fshamshirdar/pytorch-rdpg when it was checked","mcp_get_code":{"code_sha256":"b5cc72675b688b00"}},{"code_sha256":"958765de0feeec56","code_sha256_prefix":"958765de0feeec56","entry":"Actor","repo":"fshamshirdar/pytorch-rdpg","repo_kind":"listed","path":"rdpg.py","file_url":"https://github.com/fshamshirdar/pytorch-rdpg/blob/HEAD/rdpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, fshamshirdar/pytorch-rdpg when it was checked","mcp_get_code":{"code_sha256":"958765de0feeec56"}},{"code_sha256":"8bd7d62053fbfae5","code_sha256_prefix":"8bd7d62053fbfae5","entry":"Actor","repo":"dan-lennox/ml-udacity-quadcopter-rl","repo_kind":"listed","path":"agents/agent.py","file_url":"https://github.com/dan-lennox/ml-udacity-quadcopter-rl/blob/HEAD/agents/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dan-lennox/ml-udacity-quadcopter-rl when it was checked","mcp_get_code":{"code_sha256":"8bd7d62053fbfae5"}},{"code_sha256":"75b2da574221eee2","code_sha256_prefix":"75b2da574221eee2","entry":"Actor","repo":"halajadallah/RL-Quadcopter_project","repo_kind":"listed","path":"agents/agent_modified.py","file_url":"https://github.com/halajadallah/RL-Quadcopter_project/blob/HEAD/agents/agent_modified.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, halajadallah/RL-Quadcopter_project when it was checked","mcp_get_code":{"code_sha256":"75b2da574221eee2"}},{"code_sha256":"8afc63f093262b83","code_sha256_prefix":"8afc63f093262b83","entry":"Actor","repo":"InSpaceAI/RL-Zoo","repo_kind":"listed","path":"DDPG.py","file_url":"https://github.com/InSpaceAI/RL-Zoo/blob/HEAD/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, InSpaceAI/RL-Zoo when it was checked","mcp_get_code":{"code_sha256":"8afc63f093262b83"}},{"code_sha256":"4abb7a0681b9f8e3","code_sha256_prefix":"4abb7a0681b9f8e3","entry":"Actor","repo":"Gouet/DDPG_PendulumV1","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/Gouet/DDPG_PendulumV1/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Gouet/DDPG_PendulumV1 when it was checked","mcp_get_code":{"code_sha256":"4abb7a0681b9f8e3"}},{"code_sha256":"b9b27fa7acc7c73f","code_sha256_prefix":"b9b27fa7acc7c73f","entry":"Actor","repo":"madvn/DDPG","repo_kind":"listed","path":"ddpg/ddpg.py","file_url":"https://github.com/madvn/DDPG/blob/HEAD/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, madvn/DDPG when it was checked","mcp_get_code":{"code_sha256":"b9b27fa7acc7c73f"}},{"code_sha256":"ef0c12a6692597db","code_sha256_prefix":"ef0c12a6692597db","entry":"Actor","repo":"shahabi8/Deep-Reinforcement-Learning","repo_kind":"listed","path":"DDGP.py","file_url":"https://github.com/shahabi8/Deep-Reinforcement-Learning/blob/HEAD/DDGP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, shahabi8/Deep-Reinforcement-Learning when it was checked","mcp_get_code":{"code_sha256":"ef0c12a6692597db"}},{"code_sha256":"f6231123b603e20f","code_sha256_prefix":"f6231123b603e20f","entry":"Actor","repo":"alathiya/RL-Quadcoptor-Flying","repo_kind":"listed","path":"agents/agent.py","file_url":"https://github.com/alathiya/RL-Quadcoptor-Flying/blob/HEAD/agents/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, alathiya/RL-Quadcoptor-Flying when it was checked","mcp_get_code":{"code_sha256":"f6231123b603e20f"}},{"code_sha256":"c5cbbbbfdd3a367c","code_sha256_prefix":"c5cbbbbfdd3a367c","entry":"Actor","repo":"dyth/doublegum","repo_kind":"listed","path":"policies_cont/agents/DDPG.py","file_url":"https://github.com/dyth/doublegum/blob/HEAD/policies_cont/agents/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c5cbbbbfdd3a367c"}},{"code_sha256":"8f5f60d9f1d5e30f","code_sha256_prefix":"8f5f60d9f1d5e30f","entry":"Actor","repo":"marload/DeepRL-TensorFlow2","repo_kind":"listed","path":"DDPG/DDPG_Continuous.py","file_url":"https://github.com/marload/DeepRL-TensorFlow2/blob/HEAD/DDPG/DDPG_Continuous.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8f5f60d9f1d5e30f"}},{"code_sha256":"017ef34f0499756e","code_sha256_prefix":"017ef34f0499756e","entry":"Actor","repo":"abbadka/quadcopter","repo_kind":"listed","path":"agents/ddpg/agent.py","file_url":"https://github.com/abbadka/quadcopter/blob/HEAD/agents/ddpg/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, abbadka/quadcopter when it was checked","mcp_get_code":{"code_sha256":"017ef34f0499756e"}},{"code_sha256":"0d51c1e5212918ec","code_sha256_prefix":"0d51c1e5212918ec","entry":"Actor","repo":"fhbzc/FishAgentSimulation","repo_kind":"listed","path":"train_RL.py","file_url":"https://github.com/fhbzc/FishAgentSimulation/blob/HEAD/train_RL.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, fhbzc/FishAgentSimulation when it was checked","mcp_get_code":{"code_sha256":"0d51c1e5212918ec"}},{"code_sha256":"26052e22d5d45a91","code_sha256_prefix":"26052e22d5d45a91","entry":"ActorCritic","repo":"dchetelat/acer","repo_kind":"listed","path":"brain.py","file_url":"https://github.com/dchetelat/acer/blob/HEAD/brain.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actorcritic","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"26052e22d5d45a91"}},{"code_sha256":"36fb14c831b75e4f","code_sha256_prefix":"36fb14c831b75e4f","entry":"ActorNet","repo":"MLCS-Yonsei/ddpg-control","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/MLCS-Yonsei/ddpg-control/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"36fb14c831b75e4f"}},{"code_sha256":"0d7cb0b9cab3eb74","code_sha256_prefix":"0d7cb0b9cab3eb74","entry":"ActorNet","repo":"stevenpjg/ddpg-aigym","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/stevenpjg/ddpg-aigym/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0d7cb0b9cab3eb74"}},{"code_sha256":"883fbd58c181e487","code_sha256_prefix":"883fbd58c181e487","entry":"ActorNet_bn","repo":"MLCS-Yonsei/ddpg-control","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/MLCS-Yonsei/ddpg-control/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"883fbd58c181e487"}},{"code_sha256":"18c75ab6a06581a4","code_sha256_prefix":"18c75ab6a06581a4","entry":"ActorNetwork","repo":"YoUNG824/DDPG","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/YoUNG824/DDPG/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"18c75ab6a06581a4"}},{"code_sha256":"9c01f30e9f1052e8","code_sha256_prefix":"9c01f30e9f1052e8","entry":"ActorNetwork","repo":"backgom2357/Recommender_system_via_deep_RL","repo_kind":"listed","path":"actor.py","file_url":"https://github.com/backgom2357/Recommender_system_via_deep_RL/blob/HEAD/actor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, backgom2357/Recommender_system_via_deep_RL when it was checked","mcp_get_code":{"code_sha256":"9c01f30e9f1052e8"}},{"code_sha256":"fbe0975fffcc8005","code_sha256_prefix":"fbe0975fffcc8005","entry":"ActorNetwork","repo":"bmeyers/VirtualMicrogridSegmentation","repo_kind":"listed","path":"virtual_microgrids/algorithms/ddpg.py","file_url":"https://github.com/bmeyers/VirtualMicrogridSegmentation/blob/HEAD/virtual_microgrids/algorithms/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"BSD-2-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"fbe0975fffcc8005"}},{"code_sha256":"abffeadabe12af6b","code_sha256_prefix":"abffeadabe12af6b","entry":"ActorNetwork","repo":"tegg89/mann","repo_kind":"listed","path":"models/action_execution/actor_critic_nn.py","file_url":"https://github.com/tegg89/mann/blob/HEAD/models/action_execution/actor_critic_nn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"abffeadabe12af6b"}},{"code_sha256":"5c21d19fa9ff6b4b","code_sha256_prefix":"5c21d19fa9ff6b4b","entry":"Actor_network","repo":"ailab-pku/rl-framework","repo_kind":"listed","path":"DDPG/tensorflow/DDPG.py","file_url":"https://github.com/ailab-pku/rl-framework/blob/HEAD/DDPG/tensorflow/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ailab-pku/rl-framework when it was checked","mcp_get_code":{"code_sha256":"5c21d19fa9ff6b4b"}},{"code_sha256":"f21df3758ed39418","code_sha256_prefix":"f21df3758ed39418","entry":"Agent","repo":"fshamshirdar/pytorch-rdpg","repo_kind":"listed","path":"rdpg.py","file_url":"https://github.com/fshamshirdar/pytorch-rdpg/blob/HEAD/rdpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, fshamshirdar/pytorch-rdpg when it was checked","mcp_get_code":{"code_sha256":"f21df3758ed39418"}},{"code_sha256":"40c191818d46c0c5","code_sha256_prefix":"40c191818d46c0c5","entry":"Agent","repo":"Crevass/Hybrid-Agent","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/Crevass/Hybrid-Agent/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Crevass/Hybrid-Agent when it was checked","mcp_get_code":{"code_sha256":"40c191818d46c0c5"}},{"code_sha256":"beb77bbddb9714ae","code_sha256_prefix":"beb77bbddb9714ae","entry":"Agent","repo":"iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"beb77bbddb9714ae"}},{"code_sha256":"8950c65039fc4fe3","code_sha256_prefix":"8950c65039fc4fe3","entry":"Agent","repo":"IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"8950c65039fc4fe3"}},{"code_sha256":"684ee98628f58937","code_sha256_prefix":"684ee98628f58937","entry":"Agent","repo":"PeterJochem/Deep_RL","repo_kind":"listed","path":"DDPG/pendulum/myAgent_pendulum.py","file_url":"https://github.com/PeterJochem/Deep_RL/blob/HEAD/DDPG/pendulum/myAgent_pendulum.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, PeterJochem/Deep_RL when it was checked","mcp_get_code":{"code_sha256":"684ee98628f58937"}},{"code_sha256":"caf348a3362776fb","code_sha256_prefix":"caf348a3362776fb","entry":"Agent","repo":"ZainRaza14/deepRL","repo_kind":"listed","path":"DDPG/ddpg_agent.py","file_url":"https://github.com/ZainRaza14/deepRL/blob/HEAD/DDPG/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ZainRaza14/deepRL when it was checked","mcp_get_code":{"code_sha256":"caf348a3362776fb"}},{"code_sha256":"661322009d0d9169","code_sha256_prefix":"661322009d0d9169","entry":"Agent","repo":"madhur-tandon/RL-Project","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/madhur-tandon/RL-Project/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, madhur-tandon/RL-Project when it was checked","mcp_get_code":{"code_sha256":"661322009d0d9169"}},{"code_sha256":"364b3433ab267478","code_sha256_prefix":"364b3433ab267478","entry":"Agent","repo":"biemann/Continuous-Control","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/biemann/Continuous-Control/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, biemann/Continuous-Control when it was checked","mcp_get_code":{"code_sha256":"364b3433ab267478"}},{"code_sha256":"513584b85fd46561","code_sha256_prefix":"513584b85fd46561","entry":"Agent","repo":"T3chy/DDPG","repo_kind":"listed","path":"ddpg_torch.py","file_url":"https://github.com/T3chy/DDPG/blob/HEAD/ddpg_torch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, T3chy/DDPG, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"513584b85fd46561"}},{"code_sha256":"f3ea6018cdcc0b04","code_sha256_prefix":"f3ea6018cdcc0b04","entry":"Agent","repo":"marload/DeepRL-TensorFlow2","repo_kind":"listed","path":"DDPG/DDPG_Continuous.py","file_url":"https://github.com/marload/DeepRL-TensorFlow2/blob/HEAD/DDPG/DDPG_Continuous.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f3ea6018cdcc0b04"}},{"code_sha256":"2216995588e06169","code_sha256_prefix":"2216995588e06169","entry":"Agent","repo":"shehrum/RL_Continous-Control","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/shehrum/RL_Continous-Control/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, shehrum/RL_Continous-Control when it was checked","mcp_get_code":{"code_sha256":"2216995588e06169"}},{"code_sha256":"dcf4d6df3ff30ac0","code_sha256_prefix":"dcf4d6df3ff30ac0","entry":"Agents","repo":"krasing/DRLearningContinuousControl","repo_kind":"listed","path":"ddpg_agent.py","file_url":"https://github.com/krasing/DRLearningContinuousControl/blob/HEAD/ddpg_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, krasing/DRLearningContinuousControl when it was checked","mcp_get_code":{"code_sha256":"dcf4d6df3ff30ac0"}},{"code_sha256":"ddcc51cfeb97e2a4","code_sha256_prefix":"ddcc51cfeb97e2a4","entry":"BaseAgent","repo":"majercakdavid/gym-virtual-quant-trading","repo_kind":"listed","path":"agents/DDPG.py","file_url":"https://github.com/majercakdavid/gym-virtual-quant-trading/blob/HEAD/agents/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/baseagent","census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, majercakdavid/gym-virtual-quant-trading (NOASSERTION)","mcp_get_code":{"code_sha256":"ddcc51cfeb97e2a4"}},{"code_sha256":"c836b46b3c210e6a","code_sha256_prefix":"c836b46b3c210e6a","entry":"BaseOffPolicy","repo":"Souphis/mobile_robot_rl","repo_kind":"listed","path":"mobile_robot_rl/agents/sac.py","file_url":"https://github.com/Souphis/mobile_robot_rl/blob/HEAD/mobile_robot_rl/agents/sac.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c836b46b3c210e6a"}},{"code_sha256":"746b1c49c2b69b79","code_sha256_prefix":"746b1c49c2b69b79","entry":"BaseSolution","repo":"wpiszlogin/driver_critic","repo_kind":"listed","path":"base_solution.py","file_url":"https://github.com/wpiszlogin/driver_critic/blob/HEAD/base_solution.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"746b1c49c2b69b79"}},{"code_sha256":"5fe982c3dc2394d3","code_sha256_prefix":"5fe982c3dc2394d3","entry":"Brain","repo":"samuelmat19/DDPG-tf2","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/samuelmat19/DDPG-tf2/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5fe982c3dc2394d3"}},{"code_sha256":"96855c8d20a0088b","code_sha256_prefix":"96855c8d20a0088b","entry":"Buffer","repo":"DanielLSM/safe-rl-tutorial","repo_kind":"listed","path":"tutorial/ddpg.py","file_url":"https://github.com/DanielLSM/safe-rl-tutorial/blob/HEAD/tutorial/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/buffer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"96855c8d20a0088b"}},{"code_sha256":"222a72ff1d084586","code_sha256_prefix":"222a72ff1d084586","entry":"CameraResolution","repo":"avivelor/UnityMachineLearningForProjectButterfly","repo_kind":"listed","path":"ml-agents/mlagents/trainers/sac/models.py","file_url":"https://github.com/avivelor/UnityMachineLearningForProjectButterfly/blob/HEAD/ml-agents/mlagents/trainers/sac/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"222a72ff1d084586"}},{"code_sha256":"53c5f2f2df73a0e0","code_sha256_prefix":"53c5f2f2df73a0e0","entry":"ContinuousActorCritic","repo":"dchetelat/acer","repo_kind":"listed","path":"brain.py","file_url":"https://github.com/dchetelat/acer/blob/HEAD/brain.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"53c5f2f2df73a0e0"}},{"code_sha256":"749aa0dd2a4c1d09","code_sha256_prefix":"749aa0dd2a4c1d09","entry":"ContinuousDeepQ","repo":"parilo/rl-server","repo_kind":"listed","path":"tf_rl/controller/continuous_deepq.py","file_url":"https://github.com/parilo/rl-server/blob/HEAD/tf_rl/controller/continuous_deepq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, parilo/rl-server when it was checked","mcp_get_code":{"code_sha256":"749aa0dd2a4c1d09"}},{"code_sha256":"42b59cfab688e3f5","code_sha256_prefix":"42b59cfab688e3f5","entry":"Critic","repo":"dan-lennox/ml-udacity-quadcopter-rl","repo_kind":"listed","path":"agents/agent.py","file_url":"https://github.com/dan-lennox/ml-udacity-quadcopter-rl/blob/HEAD/agents/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dan-lennox/ml-udacity-quadcopter-rl when it was checked","mcp_get_code":{"code_sha256":"42b59cfab688e3f5"}},{"code_sha256":"c5b393b179d8d497","code_sha256_prefix":"c5b393b179d8d497","entry":"Critic","repo":"halajadallah/RL-Quadcopter_project","repo_kind":"listed","path":"agents/agent_modified.py","file_url":"https://github.com/halajadallah/RL-Quadcopter_project/blob/HEAD/agents/agent_modified.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, halajadallah/RL-Quadcopter_project when it was checked","mcp_get_code":{"code_sha256":"c5b393b179d8d497"}},{"code_sha256":"a36fc940a0f3eb1b","code_sha256_prefix":"a36fc940a0f3eb1b","entry":"Critic","repo":"InSpaceAI/RL-Zoo","repo_kind":"listed","path":"DDPG.py","file_url":"https://github.com/InSpaceAI/RL-Zoo/blob/HEAD/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, InSpaceAI/RL-Zoo when it was checked","mcp_get_code":{"code_sha256":"a36fc940a0f3eb1b"}},{"code_sha256":"d5cb870eb8408c73","code_sha256_prefix":"d5cb870eb8408c73","entry":"Critic","repo":"madvn/DDPG","repo_kind":"listed","path":"ddpg/ddpg.py","file_url":"https://github.com/madvn/DDPG/blob/HEAD/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, madvn/DDPG when it was checked","mcp_get_code":{"code_sha256":"d5cb870eb8408c73"}},{"code_sha256":"0872133cc6e7eee2","code_sha256_prefix":"0872133cc6e7eee2","entry":"Critic","repo":"shahabi8/Deep-Reinforcement-Learning","repo_kind":"listed","path":"DDGP.py","file_url":"https://github.com/shahabi8/Deep-Reinforcement-Learning/blob/HEAD/DDGP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, shahabi8/Deep-Reinforcement-Learning when it was checked","mcp_get_code":{"code_sha256":"0872133cc6e7eee2"}},{"code_sha256":"cf0cfca323e5c3c4","code_sha256_prefix":"cf0cfca323e5c3c4","entry":"Critic","repo":"alathiya/RL-Quadcoptor-Flying","repo_kind":"listed","path":"agents/agent.py","file_url":"https://github.com/alathiya/RL-Quadcoptor-Flying/blob/HEAD/agents/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, alathiya/RL-Quadcoptor-Flying when it was checked","mcp_get_code":{"code_sha256":"cf0cfca323e5c3c4"}},{"code_sha256":"6040d49d762613d7","code_sha256_prefix":"6040d49d762613d7","entry":"Critic","repo":"dyth/doublegum","repo_kind":"listed","path":"policies_cont/agents/DDPG.py","file_url":"https://github.com/dyth/doublegum/blob/HEAD/policies_cont/agents/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/critic","census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6040d49d762613d7"}},{"code_sha256":"7f050e7ce4583465","code_sha256_prefix":"7f050e7ce4583465","entry":"Critic","repo":"marload/DeepRL-TensorFlow2","repo_kind":"listed","path":"DDPG/DDPG_Continuous.py","file_url":"https://github.com/marload/DeepRL-TensorFlow2/blob/HEAD/DDPG/DDPG_Continuous.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/critic","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7f050e7ce4583465"}},{"code_sha256":"4080c577fc710255","code_sha256_prefix":"4080c577fc710255","entry":"Critic","repo":"abbadka/quadcopter","repo_kind":"listed","path":"agents/ddpg/agent.py","file_url":"https://github.com/abbadka/quadcopter/blob/HEAD/agents/ddpg/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, abbadka/quadcopter when it was checked","mcp_get_code":{"code_sha256":"4080c577fc710255"}},{"code_sha256":"42be45cafdda9bc6","code_sha256_prefix":"42be45cafdda9bc6","entry":"CriticNet","repo":"MLCS-Yonsei/ddpg-control","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/MLCS-Yonsei/ddpg-control/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"42be45cafdda9bc6"}},{"code_sha256":"b616451b9c41d0be","code_sha256_prefix":"b616451b9c41d0be","entry":"CriticNet","repo":"stevenpjg/ddpg-aigym","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/stevenpjg/ddpg-aigym/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b616451b9c41d0be"}},{"code_sha256":"2961cc94350daaae","code_sha256_prefix":"2961cc94350daaae","entry":"CriticNet_bn","repo":"MLCS-Yonsei/ddpg-control","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/MLCS-Yonsei/ddpg-control/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2961cc94350daaae"}},{"code_sha256":"ebdd58004bdf82fd","code_sha256_prefix":"ebdd58004bdf82fd","entry":"CriticNetwork","repo":"YoUNG824/DDPG","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/YoUNG824/DDPG/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/criticnetwork","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ebdd58004bdf82fd"}},{"code_sha256":"4644458fd0a4374e","code_sha256_prefix":"4644458fd0a4374e","entry":"CriticNetwork","repo":"bmeyers/VirtualMicrogridSegmentation","repo_kind":"listed","path":"virtual_microgrids/algorithms/ddpg.py","file_url":"https://github.com/bmeyers/VirtualMicrogridSegmentation/blob/HEAD/virtual_microgrids/algorithms/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/criticnetwork","census":null,"licence":"BSD-2-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4644458fd0a4374e"}},{"code_sha256":"6bb81ff3c30fb32a","code_sha256_prefix":"6bb81ff3c30fb32a","entry":"CriticNetwork","repo":"samuelmat19/DDPG-tf2","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/samuelmat19/DDPG-tf2/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/criticnetwork","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6bb81ff3c30fb32a"}},{"code_sha256":"e8ec892b92d9062e","code_sha256_prefix":"e8ec892b92d9062e","entry":"Critic_network","repo":"ailab-pku/rl-framework","repo_kind":"listed","path":"DDPG/tensorflow/DDPG.py","file_url":"https://github.com/ailab-pku/rl-framework/blob/HEAD/DDPG/tensorflow/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ailab-pku/rl-framework when it was checked","mcp_get_code":{"code_sha256":"e8ec892b92d9062e"}},{"code_sha256":"9f83c78d8022ed75","code_sha256_prefix":"9f83c78d8022ed75","entry":"DDPG","repo":"MLCS-Yonsei/ddpg-control","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/MLCS-Yonsei/ddpg-control/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9f83c78d8022ed75"}},{"code_sha256":"ced83557bfb5a383","code_sha256_prefix":"ced83557bfb5a383","entry":"DDPG","repo":"YoUNG824/DDPG","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/YoUNG824/DDPG/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ced83557bfb5a383"}},{"code_sha256":"5145b262fcd6a876","code_sha256_prefix":"5145b262fcd6a876","entry":"DDPG","repo":"ghliu/pytorch-ddpg","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/ghliu/pytorch-ddpg/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5145b262fcd6a876"}},{"code_sha256":"a6abf3bfff439ec4","code_sha256_prefix":"a6abf3bfff439ec4","entry":"DDPG","repo":"stevenpjg/ddpg-aigym","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/stevenpjg/ddpg-aigym/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a6abf3bfff439ec4"}},{"code_sha256":"eb9e7e016a76b1f8","code_sha256_prefix":"eb9e7e016a76b1f8","entry":"DDPG","repo":"saoudh/Reinforcement-Learning","repo_kind":"listed","path":"DDPG-master/rllab/DDPG.py","file_url":"https://github.com/saoudh/Reinforcement-Learning/blob/HEAD/DDPG-master/rllab/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, saoudh/Reinforcement-Learning when it was checked","mcp_get_code":{"code_sha256":"eb9e7e016a76b1f8"}},{"code_sha256":"d09f9c9f2dc485f8","code_sha256_prefix":"d09f9c9f2dc485f8","entry":"DDPG","repo":"thainv0212/re-ddpg","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/thainv0212/re-ddpg/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d09f9c9f2dc485f8"}},{"code_sha256":"dcb47558604bda70","code_sha256_prefix":"dcb47558604bda70","entry":"DDPG","repo":"TheInfamousWayne/ddpg","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/TheInfamousWayne/ddpg/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"dcb47558604bda70"}},{"code_sha256":"51208e609141fcee","code_sha256_prefix":"51208e609141fcee","entry":"DDPG","repo":"dan-lennox/ml-udacity-quadcopter-rl","repo_kind":"listed","path":"agents/agent.py","file_url":"https://github.com/dan-lennox/ml-udacity-quadcopter-rl/blob/HEAD/agents/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, dan-lennox/ml-udacity-quadcopter-rl when it was checked","mcp_get_code":{"code_sha256":"51208e609141fcee"}},{"code_sha256":"8190363f4546bfd1","code_sha256_prefix":"8190363f4546bfd1","entry":"DDPG","repo":"halajadallah/RL-Quadcopter_project","repo_kind":"listed","path":"agents/agent_modified.py","file_url":"https://github.com/halajadallah/RL-Quadcopter_project/blob/HEAD/agents/agent_modified.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, halajadallah/RL-Quadcopter_project when it was checked","mcp_get_code":{"code_sha256":"8190363f4546bfd1"}},{"code_sha256":"ae6be9eb7b4764c8","code_sha256_prefix":"ae6be9eb7b4764c8","entry":"DDPG","repo":"Dekki-Aero/DDPG","repo_kind":"listed","path":"DDPG-TF/ddpg/ddpg.py","file_url":"https://github.com/Dekki-Aero/DDPG/blob/HEAD/DDPG-TF/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Dekki-Aero/DDPG when it was checked","mcp_get_code":{"code_sha256":"ae6be9eb7b4764c8"}},{"code_sha256":"397b92de9510f2f3","code_sha256_prefix":"397b92de9510f2f3","entry":"DDPG","repo":"madvn/DDPG","repo_kind":"listed","path":"ddpg/ddpg.py","file_url":"https://github.com/madvn/DDPG/blob/HEAD/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, madvn/DDPG when it was checked","mcp_get_code":{"code_sha256":"397b92de9510f2f3"}},{"code_sha256":"c328a2f2ee939de2","code_sha256_prefix":"c328a2f2ee939de2","entry":"DDPG","repo":"tensorlayer/RLzoo","repo_kind":"listed","path":"rlzoo/algorithms/ddpg/ddpg.py","file_url":"https://github.com/tensorlayer/RLzoo/blob/HEAD/rlzoo/algorithms/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c328a2f2ee939de2"}},{"code_sha256":"499a19e5cb3d719d","code_sha256_prefix":"499a19e5cb3d719d","entry":"DDPG","repo":"shahabi8/Deep-Reinforcement-Learning","repo_kind":"listed","path":"DDGP.py","file_url":"https://github.com/shahabi8/Deep-Reinforcement-Learning/blob/HEAD/DDGP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, shahabi8/Deep-Reinforcement-Learning when it was checked","mcp_get_code":{"code_sha256":"499a19e5cb3d719d"}},{"code_sha256":"77ca3b0e41fef94a","code_sha256_prefix":"77ca3b0e41fef94a","entry":"DDPG","repo":"JonasRSV/DDPG","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/JonasRSV/DDPG/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, JonasRSV/DDPG when it was checked","mcp_get_code":{"code_sha256":"77ca3b0e41fef94a"}},{"code_sha256":"1853e9d1db43078d","code_sha256_prefix":"1853e9d1db43078d","entry":"DDPG","repo":"alathiya/RL-Quadcoptor-Flying","repo_kind":"listed","path":"agents/agent.py","file_url":"https://github.com/alathiya/RL-Quadcoptor-Flying/blob/HEAD/agents/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, alathiya/RL-Quadcoptor-Flying when it was checked","mcp_get_code":{"code_sha256":"1853e9d1db43078d"}},{"code_sha256":"7c027fdd3a59bfb8","code_sha256_prefix":"7c027fdd3a59bfb8","entry":"DDPG","repo":"dyth/doublegum","repo_kind":"listed","path":"policies_cont/agents/DDPG.py","file_url":"https://github.com/dyth/doublegum/blob/HEAD/policies_cont/agents/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7c027fdd3a59bfb8"}},{"code_sha256":"e8dad0570efe7ab9","code_sha256_prefix":"e8dad0570efe7ab9","entry":"DDPG","repo":"WittmannF/quadcopter-best-practices","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/WittmannF/quadcopter-best-practices/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, WittmannF/quadcopter-best-practices when it was checked","mcp_get_code":{"code_sha256":"e8dad0570efe7ab9"}},{"code_sha256":"ae000ab63f993f26","code_sha256_prefix":"ae000ab63f993f26","entry":"DDPG","repo":"abbadka/quadcopter","repo_kind":"listed","path":"agents/ddpg/agent.py","file_url":"https://github.com/abbadka/quadcopter/blob/HEAD/agents/ddpg/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, abbadka/quadcopter when it was checked","mcp_get_code":{"code_sha256":"ae000ab63f993f26"}},{"code_sha256":"42c7eae4db28a7cb","code_sha256_prefix":"42c7eae4db28a7cb","entry":"DDPG","repo":"bmeyers/VirtualMicrogridSegmentation","repo_kind":"listed","path":"virtual_microgrids/algorithms/ddpg.py","file_url":"https://github.com/bmeyers/VirtualMicrogridSegmentation/blob/HEAD/virtual_microgrids/algorithms/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"BSD-2-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"42c7eae4db28a7cb"}},{"code_sha256":"caf935ecdc9a432e","code_sha256_prefix":"caf935ecdc9a432e","entry":"DDPG","repo":"anita-hu/TF2-RL","repo_kind":"listed","path":"DDPG/TF2_DDPG_Basic.py","file_url":"https://github.com/anita-hu/TF2-RL/blob/HEAD/DDPG/TF2_DDPG_Basic.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"caf935ecdc9a432e"}},{"code_sha256":"752f0cadbbfe89a3","code_sha256_prefix":"752f0cadbbfe89a3","entry":"DDPG","repo":"susan-amin/SparseBaseline1","repo_kind":"listed","path":"engine/algorithms/DDPG/ddpg.py","file_url":"https://github.com/susan-amin/SparseBaseline1/blob/HEAD/engine/algorithms/DDPG/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, susan-amin/SparseBaseline1 when it was checked","mcp_get_code":{"code_sha256":"752f0cadbbfe89a3"}},{"code_sha256":"3355949c0d857a6e","code_sha256_prefix":"3355949c0d857a6e","entry":"DDPG","repo":"majercakdavid/gym-virtual-quant-trading","repo_kind":"listed","path":"agents/DDPG.py","file_url":"https://github.com/majercakdavid/gym-virtual-quant-trading/blob/HEAD/agents/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, majercakdavid/gym-virtual-quant-trading (NOASSERTION)","mcp_get_code":{"code_sha256":"3355949c0d857a6e"}},{"code_sha256":"e88bf23758633506","code_sha256_prefix":"e88bf23758633506","entry":"DDPG","repo":"DanielLSM/safe-rl-tutorial","repo_kind":"listed","path":"tutorial/ddpg.py","file_url":"https://github.com/DanielLSM/safe-rl-tutorial/blob/HEAD/tutorial/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e88bf23758633506"}},{"code_sha256":"b861cffa858f460c","code_sha256_prefix":"b861cffa858f460c","entry":"DDPG","repo":"Philori22/DDPG-aigym","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/Philori22/DDPG-aigym/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Philori22/DDPG-aigym when it was checked","mcp_get_code":{"code_sha256":"b861cffa858f460c"}},{"code_sha256":"a7f923df06fb12c2","code_sha256_prefix":"a7f923df06fb12c2","entry":"DDPG","repo":"SaminYeasar/off_policy_ac","repo_kind":"listed","path":"DDPG/DDPG.py","file_url":"https://github.com/SaminYeasar/off_policy_ac/blob/HEAD/DDPG/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, SaminYeasar/off_policy_ac when it was checked","mcp_get_code":{"code_sha256":"a7f923df06fb12c2"}},{"code_sha256":"d96fe6b321763c14","code_sha256_prefix":"d96fe6b321763c14","entry":"DDPGAgent","repo":"J93T/TP4-DDPG","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/J93T/TP4-DDPG/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/ddpgagent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, J93T/TP4-DDPG when it was checked","mcp_get_code":{"code_sha256":"d96fe6b321763c14"}},{"code_sha256":"4b11a27451c374cd","code_sha256_prefix":"4b11a27451c374cd","entry":"DDPGAgent","repo":"InSpaceAI/RL-Zoo","repo_kind":"listed","path":"DDPG.py","file_url":"https://github.com/InSpaceAI/RL-Zoo/blob/HEAD/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/ddpgagent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, InSpaceAI/RL-Zoo when it was checked","mcp_get_code":{"code_sha256":"4b11a27451c374cd"}},{"code_sha256":"76a41f814d76f5c0","code_sha256_prefix":"76a41f814d76f5c0","entry":"DDPGAgent","repo":"hemilpanchiwala/Hindsight-Experience-Replay","repo_kind":"listed","path":"ddpg_with_her/DDPGAgent.py","file_url":"https://github.com/hemilpanchiwala/Hindsight-Experience-Replay/blob/HEAD/ddpg_with_her/DDPGAgent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/ddpgagent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hemilpanchiwala/Hindsight-Experience-Replay when it was checked","mcp_get_code":{"code_sha256":"76a41f814d76f5c0"}},{"code_sha256":"5b513793c76f96d8","code_sha256_prefix":"5b513793c76f96d8","entry":"DDPGAgent","repo":"denizmguen/IANNWTF2019-Project","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/denizmguen/IANNWTF2019-Project/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/ddpgagent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, denizmguen/IANNWTF2019-Project when it was checked","mcp_get_code":{"code_sha256":"5b513793c76f96d8"}},{"code_sha256":"fb2a2e6b4cc0d551","code_sha256_prefix":"fb2a2e6b4cc0d551","entry":"DDPGAgent","repo":"soumik12345/DDPG","repo_kind":"listed","path":"src/agents.py","file_url":"https://github.com/soumik12345/DDPG/blob/HEAD/src/agents.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/ddpgagent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, soumik12345/DDPG when it was checked","mcp_get_code":{"code_sha256":"fb2a2e6b4cc0d551"}},{"code_sha256":"c0e725d5bf9fb153","code_sha256_prefix":"c0e725d5bf9fb153","entry":"DDPGAgent","repo":"KelvinYang0320/deepbots-panda","repo_kind":"listed","path":"Panda_RL/controllers/robot_supervisor_manager/agent/ddpg.py","file_url":"https://github.com/KelvinYang0320/deepbots-panda/blob/HEAD/Panda_RL/controllers/robot_supervisor_manager/agent/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/ddpgagent","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c0e725d5bf9fb153"}},{"code_sha256":"078c84de4438f91b","code_sha256_prefix":"078c84de4438f91b","entry":"DDPGController","repo":"guillaumeboniface/reacher","repo_kind":"listed","path":"ddpg_controller.py","file_url":"https://github.com/guillaumeboniface/reacher/blob/HEAD/ddpg_controller.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, guillaumeboniface/reacher when it was checked","mcp_get_code":{"code_sha256":"078c84de4438f91b"}},{"code_sha256":"af8a78d9208cc109","code_sha256_prefix":"af8a78d9208cc109","entry":"DDPG_agent","repo":"xyshadow/baseline_ddpg","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/xyshadow/baseline_ddpg/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"af8a78d9208cc109"}},{"code_sha256":"b2fbe2ad70b688a2","code_sha256_prefix":"b2fbe2ad70b688a2","entry":"DDPG_model","repo":"ailab-pku/rl-framework","repo_kind":"listed","path":"DDPG/tensorflow/DDPG.py","file_url":"https://github.com/ailab-pku/rl-framework/blob/HEAD/DDPG/tensorflow/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ailab-pku/rl-framework when it was checked","mcp_get_code":{"code_sha256":"b2fbe2ad70b688a2"}},{"code_sha256":"95b0927e10c3dd78","code_sha256_prefix":"95b0927e10c3dd78","entry":"Ddpg","repo":"mathformoso/RL-playground---ddpg","repo_kind":"listed","path":"DDPG.py","file_url":"https://github.com/mathformoso/RL-playground---ddpg/blob/HEAD/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"95b0927e10c3dd78"}},{"code_sha256":"ff673a112b0d8acd","code_sha256_prefix":"ff673a112b0d8acd","entry":"DeepDeterministicPolicyGradient","repo":"yukezhu/tensorflow-reinforce","repo_kind":"listed","path":"rl/pg_ddpg.py","file_url":"https://github.com/yukezhu/tensorflow-reinforce/blob/HEAD/rl/pg_ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ff673a112b0d8acd"}},{"code_sha256":"9c10e0c8cad8f8a1","code_sha256_prefix":"9c10e0c8cad8f8a1","entry":"EncoderType","repo":"avivelor/UnityMachineLearningForProjectButterfly","repo_kind":"listed","path":"ml-agents/mlagents/trainers/sac/models.py","file_url":"https://github.com/avivelor/UnityMachineLearningForProjectButterfly/blob/HEAD/ml-agents/mlagents/trainers/sac/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9c10e0c8cad8f8a1"}},{"code_sha256":"d702970461989ce2","code_sha256_prefix":"d702970461989ce2","entry":"GaussianPolicyHead","repo":"Souphis/mobile_robot_rl","repo_kind":"listed","path":"mobile_robot_rl/agents/sac.py","file_url":"https://github.com/Souphis/mobile_robot_rl/blob/HEAD/mobile_robot_rl/agents/sac.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d702970461989ce2"}},{"code_sha256":"c3809b45fe3af363","code_sha256_prefix":"c3809b45fe3af363","entry":"LearningModel","repo":"avivelor/UnityMachineLearningForProjectButterfly","repo_kind":"listed","path":"ml-agents/mlagents/trainers/sac/models.py","file_url":"https://github.com/avivelor/UnityMachineLearningForProjectButterfly/blob/HEAD/ml-agents/mlagents/trainers/sac/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c3809b45fe3af363"}},{"code_sha256":"709bf3140064269c","code_sha256_prefix":"709bf3140064269c","entry":"LearningRateSchedule","repo":"avivelor/UnityMachineLearningForProjectButterfly","repo_kind":"listed","path":"ml-agents/mlagents/trainers/sac/models.py","file_url":"https://github.com/avivelor/UnityMachineLearningForProjectButterfly/blob/HEAD/ml-agents/mlagents/trainers/sac/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"709bf3140064269c"}},{"code_sha256":"ed80a9cbb590756d","code_sha256_prefix":"ed80a9cbb590756d","entry":"MADDPG_Agent","repo":"sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3","repo_kind":"listed","path":"maddpgAgent.py","file_url":"https://github.com/sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3/blob/HEAD/maddpgAgent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3 when it was checked","mcp_get_code":{"code_sha256":"ed80a9cbb590756d"}},{"code_sha256":"84a671ee7bad8513","code_sha256_prefix":"84a671ee7bad8513","entry":"Memory","repo":"anita-hu/TF2-RL","repo_kind":"listed","path":"DDPG/TF2_DDPG_Basic.py","file_url":"https://github.com/anita-hu/TF2-RL/blob/HEAD/DDPG/TF2_DDPG_Basic.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/memory","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"84a671ee7bad8513"}},{"code_sha256":"c3b2071edfe94da7","code_sha256_prefix":"c3b2071edfe94da7","entry":"NAF","repo":"MathPhysSim/PER-NAF","repo_kind":"listed","path":"pernaf/pernaf/naf.py","file_url":"https://github.com/MathPhysSim/PER-NAF/blob/HEAD/pernaf/pernaf/naf.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c3b2071edfe94da7"}},{"code_sha256":"cd47b224d263fba6","code_sha256_prefix":"cd47b224d263fba6","entry":"OrnsteinUhlenbeck","repo":"denizmguen/IANNWTF2019-Project","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/denizmguen/IANNWTF2019-Project/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, denizmguen/IANNWTF2019-Project when it was checked","mcp_get_code":{"code_sha256":"cd47b224d263fba6"}},{"code_sha256":"b34e1d14d05b3345","code_sha256_prefix":"b34e1d14d05b3345","entry":"PrioritizedReplayBuffer","repo":"MathPhysSim/PER-NAF","repo_kind":"listed","path":"pernaf/pernaf/naf.py","file_url":"https://github.com/MathPhysSim/PER-NAF/blob/HEAD/pernaf/pernaf/naf.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b34e1d14d05b3345"}},{"code_sha256":"66f422ab00f28663","code_sha256_prefix":"66f422ab00f28663","entry":"RDPG","repo":"fshamshirdar/pytorch-rdpg","repo_kind":"listed","path":"rdpg.py","file_url":"https://github.com/fshamshirdar/pytorch-rdpg/blob/HEAD/rdpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, fshamshirdar/pytorch-rdpg when it was checked","mcp_get_code":{"code_sha256":"66f422ab00f28663"}},{"code_sha256":"adb269cf9b74e9a6","code_sha256_prefix":"adb269cf9b74e9a6","entry":"Reduction","repo":"Souphis/mobile_robot_rl","repo_kind":"listed","path":"mobile_robot_rl/agents/sac.py","file_url":"https://github.com/Souphis/mobile_robot_rl/blob/HEAD/mobile_robot_rl/agents/sac.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"adb269cf9b74e9a6"}},{"code_sha256":"49ac8c4b2338f149","code_sha256_prefix":"49ac8c4b2338f149","entry":"ReplayBuffer","repo":"denizmguen/IANNWTF2019-Project","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/denizmguen/IANNWTF2019-Project/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/replaybuffer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, denizmguen/IANNWTF2019-Project when it was checked","mcp_get_code":{"code_sha256":"49ac8c4b2338f149"}},{"code_sha256":"0d2b4efe0274fc66","code_sha256_prefix":"0d2b4efe0274fc66","entry":"ReplayBuffer","repo":"samuelmat19/DDPG-tf2","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/samuelmat19/DDPG-tf2/blob/HEAD/src/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/replaybuffer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0d2b4efe0274fc66"}},{"code_sha256":"1229a5d8dea62487","code_sha256_prefix":"1229a5d8dea62487","entry":"ReplayBuffer","repo":"Philori22/DDPG-aigym","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/Philori22/DDPG-aigym/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/replaybuffer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Philori22/DDPG-aigym when it was checked","mcp_get_code":{"code_sha256":"1229a5d8dea62487"}},{"code_sha256":"05a3439d18f70f4b","code_sha256_prefix":"05a3439d18f70f4b","entry":"ReplayBufferPER","repo":"MathPhysSim/PER-NAF","repo_kind":"listed","path":"pernaf/pernaf/naf.py","file_url":"https://github.com/MathPhysSim/PER-NAF/blob/HEAD/pernaf/pernaf/naf.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"05a3439d18f70f4b"}},{"code_sha256":"9d5ea952455199bc","code_sha256_prefix":"9d5ea952455199bc","entry":"ReplayMemory","repo":"tilkb/thermoai","repo_kind":"listed","path":"controller/RL/DDPG.py","file_url":"https://github.com/tilkb/thermoai/blob/HEAD/controller/RL/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/replaymemory","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, tilkb/thermoai when it was checked","mcp_get_code":{"code_sha256":"9d5ea952455199bc"}},{"code_sha256":"1be47476efdc31c1","code_sha256_prefix":"1be47476efdc31c1","entry":"SAC","repo":"Souphis/mobile_robot_rl","repo_kind":"listed","path":"mobile_robot_rl/agents/sac.py","file_url":"https://github.com/Souphis/mobile_robot_rl/blob/HEAD/mobile_robot_rl/agents/sac.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/sac","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1be47476efdc31c1"}},{"code_sha256":"7b82c41b5ad0e056","code_sha256_prefix":"7b82c41b5ad0e056","entry":"SACModel","repo":"avivelor/UnityMachineLearningForProjectButterfly","repo_kind":"listed","path":"ml-agents/mlagents/trainers/sac/models.py","file_url":"https://github.com/avivelor/UnityMachineLearningForProjectButterfly/blob/HEAD/ml-agents/mlagents/trainers/sac/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7b82c41b5ad0e056"}},{"code_sha256":"338005115fd3efac","code_sha256_prefix":"338005115fd3efac","entry":"SACNetwork","repo":"avivelor/UnityMachineLearningForProjectButterfly","repo_kind":"listed","path":"ml-agents/mlagents/trainers/sac/models.py","file_url":"https://github.com/avivelor/UnityMachineLearningForProjectButterfly/blob/HEAD/ml-agents/mlagents/trainers/sac/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"338005115fd3efac"}},{"code_sha256":"8a1d8ca5ca9e0472","code_sha256_prefix":"8a1d8ca5ca9e0472","entry":"SACPolicyNetwork","repo":"avivelor/UnityMachineLearningForProjectButterfly","repo_kind":"listed","path":"ml-agents/mlagents/trainers/sac/models.py","file_url":"https://github.com/avivelor/UnityMachineLearningForProjectButterfly/blob/HEAD/ml-agents/mlagents/trainers/sac/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8a1d8ca5ca9e0472"}},{"code_sha256":"ac81a4e465c9a89b","code_sha256_prefix":"ac81a4e465c9a89b","entry":"SACTargetNetwork","repo":"avivelor/UnityMachineLearningForProjectButterfly","repo_kind":"listed","path":"ml-agents/mlagents/trainers/sac/models.py","file_url":"https://github.com/avivelor/UnityMachineLearningForProjectButterfly/blob/HEAD/ml-agents/mlagents/trainers/sac/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ac81a4e465c9a89b"}},{"code_sha256":"97e32fd094fe28c9","code_sha256_prefix":"97e32fd094fe28c9","entry":"SumTree","repo":"anita-hu/TF2-RL","repo_kind":"listed","path":"DDPG/TF2_DDPG_Basic.py","file_url":"https://github.com/anita-hu/TF2-RL/blob/HEAD/DDPG/TF2_DDPG_Basic.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"97e32fd094fe28c9"}},{"code_sha256":"2d6179a73f14ca5e","code_sha256_prefix":"2d6179a73f14ca5e","entry":"UnityException","repo":"avivelor/UnityMachineLearningForProjectButterfly","repo_kind":"listed","path":"ml-agents/mlagents/trainers/sac/models.py","file_url":"https://github.com/avivelor/UnityMachineLearningForProjectButterfly/blob/HEAD/ml-agents/mlagents/trainers/sac/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2d6179a73f14ca5e"}},{"code_sha256":"28af75dd1e756e4d","code_sha256_prefix":"28af75dd1e756e4d","entry":"UnityTrainerException","repo":"avivelor/UnityMachineLearningForProjectButterfly","repo_kind":"listed","path":"ml-agents/mlagents/trainers/sac/models.py","file_url":"https://github.com/avivelor/UnityMachineLearningForProjectButterfly/blob/HEAD/ml-agents/mlagents/trainers/sac/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"28af75dd1e756e4d"}},{"code_sha256":"7484fd6def5722c7","code_sha256_prefix":"7484fd6def5722c7","entry":"batch_norm","repo":"MLCS-Yonsei/ddpg-control","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/MLCS-Yonsei/ddpg-control/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/batch-norm","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7484fd6def5722c7"}},{"code_sha256":"930b524d6b021ed1","code_sha256_prefix":"930b524d6b021ed1","entry":"batch_norm","repo":"tegg89/DLCamp_Jeju2018","repo_kind":"listed","path":"models/action_execution/actor_critic_nn.py","file_url":"https://github.com/tegg89/DLCamp_Jeju2018/blob/HEAD/models/action_execution/actor_critic_nn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/batch-norm","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"930b524d6b021ed1"}},{"code_sha256":"c04864a6841339e7","code_sha256_prefix":"c04864a6841339e7","entry":"check_next_to_bomb","repo":"tegg89/DLCamp_Jeju2018","repo_kind":"listed","path":"env_processing/shaping.py","file_url":"https://github.com/tegg89/DLCamp_Jeju2018/blob/HEAD/env_processing/shaping.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c04864a6841339e7"}},{"code_sha256":"fa624e896014aa19","code_sha256_prefix":"fa624e896014aa19","entry":"ddpg_trainer","repo":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","repo_kind":"listed","path":"software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","file_url":"https://github.com/dfki-ric-underactuated-lab/torque_limited_simple_pendulum/blob/HEAD/software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"fa624e896014aa19"}},{"code_sha256":"e95e6dd3a35646ba","code_sha256_prefix":"e95e6dd3a35646ba","entry":"discretize","repo":"tegg89/DLCamp_Jeju2018","repo_kind":"listed","path":"models/action_execution/actor_critic_nn.py","file_url":"https://github.com/tegg89/DLCamp_Jeju2018/blob/HEAD/models/action_execution/actor_critic_nn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/discretize","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e95e6dd3a35646ba"}},{"code_sha256":"dfd2f69c5bd6bd73","code_sha256_prefix":"dfd2f69c5bd6bd73","entry":"export_plot","repo":"bmeyers/VirtualMicrogridSegmentation","repo_kind":"listed","path":"virtual_microgrids/algorithms/ddpg.py","file_url":"https://github.com/bmeyers/VirtualMicrogridSegmentation/blob/HEAD/virtual_microgrids/algorithms/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"BSD-2-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"dfd2f69c5bd6bd73"}},{"code_sha256":"af08b37858b1dd07","code_sha256_prefix":"af08b37858b1dd07","entry":"fan_in_uniform_init","repo":"majercakdavid/gym-virtual-quant-trading","repo_kind":"listed","path":"agents/DDPG.py","file_url":"https://github.com/majercakdavid/gym-virtual-quant-trading/blob/HEAD/agents/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, majercakdavid/gym-virtual-quant-trading (NOASSERTION)","mcp_get_code":{"code_sha256":"af08b37858b1dd07"}},{"code_sha256":"a6b3153326abaddd","code_sha256_prefix":"a6b3153326abaddd","entry":"freeze","repo":"HJDQN/HJQ","repo_kind":"listed","path":"algorithms/ddpg/ddpg.py","file_url":"https://github.com/HJDQN/HJQ/blob/HEAD/algorithms/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/freeze","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, HJDQN/HJQ when it was checked","mcp_get_code":{"code_sha256":"a6b3153326abaddd"}},{"code_sha256":"ff560a45eef0d026","code_sha256_prefix":"ff560a45eef0d026","entry":"grad_inverter","repo":"MLCS-Yonsei/ddpg-control","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/MLCS-Yonsei/ddpg-control/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ff560a45eef0d026"}},{"code_sha256":"88db7be53206704c","code_sha256_prefix":"88db7be53206704c","entry":"grad_inverter","repo":"stevenpjg/ddpg-aigym","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/stevenpjg/ddpg-aigym/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"88db7be53206704c"}},{"code_sha256":"e78231c9f4eb9c2f","code_sha256_prefix":"e78231c9f4eb9c2f","entry":"hist_summaries","repo":"SimonRamstedt/ddpg","repo_kind":"listed","path":"ddpg_nets_dm.py","file_url":"https://github.com/SimonRamstedt/ddpg/blob/HEAD/ddpg_nets_dm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e78231c9f4eb9c2f"}},{"code_sha256":"269f19cc9358c590","code_sha256_prefix":"269f19cc9358c590","entry":"init_weights","repo":"Medabid1/RL_Project","repo_kind":"listed","path":"network/Networks.py","file_url":"https://github.com/Medabid1/RL_Project/blob/HEAD/network/Networks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/init-weights","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Medabid1/RL_Project when it was checked","mcp_get_code":{"code_sha256":"269f19cc9358c590"}},{"code_sha256":"8e9ed77aca673ea4","code_sha256_prefix":"8e9ed77aca673ea4","entry":"model_NN1","repo":"tegg89/DLCamp_Jeju2018","repo_kind":"listed","path":"models/graph_construction/NN1.py","file_url":"https://github.com/tegg89/DLCamp_Jeju2018/blob/HEAD/models/graph_construction/NN1.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8e9ed77aca673ea4"}},{"code_sha256":"13e0cdee9d418dbc","code_sha256_prefix":"13e0cdee9d418dbc","entry":"model_NN2","repo":"tegg89/DLCamp_Jeju2018","repo_kind":"listed","path":"models/action_execution/NN2.py","file_url":"https://github.com/tegg89/DLCamp_Jeju2018/blob/HEAD/models/action_execution/NN2.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"13e0cdee9d418dbc"}},{"code_sha256":"54074d019aff0495","code_sha256_prefix":"54074d019aff0495","entry":"normal_dist","repo":"Crevass/Hybrid-Agent","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/Crevass/Hybrid-Agent/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Crevass/Hybrid-Agent when it was checked","mcp_get_code":{"code_sha256":"54074d019aff0495"}},{"code_sha256":"698f442074344c97","code_sha256_prefix":"698f442074344c97","entry":"policy","repo":"SimonRamstedt/ddpg","repo_kind":"listed","path":"ddpg_nets_dm.py","file_url":"https://github.com/SimonRamstedt/ddpg/blob/HEAD/ddpg_nets_dm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/policy-2","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"698f442074344c97"}},{"code_sha256":"093c23bdbb785c8a","code_sha256_prefix":"093c23bdbb785c8a","entry":"reward_shaping","repo":"tegg89/DLCamp_Jeju2018","repo_kind":"listed","path":"env_processing/shaping.py","file_url":"https://github.com/tegg89/DLCamp_Jeju2018/blob/HEAD/env_processing/shaping.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"093c23bdbb785c8a"}},{"code_sha256":"14b6d9e3982a117c","code_sha256_prefix":"14b6d9e3982a117c","entry":"run_ddpg","repo":"HJDQN/HJQ","repo_kind":"listed","path":"algorithms/ddpg/ddpg.py","file_url":"https://github.com/HJDQN/HJQ/blob/HEAD/algorithms/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, HJDQN/HJQ when it was checked","mcp_get_code":{"code_sha256":"14b6d9e3982a117c"}},{"code_sha256":"c6840dd2ce1ed774","code_sha256_prefix":"c6840dd2ce1ed774","entry":"set_arrow_properties","repo":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","repo_kind":"listed","path":"software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","file_url":"https://github.com/dfki-ric-underactuated-lab/torque_limited_simple_pendulum/blob/HEAD/software/python/simple_pendulum/reinforcement_learning/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c6840dd2ce1ed774"}},{"code_sha256":"e58c3a477f895e6c","code_sha256_prefix":"e58c3a477f895e6c","entry":"set_log_dir","repo":"HJDQN/HJQ","repo_kind":"listed","path":"algorithms/ddpg/ddpg.py","file_url":"https://github.com/HJDQN/HJQ/blob/HEAD/algorithms/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, HJDQN/HJQ when it was checked","mcp_get_code":{"code_sha256":"e58c3a477f895e6c"}},{"code_sha256":"af1d4d0c4d0351c5","code_sha256_prefix":"af1d4d0c4d0351c5","entry":"sharpe","repo":"wassname/rl-portfolio-management","repo_kind":"listed","path":"rl_portfolio_management/util.py","file_url":"https://github.com/wassname/rl-portfolio-management/blob/HEAD/rl_portfolio_management/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"af1d4d0c4d0351c5"}},{"code_sha256":"0374c56639501f7a","code_sha256_prefix":"0374c56639501f7a","entry":"sn","repo":"dyth/doublegum","repo_kind":"listed","path":"policies_cont/agents/DDPG.py","file_url":"https://github.com/dyth/doublegum/blob/HEAD/policies_cont/agents/DDPG.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0374c56639501f7a"}},{"code_sha256":"84d603f2102cf1ed","code_sha256_prefix":"84d603f2102cf1ed","entry":"softmax","repo":"wassname/rl-portfolio-management","repo_kind":"listed","path":"rl_portfolio_management/util.py","file_url":"https://github.com/wassname/rl-portfolio-management/blob/HEAD/rl_portfolio_management/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/softmax","census":{"url":"/census/softmax","implementations":53,"papers":63,"distinct_outputs":16,"n_buckets":8,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"84d603f2102cf1ed"}},{"code_sha256":"7f073c276baecc11","code_sha256_prefix":"7f073c276baecc11","entry":"train","repo":"liampetti/DDPG","repo_kind":"listed","path":"ddpg.py","file_url":"https://github.com/liampetti/DDPG/blob/HEAD/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/train","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, liampetti/DDPG when it was checked","mcp_get_code":{"code_sha256":"7f073c276baecc11"}},{"code_sha256":"24c0dee0fb0fec39","code_sha256_prefix":"24c0dee0fb0fec39","entry":"unfreeze","repo":"HJDQN/HJQ","repo_kind":"listed","path":"algorithms/ddpg/ddpg.py","file_url":"https://github.com/HJDQN/HJQ/blob/HEAD/algorithms/ddpg/ddpg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, HJDQN/HJQ when it was checked","mcp_get_code":{"code_sha256":"24c0dee0fb0fec39"}},{"code_sha256":"ac16f6e8f09e31bc","code_sha256_prefix":"ac16f6e8f09e31bc","entry":"update_target_weights","repo":"anita-hu/TF2-RL","repo_kind":"listed","path":"DDPG/TF2_DDPG_Basic.py","file_url":"https://github.com/anita-hu/TF2-RL/blob/HEAD/DDPG/TF2_DDPG_Basic.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ac16f6e8f09e31bc"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"baad68ce53b63c26edce3cc61ad8fcfd1840117a0fea591f745a1235e3624dd7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}