{"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/soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","arxiv_id":"1801.01290","date":"2018-01-04","proceeding":"ICML 2018 7","authors":["Tuomas Haarnoja","Aurick Zhou","Pieter Abbeel","Sergey Levine"],"abstract":"A platform for Applied Reinforcement Learning (Applied RL)","url_abs":"http://arxiv.org/abs/1801.01290v2","url_pdf":"http://arxiv.org/pdf/1801.01290v2.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":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/haarnoja/sac","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/AmmarFayad/Behavioral-Actor-Critic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/AutumnWu/Streamlined-Off-Policy-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/FOCAL-ICLR/FOCAL-ICLR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/Kaixhin/imitation-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/MarsEleven/car_racer_RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","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":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/QuentinVacher-rl/SoftActorCritic-in-Cpp-using-LibTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/RLAgent/state-marginal-matching","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","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":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/ShawK91/Evolutionary-Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/ShawK91/erl_paper_nips18","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/Steinheilig/Imbiss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/X3N4/car_racer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/ac-93/soft-actor-critic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/ajaysub110/rl-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/andrejorsula/drl_grasping","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/araffin/sbx","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/autumnwu/aggressive-q-learning-with-ensembles","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/baturaysaglam/la3p","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/ccolas/rl_stats","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/cindycia/Atari-SAC-Discrete","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/core-robotics-lab/icct","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/dasgringuen/assetto_corsa_gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","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":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/donamin/llc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/facebookresearch/ReAgent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","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":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/flowersteam/rl_stats","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/garyzyr001/rethinking-airl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/gijskoning/ReproducingCURL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","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":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/hyunin-lee/ForecasterSAC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/ikostrikov/jax-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/kairproject/kair_algorithms_draft","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/kdally/fault-tolerant-flight-control-drl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/ku2482/discor.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/ku2482/gail-airl-ppo.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/ku2482/rljax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/ku2482/rltorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/ku2482/soft-actor-critic.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/kushagra06/SAC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/lanqingli1993/focal-iclr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/learn-to-race/l2r","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-2.0"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/lollcat/Soft-Actor-Critic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/lucadellalib/sac-beta","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","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":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/moreanp/csro","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/mxblr/DeepRLHockey","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/nagisazj/idaq_public","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/polixir/NeoRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/pranz24/pytorch-soft-actor-critic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/quantumiracle/Popular-RL-Algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","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":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/roythuly/obac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/sunfex/weighted-sac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","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":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/tarod13/SAC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/thomashirtz/pytorch-soft-actor-critic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/thomashirtz/soft-actor-critic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/tilkb/thermoai","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/timoklein/car_racer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/tliu1997/rnac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/tmjeong1103/RL_with_RAY","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/toshikwa/discor.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/toshikwa/soft-actor-critic.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/trackmania-rl/tmrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/watchernyu/spinningup-drl-prototyping","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/yhisaki/average-reward-drl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/yimingpeng/sac-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/yining043/SAC-discrete","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/BY571/Soft-Actor-Critic-and-Extensions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","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":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/Ipsedo/EvoMotion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/facebookresearch/rl/blob/main/examples/sac/sac.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","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":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/jakegrigsby/deep_control/blob/master/deep_control/sac.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/sac.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/pytorch/rl/tree/main/examples/sac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","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":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/seungju-k1m/sac-td3-td7","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/tensorlayer/RLzoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","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"}},{"paper_slug":"soft-actor-critic-off-policy-maximum-entropy","repo_url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/sac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"omniverse-isaac-gym","task_name":"Omniverse Isaac Gym"},{"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":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"soft-actor-critic","method_name":"Soft Actor Critic"}],"datasets_introduced":[],"methods_introduced":[{"slug":"soft-actor-critic","name":"Soft Actor Critic","full_name":"Soft Actor Critic"}],"results":[{"leaderboard":"/sota/continuous-control-on-lunar-lander-openai-gym","task":"Continuous Control","dataset":"Lunar Lander (OpenAI Gym)","model":"SAC","rank_in_archive_order":1,"of":5,"metrics":{"Score":"284.59±0.97"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-ant-v4","task":"OpenAI Gym","dataset":"Ant-v4","model":"SAC","rank_in_archive_order":3,"of":5,"metrics":{"Average Return":"5208.09"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-halfcheetah-v4","task":"OpenAI Gym","dataset":"HalfCheetah-v4","model":"SAC","rank_in_archive_order":1,"of":5,"metrics":{"Average Return":"15836.04"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-hopper-v4","task":"OpenAI Gym","dataset":"Hopper-v4","model":"SAC","rank_in_archive_order":3,"of":5,"metrics":{"Average Return":"2882.56"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-humanoid-v4","task":"OpenAI Gym","dataset":"Humanoid-v4","model":"SAC","rank_in_archive_order":2,"of":5,"metrics":{"Average Return":"6211.50"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-walker2d-v4","task":"OpenAI Gym","dataset":"Walker2d-v4","model":"SAC","rank_in_archive_order":1,"of":5,"metrics":{"Average Return":"5745.27"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.01290","atlas_url":"https://app.syntology.ai/?focus=1801.01290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.01290"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1801.01290"},"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":"1801.01290"},"call":"get_harvested_code_for_paper(arxiv_id=\"1801.01290\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"1801.01290"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1801.01290\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1801.01290"},"call":"get_concepts_for_paper(arxiv_id=\"1801.01290\")"}],"by_repo":[{"repo":"haarnoja/sac","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"AmmarFayad/Behavioral-Actor-Critic","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"AutumnWu/Streamlined-Off-Policy-Learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"FOCAL-ICLR/FOCAL-ICLR","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2010.01112"],"harvested_for_calls":[{"arxiv_id":"2010.01112","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.01112"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.01112\")"}]},{"repo":"Kaixhin/imitation-learning","kind":"listed","samples":2,"ran":2,"instrument":1,"unverified":0},{"repo":"MarsEleven/car_racer_RL","kind":"listed","samples":7,"ran":3,"instrument":0,"unverified":4},{"repo":"MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning","kind":"listed","samples":7,"ran":6,"instrument":0,"unverified":1},{"repo":"MrSyee/pg-is-all-you-need","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"QuentinVacher-rl/SoftActorCritic-in-Cpp-using-LibTorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"RLAgent/state-marginal-matching","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1705.05363"],"harvested_for_calls":[{"arxiv_id":"1705.05363","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1705.05363"},"call":"get_harvested_code_for_paper(arxiv_id=\"1705.05363\")"}]},{"repo":"Rafael1s/Deep-Reinforcement-Learning-Udacity","kind":"listed","samples":6,"ran":3,"instrument":0,"unverified":3},{"repo":"SaminYeasar/off_policy_ac","kind":"listed","samples":6,"ran":5,"instrument":2,"unverified":1},{"repo":"ShawK91/Evolutionary-Reinforcement-Learning","kind":"listed","samples":3,"ran":1,"instrument":0,"unverified":2},{"repo":"ShawK91/erl_paper_nips18","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Steinheilig/Imbiss","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"X3N4/car_racer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ac-93/soft-actor-critic","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1812.05905"],"harvested_for_calls":[{"arxiv_id":"1812.05905","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1812.05905"},"call":"get_harvested_code_for_paper(arxiv_id=\"1812.05905\")"}]},{"repo":"ajaysub110/rl-pytorch","kind":"listed","samples":7,"ran":2,"instrument":0,"unverified":5},{"repo":"andrejorsula/drl_grasping","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2010.02193"],"harvested_for_calls":[{"arxiv_id":"2010.02193","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.02193"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.02193\")"}]},{"repo":"araffin/sbx","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2410.09754"],"harvested_for_calls":[{"arxiv_id":"2410.09754","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.09754"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.09754\")"}]},{"repo":"autumnwu/aggressive-q-learning-with-ensembles","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"baturaysaglam/la3p","kind":"listed","samples":4,"ran":3,"instrument":0,"unverified":1},{"repo":"ccolas/rl_stats","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1904.06979"],"harvested_for_calls":[{"arxiv_id":"1904.06979","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1904.06979"},"call":"get_harvested_code_for_paper(arxiv_id=\"1904.06979\")"}]},{"repo":"cindycia/Atari-SAC-Discrete","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1910.07207"],"harvested_for_calls":[{"arxiv_id":"1910.07207","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1910.07207"},"call":"get_harvested_code_for_paper(arxiv_id=\"1910.07207\")"}]},{"repo":"core-robotics-lab/icct","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"dasgringuen/assetto_corsa_gym","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2110.06169"],"harvested_for_calls":[{"arxiv_id":"2110.06169","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2110.06169"},"call":"get_harvested_code_for_paper(arxiv_id=\"2110.06169\")"}]},{"repo":"dfki-ric-underactuated-lab/torque_limited_simple_pendulum","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1509.02971"],"harvested_for_calls":[{"arxiv_id":"1509.02971","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1509.02971"},"call":"get_harvested_code_for_paper(arxiv_id=\"1509.02971\")"}]},{"repo":"donamin/llc","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"facebookresearch/ReAgent","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":"flowersteam/rl_stats","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"garyzyr001/rethinking-airl","kind":"listed","samples":8,"ran":4,"instrument":0,"unverified":4},{"repo":"gijskoning/ReproducingCURL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"h-aboutalebi/SparceReward","kind":"listed","samples":4,"ran":3,"instrument":0,"unverified":1},{"repo":"hyunin-lee/ForecasterSAC","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"ikostrikov/jax-rl","kind":"listed","samples":4,"ran":0,"instrument":0,"unverified":4},{"repo":"kairproject/kair_algorithms_draft","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"kdally/fault-tolerant-flight-control-drl","kind":"listed","samples":10,"ran":8,"instrument":6,"unverified":2},{"repo":"ku2482/discor.pytorch","kind":"listed","samples":11,"ran":4,"instrument":1,"unverified":7},{"repo":"ku2482/gail-airl-ppo.pytorch","kind":"listed","samples":5,"ran":2,"instrument":0,"unverified":3},{"repo":"ku2482/rljax","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ku2482/rltorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1910.07207"],"harvested_for_calls":[{"arxiv_id":"1910.07207","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1910.07207"},"call":"get_harvested_code_for_paper(arxiv_id=\"1910.07207\")"}]},{"repo":"ku2482/soft-actor-critic.pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2110.02034"],"harvested_for_calls":[{"arxiv_id":"2110.02034","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2110.02034"},"call":"get_harvested_code_for_paper(arxiv_id=\"2110.02034\")"}]},{"repo":"kushagra06/SAC","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"lanqingli1993/focal-iclr","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"learn-to-race/l2r","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lollcat/Soft-Actor-Critic","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lucadellalib/sac-beta","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"marload/DeepRL-TensorFlow2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":5,"harvested_for":["1312.5602","1509.02971","1509.06461","1602.01783","1707.06347"],"harvested_for_calls":[{"arxiv_id":"1312.5602","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1312.5602"},"call":"get_harvested_code_for_paper(arxiv_id=\"1312.5602\")"},{"arxiv_id":"1509.02971","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1509.02971"},"call":"get_harvested_code_for_paper(arxiv_id=\"1509.02971\")"},{"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":"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":"moreanp/csro","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2311.03695"],"harvested_for_calls":[{"arxiv_id":"2311.03695","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2311.03695"},"call":"get_harvested_code_for_paper(arxiv_id=\"2311.03695\")"}]},{"repo":"mxblr/DeepRLHockey","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"nagisazj/idaq_public","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2305.19529"],"harvested_for_calls":[{"arxiv_id":"2305.19529","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.19529"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.19529\")"}]},{"repo":"polixir/NeoRL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"pranz24/pytorch-soft-actor-critic","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"quantumiracle/Popular-RL-Algorithms","kind":"listed","samples":4,"ran":3,"instrument":0,"unverified":1},{"repo":"rk1998/robot-sac","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"roythuly/obac","kind":"listed","samples":4,"ran":3,"instrument":0,"unverified":1},{"repo":"sunfex/weighted-sac","kind":"listed","samples":4,"ran":3,"instrument":0,"unverified":1},{"repo":"susan-amin/SparseBaseline1","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1509.02971"],"harvested_for_calls":[{"arxiv_id":"1509.02971","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1509.02971"},"call":"get_harvested_code_for_paper(arxiv_id=\"1509.02971\")"}]},{"repo":"tarod13/SAC","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"thomashirtz/pytorch-soft-actor-critic","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1812.05905"],"harvested_for_calls":[{"arxiv_id":"1812.05905","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1812.05905"},"call":"get_harvested_code_for_paper(arxiv_id=\"1812.05905\")"}]},{"repo":"thomashirtz/soft-actor-critic","kind":"listed","samples":12,"ran":7,"instrument":3,"unverified":5},{"repo":"tilkb/thermoai","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1509.02971","1707.06347"],"harvested_for_calls":[{"arxiv_id":"1509.02971","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1509.02971"},"call":"get_harvested_code_for_paper(arxiv_id=\"1509.02971\")"},{"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":"timoklein/car_racer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tliu1997/rnac","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2307.08875"],"harvested_for_calls":[{"arxiv_id":"2307.08875","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2307.08875"},"call":"get_harvested_code_for_paper(arxiv_id=\"2307.08875\")"}]},{"repo":"tmjeong1103/RL_with_RAY","kind":"listed","samples":4,"ran":4,"instrument":1,"unverified":0},{"repo":"toshikwa/discor.pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2003.07305"],"harvested_for_calls":[{"arxiv_id":"2003.07305","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2003.07305"},"call":"get_harvested_code_for_paper(arxiv_id=\"2003.07305\")"}]},{"repo":"toshikwa/soft-actor-critic.pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2605.21282"],"harvested_for_calls":[{"arxiv_id":"2605.21282","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2605.21282"},"call":"get_harvested_code_for_paper(arxiv_id=\"2605.21282\")"}]},{"repo":"trackmania-rl/tmrl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"watchernyu/spinningup-drl-prototyping","kind":"listed","samples":6,"ran":2,"instrument":0,"unverified":4},{"repo":"yhisaki/average-reward-drl","kind":"listed","samples":13,"ran":10,"instrument":3,"unverified":3},{"repo":"yimingpeng/sac-master","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yining043/SAC-discrete","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"BY571/Soft-Actor-Critic-and-Extensions","kind":"listed","samples":10,"ran":9,"instrument":1,"unverified":1},{"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":"Ipsedo/EvoMotion","kind":"listed","samples":0,"ran":0,"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":"opendilab/DI-engine","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1707.01495","1901.02860","2106.01345","2304.12824"],"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\")"},{"arxiv_id":"1901.02860","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1901.02860"},"call":"get_harvested_code_for_paper(arxiv_id=\"1901.02860\")"},{"arxiv_id":"2106.01345","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.01345"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.01345\")"},{"arxiv_id":"2304.12824","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2304.12824"},"call":"get_harvested_code_for_paper(arxiv_id=\"2304.12824\")"}]},{"repo":"pytorch/rl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2106.01345"],"harvested_for_calls":[{"arxiv_id":"2106.01345","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.01345"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.01345\")"}]},{"repo":"ray-project/ray","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"seungju-k1m/sac-td3-td7","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tensorlayer/RLzoo","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":6,"harvested_for":["1502.05477","1509.02971","1509.06461","1511.05952","1602.01783","1707.06347"],"harvested_for_calls":[{"arxiv_id":"1502.05477","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1502.05477"},"call":"get_harvested_code_for_paper(arxiv_id=\"1502.05477\")"},{"arxiv_id":"1509.02971","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1509.02971"},"call":"get_harvested_code_for_paper(arxiv_id=\"1509.02971\")"},{"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\")"},{"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":"toni-sm/skrl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"xiuyu0000/new_papers_codes","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":"03c32bed08513135","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The code implements the Soft Actor-Critic (SAC) algorithm with a manually tuned temperature parameter as proposed in the paper.","centrality":"contribution","entry":"Agent_ManualTemperature","entry_sha256":"0918147b61a18074","n_bricks":7,"bricks":[{"entry":"Agent_ManualTemperature","code_sha256":"0918147b61a18074","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Agent","code_sha256":"b0e759b2d521e146","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"7c4433b21cf61a2c","role":"model","order":2,"level":1,"status":"ran"},{"entry":"Value","code_sha256":"f8845c35735f20bc","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"de5e64dc2bfc6a33","role":"model","order":4,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"ac5ecca5b7705f8a","role":"sampler","order":5,"level":1,"status":"ran"},{"entry":"Network","code_sha256":"de764e9177884a12","role":"helper","order":6,"level":1,"status":"ran"}],"ran_individually":6,"ran_individually_constructed":6,"ran_individually_by_status":{"ran":6},"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"0c993485e821c715","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The paper claims this code implements the Soft Actor-Critic (SAC) algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"soft_actor_critic_agent","entry_sha256":"3a0835e6ce008741","n_bricks":6,"bricks":[{"entry":"soft_actor_critic_agent","code_sha256":"3a0835e6ce008741","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"GaussianPolicy","code_sha256":"bf0d89394b22e1b6","role":"model","order":1,"level":1,"status":"ran"},{"entry":"QNetwork","code_sha256":"f37748964b0cd7da","role":"model","order":2,"level":1,"status":"ran"},{"entry":"hard_update","code_sha256":"799c08d64f58d9ef","role":"update_rule","order":3,"level":0,"status":"unverified"},{"entry":"soft_update","code_sha256":"f735812881238a1f","role":"update_rule","order":4,"level":0,"status":"unverified"},{"entry":"weights_init_","code_sha256":"0537c4bc8300d410","role":"helper","order":5,"level":0,"status":"unverified"}],"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"177af73651d6fe84","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The code implements the Soft Actor-Critic (SAC) algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"SAC","entry_sha256":"569d921eb9b51536","n_bricks":10,"bricks":[{"entry":"SAC","code_sha256":"569d921eb9b51536","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ReplayBuffer","code_sha256":"8119b0afbe2d940e","role":"sampler","order":1,"level":1,"status":"ran"},{"entry":"bytes_to_params","code_sha256":"fa8517ef05057c7f","role":"helper","order":2,"level":1,"status":"ran_draft_wrong"},{"entry":"data_to_json","code_sha256":"36b66092679a3132","role":"helper","order":3,"level":1,"status":"ran_draft_wrong"},{"entry":"json_to_data","code_sha256":"ad86f46cc9af956b","role":"helper","order":4,"level":1,"status":"ran_draft_wrong"},{"entry":"params_to_bytes","code_sha256":"1d75daad61f15424","role":"helper","order":5,"level":1,"status":"ran_draft_wrong"},{"entry":"scale_action","code_sha256":"4a486e5048778576","role":"helper","order":6,"level":1,"status":"ran_draft_wrong"},{"entry":"set_global_seeds","code_sha256":"0dfad75cd2d202d6","role":"helper","order":7,"level":0,"status":"unverified"},{"entry":"unscale_action","code_sha256":"5a4d3fd6b28ecaf4","role":"helper","order":8,"level":1,"status":"ran_draft_wrong"},{"entry":"is_json_serializable","code_sha256":"c70b5621a0ca8047","role":"helper","order":9,"level":1,"status":"ran_violates"}],"ran_individually":8,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1,"ran_draft_wrong":6,"ran_violates":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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"24fd2c1b4dec60b7","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"This code implements the Soft Actor-Critic (SAC) algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"SAC","entry_sha256":"0edd4b0f90be8f84","n_bricks":7,"bricks":[{"entry":"SAC","code_sha256":"0edd4b0f90be8f84","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"f8ead4c2c205ecd8","role":"model","order":1,"level":1,"status":"ran"},{"entry":"DeterministicPolicy","code_sha256":"7553f61c31debefb","role":"model","order":2,"level":1,"status":"ran"},{"entry":"GaussianPolicy","code_sha256":"152bc1e449547d23","role":"model","order":3,"level":1,"status":"ran"},{"entry":"hard_update","code_sha256":"799c08d64f58d9ef","role":"update_rule","order":4,"level":0,"status":"unverified"},{"entry":"soft_update","code_sha256":"f735812881238a1f","role":"update_rule","order":5,"level":0,"status":"unverified"},{"entry":"weights_init_","code_sha256":"0537c4bc8300d410","role":"helper","order":6,"level":0,"status":"unverified"}],"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"2f2011b782dd98ad","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The code implements the Soft Actor-Critic (SAC) algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"Agent","entry_sha256":"2ae117303c9ac594","n_bricks":11,"bricks":[{"entry":"Agent","code_sha256":"2ae117303c9ac594","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"5d8f81c210a0aacb","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"8f0377d2cad944f3","role":"model","order":2,"level":1,"status":"ran"},{"entry":"DeepActor","code_sha256":"9ee95d5b4fc2dd44","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"DeepCritic","code_sha256":"a57bb45ab6a0bc51","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"DeepIQN","code_sha256":"693c33a1aa6474c6","role":"helper","order":5,"level":1,"status":"ran"},{"entry":"IQN","code_sha256":"94a135edcb95baf2","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"PrioritizedReplay","code_sha256":"91bcdaabd64f8eee","role":"helper","order":7,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"a6c39d1200737d3f","role":"helper","order":8,"level":1,"status":"ran"},{"entry":"calculate_huber_loss","code_sha256":"d9d455622c2dcd61","role":"loss","order":9,"level":1,"status":"ran_draft_wrong"},{"entry":"hidden_init","code_sha256":"24ee38e114b38bce","role":"helper","order":10,"level":1,"status":"ran_honours"}],"ran_individually":10,"ran_individually_constructed":8,"ran_individually_by_status":{"ran":8,"ran_draft_wrong":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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"3326fb95331cf825","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The code implements the Soft Actor-Critic (SAC) algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"SAC","entry_sha256":"4849ba61ae47dd70","n_bricks":13,"bricks":[{"entry":"SAC","code_sha256":"4849ba61ae47dd70","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"AlgorithmBase","code_sha256":"110041979f3c0cb8","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"Batch","code_sha256":"6bb425a4771dc88f","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"ConcatStateAction","code_sha256":"c10734f04f231cb4","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"Logger","code_sha256":"4aec8353051fa16d","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"MultiLinear","code_sha256":"5d3a98fbf8446e0c","role":"helper","order":5,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"e9664791458e5ade","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"ScalarHolder","code_sha256":"33ec92b652664841","role":"helper","order":7,"level":1,"status":"ran"},{"entry":"SquashedDiagonalGaussianHead","code_sha256":"02a45597a277afab","role":"helper","order":8,"level":1,"status":"ran"},{"entry":"ortho_init","code_sha256":"5c5bce3523ed4d69","role":"helper","order":9,"level":1,"status":"ran_draft_wrong"},{"entry":"polyak_update","code_sha256":"f299a2900b4034fa","role":"helper","order":10,"level":0,"status":"unverified"},{"entry":"convert_to_tensor","code_sha256":"cdf94e91c8746537","role":"helper","order":11,"level":1,"status":"ran_draft_wrong"},{"entry":"group_by_keys","code_sha256":"1dd9b9ae9fa9426f","role":"helper","order":12,"level":1,"status":"ran_draft_wrong"}],"ran_individually":10,"ran_individually_constructed":6,"ran_individually_by_status":{"ran":7,"ran_draft_wrong":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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"38e92271f5c0ea06","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"Implements the Soft Actor-Critic algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"SAC_Trainer","entry_sha256":"3e1e70dd1d5f3958","n_bricks":4,"bricks":[{"entry":"SAC_Trainer","code_sha256":"3e1e70dd1d5f3958","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"PolicyNetwork","code_sha256":"540316788d2c30c7","role":"model","order":1,"level":1,"status":"ran"},{"entry":"SoftQNetwork","code_sha256":"0688d4da92feee38","role":"model","order":2,"level":1,"status":"ran"},{"entry":"ReplayBuffer","code_sha256":"70249df825c62d7e","role":"sampler","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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"3f806562f9045e27","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The code implements the soft actor-critic (SAC) algorithm, which is an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"mlp_actor_critic","entry_sha256":"8498689f07030ac8","n_bricks":6,"bricks":[{"entry":"mlp_actor_critic","code_sha256":"8498689f07030ac8","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"apply_squashing_func","code_sha256":"198be549ce9696ef","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"mlp","code_sha256":"e68b07bcdded00fa","role":"helper","order":2,"level":0,"status":"unverified"},{"entry":"mlp_gaussian_policy","code_sha256":"a860fee8188a0218","role":"model","order":3,"level":0,"status":"unverified"},{"entry":"clip_but_pass_gradient","code_sha256":"4731ca1d377b8284","role":"helper","order":4,"level":1,"status":"ran_honours"},{"entry":"gaussian_likelihood","code_sha256":"5c26c93931dce503","role":"helper","order":5,"level":1,"status":"ran_honours"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"42669f5563aa73fe","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The paper claims an off-policy maximum entropy deep reinforcement learning algorithm with a stochastic actor, specifically the Soft Actor-Critic (SAC) method.","centrality":"contribution","entry":"SACActor","entry_sha256":"e5d43066162708ff","n_bricks":2,"bricks":[{"entry":"SACActor","code_sha256":"e5d43066162708ff","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"RLNetwork","code_sha256":"b36d35fd411b0150","role":"helper","order":1,"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"4a777313f95db1d1","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"This code implements the Soft Actor-Critic (SAC) algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"MLPActorCritic","entry_sha256":"a830c8ece63f9c57","n_bricks":4,"bricks":[{"entry":"MLPActorCritic","code_sha256":"a830c8ece63f9c57","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"MLPGaussianPolicy","code_sha256":"c02fc6e11c3ba5cf","role":"model","order":1,"level":1,"status":"ran"},{"entry":"MLPQFunction","code_sha256":"14211bf5685457cf","role":"model","order":2,"level":1,"status":"ran"},{"entry":"mlp","code_sha256":"a1e9dc4773ffeba5","role":"helper","order":3,"level":1,"status":"ran_draft_wrong"}],"ran_individually":4,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3,"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"502f495892de7c59","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The code implements a stochastic actor for off-policy maximum entropy deep reinforcement learning, which models a Gaussian policy with learnable mean and log standard deviation parameters.","centrality":"contribution","entry":"SoftActor","entry_sha256":"b473c449b3da39cc","n_bricks":2,"bricks":[{"entry":"SoftActor","code_sha256":"b473c449b3da39cc","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"_create_fcnn","code_sha256":"b7fc01f37cbb0eb1","role":"model","order":1,"level":1,"status":"ran_draft_wrong"}],"ran_individually":2,"ran_individually_constructed":1,"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"55a8bb1f4bce436c","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The paper claims this code implements the Soft Actor-Critic algorithm for off-policy maximum entropy deep reinforcement learning with a stochastic actor.","centrality":"contribution","entry":"SAC","entry_sha256":"348b1924f106de50","n_bricks":13,"bricks":[{"entry":"SAC","code_sha256":"348b1924f106de50","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Algorithm","code_sha256":"eaf547baf5f33e43","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"GaussianPolicy","code_sha256":"8761dc745b44dc04","role":"model","order":2,"level":1,"status":"ran"},{"entry":"TwinnedStateActionFunction","code_sha256":"5d13132d2e3c5ef0","role":"model","order":3,"level":1,"status":"ran"},{"entry":"assert_action","code_sha256":"ded76544fe9d6607","role":"helper","order":4,"level":0,"status":"unverified"},{"entry":"disable_gradients","code_sha256":"56dd8863f4522252","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"soft_update","code_sha256":"e8abbe917721f0c8","role":"helper","order":6,"level":0,"status":"unverified"},{"entry":"update_params","code_sha256":"33523284389291bf","role":"helper","order":7,"level":0,"status":"unverified"},{"entry":"BaseNetwork","code_sha256":"d6d4b5a5d84ba8ad","role":"helper","order":8,"level":0,"status":"unverified"},{"entry":"create_linear_network","code_sha256":"248f63c9cf4d972e","role":"helper","order":9,"level":1,"status":"ran_fixture"},{"entry":"StateActionFunction","code_sha256":"b1e066bc1ff4b61b","role":"model","order":10,"level":1,"status":"ran"},{"entry":"_soft_update","code_sha256":"231f633be51bd617","role":"helper","order":11,"level":0,"status":"unverified"},{"entry":"initialize_weights_xavier","code_sha256":"544fe1f08a36cc62","role":"helper","order":12,"level":0,"status":"unverified"}],"ran_individually":4,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3,"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"6d1ab8e8bdfceece","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The paper claims this code implements the Soft Actor-Critic algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"SAC","entry_sha256":"217cd7f6f86864da","n_bricks":3,"bricks":[{"entry":"SAC","code_sha256":"217cd7f6f86864da","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"hard_update","code_sha256":"7abe222eb3afeb6f","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"soft_update","code_sha256":"fcdeb82694a504e1","role":"helper","order":2,"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"71e70b31947abb15","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"This code implements the Soft Actor-Critic (SAC) algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"SAC","entry_sha256":"9e2e2c85eabbd88f","n_bricks":8,"bricks":[{"entry":"SAC","code_sha256":"9e2e2c85eabbd88f","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"AbstractAgent","code_sha256":"424bf06f8d8eb998","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"DeterministicPolicy","code_sha256":"3faeea6e22edd34d","role":"model","order":2,"level":1,"status":"ran"},{"entry":"GaussianPolicy","code_sha256":"8ee15fddb3528e86","role":"model","order":3,"level":1,"status":"ran"},{"entry":"QNetwork","code_sha256":"ff10fc4473be092a","role":"model","order":4,"level":1,"status":"ran"},{"entry":"hard_update","code_sha256":"799c08d64f58d9ef","role":"update_rule","order":5,"level":0,"status":"unverified"},{"entry":"soft_update","code_sha256":"f735812881238a1f","role":"update_rule","order":6,"level":0,"status":"unverified"},{"entry":"weights_init_","code_sha256":"0537c4bc8300d410","role":"helper","order":7,"level":0,"status":"unverified"}],"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"7afa0732a741d65f","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The paper claims this code implements the Soft Actor-Critic (SAC) algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"Agent","entry_sha256":"05437b66f08eb4d6","n_bricks":12,"bricks":[{"entry":"Agent","code_sha256":"05437b66f08eb4d6","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ReplayBuffer","code_sha256":"0020d85f4dbfb10b","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"StochasticPolicy","code_sha256":"7e61ac4f70c90628","role":"model","order":2,"level":1,"status":"ran"},{"entry":"TwinnedQNetworks","code_sha256":"5b2e9a4c85bbab7d","role":"model","order":3,"level":1,"status":"ran"},{"entry":"eval_mode","code_sha256":"298e84cf1d9ed36c","role":"helper","order":4,"level":1,"status":"ran_draft_wrong"},{"entry":"get_device","code_sha256":"d4978950888874f4","role":"helper","order":5,"level":1,"status":"ran_draft_wrong"},{"entry":"load_model","code_sha256":"706459e26fbb0b4c","role":"helper","order":6,"level":0,"status":"unverified"},{"entry":"save_model","code_sha256":"7d297778525c40d1","role":"helper","order":7,"level":0,"status":"unverified"},{"entry":"update_network_parameters","code_sha256":"85fff8ae028fc1dd","role":"update_rule","order":8,"level":0,"status":"unverified"},{"entry":"get_multilayer_perceptron","code_sha256":"1afbe631504fbaf7","role":"helper","order":9,"level":1,"status":"ran_draft_wrong"},{"entry":"weight_initialization","code_sha256":"6ae1b395aeb4e7d3","role":"helper","order":10,"level":0,"status":"unverified"},{"entry":"QNetwork","code_sha256":"b7030d8d56cd639a","role":"helper","order":11,"level":1,"status":"ran"}],"ran_individually":7,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4,"ran_draft_wrong":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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"8aeea19ed7035e4d","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The code implements the Soft Actor-Critic algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"SAC","entry_sha256":"43d63d9b3b6240a1","n_bricks":6,"bricks":[{"entry":"SAC","code_sha256":"43d63d9b3b6240a1","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"dc01224a73ea8148","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"a0a4c6c892e497cd","role":"model","order":2,"level":1,"status":"ran"},{"entry":"apply_squashing_func","code_sha256":"52028903a218ba91","role":"helper","order":3,"level":1,"status":"ran_draft_wrong"},{"entry":"gaussian_likelihood","code_sha256":"958cab9f3ba6af81","role":"helper","order":4,"level":1,"status":"ran_draft_wrong"},{"entry":"weight_init","code_sha256":"68c08ef9d5d473a7","role":"helper","order":5,"level":0,"status":"unverified"}],"ran_individually":5,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3,"ran_draft_wrong":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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"8ef2b775d0263949","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The code implements the Soft Actor-Critic (SAC) algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"SACLearner","entry_sha256":"6bc96035de025e83","n_bricks":4,"bricks":[{"entry":"SACLearner","code_sha256":"6bc96035de025e83","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Model","code_sha256":"3ef56075bad93ec9","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"_update_jit","code_sha256":"f07528bc5e071757","role":"update_rule","order":2,"level":0,"status":"unverified"},{"entry":"target_update","code_sha256":"f62b5d3c6983e5aa","role":"helper","order":3,"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"8f0e5a2033e2561b","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The code implements the Soft Actor-Critic (SAC) algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"SAC","entry_sha256":"1cb5a8aa4ee6cb43","n_bricks":8,"bricks":[{"entry":"SAC","code_sha256":"1cb5a8aa4ee6cb43","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"BatchQNet","code_sha256":"e6f3bef6186ec524","role":"model","order":1,"level":1,"status":"ran"},{"entry":"DeterministicPolicy","code_sha256":"56013393aeafd8da","role":"model","order":2,"level":1,"status":"ran"},{"entry":"GaussianPolicy","code_sha256":"5722a85a4a153169","role":"model","order":3,"level":1,"status":"ran"},{"entry":"hard_update","code_sha256":"799c08d64f58d9ef","role":"helper","order":4,"level":0,"status":"unverified"},{"entry":"soft_update","code_sha256":"f735812881238a1f","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"BaseQNet","code_sha256":"d6b54769dcaa3ec5","role":"model","order":6,"level":1,"status":"ran"},{"entry":"weights_init_","code_sha256":"0537c4bc8300d410","role":"helper","order":7,"level":0,"status":"unverified"}],"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"9adf4f562cd31d82","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The code implements the Soft Actor-Critic algorithm, a model-free deep reinforcement learning method that maximizes entropy while optimizing policy performance.","centrality":"contribution","entry":"SAC","entry_sha256":"9efbd1e63c6644e5","n_bricks":8,"bricks":[{"entry":"SAC","code_sha256":"9efbd1e63c6644e5","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"DeterministicPolicy","code_sha256":"56013393aeafd8da","role":"model","order":1,"level":1,"status":"ran"},{"entry":"GaussianPolicy","code_sha256":"8ee15fddb3528e86","role":"model","order":2,"level":1,"status":"ran"},{"entry":"QNetwork","code_sha256":"ff10fc4473be092a","role":"model","order":3,"level":1,"status":"ran"},{"entry":"compute_weight_X","code_sha256":"a2697a9ea209c680","role":"helper","order":4,"level":1,"status":"ran_honours"},{"entry":"hard_update","code_sha256":"799c08d64f58d9ef","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"soft_update","code_sha256":"f735812881238a1f","role":"helper","order":6,"level":0,"status":"unverified"},{"entry":"weights_init_","code_sha256":"0537c4bc8300d410","role":"helper","order":7,"level":0,"status":"unverified"}],"ran_individually":4,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3,"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ab52e9144e49f38b","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The paper claims to implement the Soft Actor-Critic algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"SAC","entry_sha256":"6af70c8a2239d7c5","n_bricks":13,"bricks":[{"entry":"SAC","code_sha256":"6af70c8a2239d7c5","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Algorithm","code_sha256":"803d90cd603ff8c0","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"Buffer","code_sha256":"94573a894a42ebff","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"StateDependentPolicy","code_sha256":"f0f9d0b00b3e9632","role":"model","order":3,"level":1,"status":"ran"},{"entry":"TwinnedStateActionFunction","code_sha256":"e42d91ba746c3a14","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"disable_gradient","code_sha256":"ed542fae5c7f2c04","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"soft_update","code_sha256":"8dc0540b8dfe9b97","role":"helper","order":6,"level":0,"status":"unverified"},{"entry":"SerializedBuffer","code_sha256":"c74fba5d30037b69","role":"helper","order":7,"level":1,"status":"ran"},{"entry":"build_mlp","code_sha256":"c511268a73d82fc6","role":"helper","order":8,"level":1,"status":"ran_draft_wrong"},{"entry":"evaluate_lop_pi","code_sha256":"1cfc11023c8784d6","role":"helper","order":9,"level":1,"status":"ran_draft_wrong"},{"entry":"reparameterize","code_sha256":"7c5e74bc668cf5cc","role":"helper","order":10,"level":1,"status":"ran_draft_wrong"},{"entry":"atanh","code_sha256":"264c9e17d7dfe7eb","role":"helper","order":11,"level":1,"status":"ran_honours"},{"entry":"calculate_log_pi","code_sha256":"b4f2ea8b3db73cea","role":"helper","order":12,"level":1,"status":"ran_draft_wrong"}],"ran_individually":9,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4,"ran_draft_wrong":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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"b9bb35d3946b1c03","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The paper proposes the Soft Actor-Critic (SAC) algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"SAC","entry_sha256":"fa07dbb92f6c222b","n_bricks":7,"bricks":[{"entry":"SAC","code_sha256":"fa07dbb92f6c222b","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"DeterministicPolicy","code_sha256":"d4dfbbf39952f704","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"GaussianPolicy","code_sha256":"57c7562fda9bbab3","role":"model","order":2,"level":1,"status":"ran"},{"entry":"QNetwork","code_sha256":"e3aca820c0049604","role":"model","order":3,"level":1,"status":"ran"},{"entry":"hard_update","code_sha256":"1adf91cc413cf6c2","role":"update_rule","order":4,"level":0,"status":"unverified"},{"entry":"soft_update","code_sha256":"ace24484ab1d6b7f","role":"update_rule","order":5,"level":0,"status":"unverified"},{"entry":"weights_init_","code_sha256":"abe2b5a0b5e817fd","role":"helper","order":6,"level":0,"status":"unverified"}],"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"bdd0e01576c7006a","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The code implements a stochastic actor policy with entropy regularization for off-policy maximum entropy deep reinforcement learning, as proposed in the Soft Actor-Critic paper.","centrality":"contribution","entry":"TanhGaussianPolicySACAdapt","entry_sha256":"f552f5cc13186908","n_bricks":3,"bricks":[{"entry":"TanhGaussianPolicySACAdapt","code_sha256":"f552f5cc13186908","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Mlp","code_sha256":"3ec1489c1ccfeec3","role":"model","order":1,"level":1,"status":"ran"},{"entry":"weights_init_","code_sha256":"0537c4bc8300d410","role":"helper","order":2,"level":0,"status":"unverified"}],"ran_individually":2,"ran_individually_constructed":1,"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d403ed8fc6e6a467","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The paper claims this code implements the Soft Actor-Critic algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"SoftActorCritic","entry_sha256":"ecf34b65e8d9d3bb","n_bricks":7,"bricks":[{"entry":"SoftActorCritic","code_sha256":"ecf34b65e8d9d3bb","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"PolicyNetwork","code_sha256":"ec7050db6c32a43a","role":"model","order":1,"level":1,"status":"ran"},{"entry":"QNetwork","code_sha256":"e182a5c8f1d1e16f","role":"model","order":2,"level":1,"status":"ran"},{"entry":"ReplayMemory","code_sha256":"995a5d6382ee476d","role":"sampler","order":3,"level":0,"status":"unverified"},{"entry":"copy_params","code_sha256":"d1076220e33b55ba","role":"helper","order":4,"level":0,"status":"unverified"},{"entry":"soft_update","code_sha256":"54ab8d446018b958","role":"update_rule","order":5,"level":0,"status":"unverified"},{"entry":"init_weights","code_sha256":"8576d4b41e6ed12f","role":"helper","order":6,"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d8d052895ed6eaaa","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The paper claims this code implements the Soft Actor-Critic (SAC) algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"SAC","entry_sha256":"104ef2d3e37baa21","n_bricks":11,"bricks":[{"entry":"SAC","code_sha256":"104ef2d3e37baa21","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Algorithm","code_sha256":"ff7a80131e64a08d","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"Buffer","code_sha256":"b6b1a23b07a627dd","role":"helper","order":2,"level":0,"status":"unverified"},{"entry":"StateDependentPolicy","code_sha256":"77baa7a1a168fc24","role":"model","order":3,"level":1,"status":"ran"},{"entry":"TwinnedStateActionFunction","code_sha256":"e42d91ba746c3a14","role":"model","order":4,"level":1,"status":"ran"},{"entry":"disable_gradient","code_sha256":"ed542fae5c7f2c04","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"soft_update","code_sha256":"8dc0540b8dfe9b97","role":"helper","order":6,"level":0,"status":"unverified"},{"entry":"SerializedBuffer","code_sha256":"eb9bc09b3ca641cb","role":"helper","order":7,"level":1,"status":"ran"},{"entry":"build_mlp","code_sha256":"c511268a73d82fc6","role":"helper","order":8,"level":1,"status":"ran_draft_wrong"},{"entry":"reparameterize","code_sha256":"7c5e74bc668cf5cc","role":"helper","order":9,"level":1,"status":"ran_draft_wrong"},{"entry":"calculate_log_pi","code_sha256":"b4f2ea8b3db73cea","role":"helper","order":10,"level":1,"status":"ran_draft_wrong"}],"ran_individually":6,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":3,"ran_draft_wrong":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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ea1ea881ec00edf6","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The code implements the Soft Actor-Critic algorithm, an off-policy maximum entropy deep reinforcement learning method with a stochastic actor.","centrality":"contribution","entry":"SAC","entry_sha256":"d77f61cb28da8383","n_bricks":7,"bricks":[{"entry":"SAC","code_sha256":"d77f61cb28da8383","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"DeterministicPolicy","code_sha256":"56013393aeafd8da","role":"model","order":1,"level":1,"status":"ran"},{"entry":"GaussianPolicy","code_sha256":"8ee15fddb3528e86","role":"model","order":2,"level":1,"status":"ran"},{"entry":"QNetwork","code_sha256":"ff10fc4473be092a","role":"model","order":3,"level":1,"status":"ran"},{"entry":"hard_update","code_sha256":"799c08d64f58d9ef","role":"helper","order":4,"level":0,"status":"unverified"},{"entry":"soft_update","code_sha256":"f735812881238a1f","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"weights_init_","code_sha256":"0537c4bc8300d410","role":"helper","order":6,"level":0,"status":"unverified"}],"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":"612af00c2047","n_siblings":26,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"f9d74563daee1fbd","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The paper proposes a soft actor-critic method for off-policy maximum entropy deep reinforcement learning with a stochastic actor.","centrality":"component","entry":"ReplayBuffer","entry_sha256":"31b7a842f737b97e","n_bricks":1,"bricks":[{"entry":"ReplayBuffer","code_sha256":"31b7a842f737b97e","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":"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":"612af00c2047","n_siblings":26,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"fe2e45dc0661c714","source_kind":"harvested","method_name":"soft actor-critic","realizes_method":"soft actor-critic","graph_method":"soft actor-critic","realizes_severed":false,"claim":"The paper proposes a stochastic actor (policy) for off-policy maximum entropy deep reinforcement learning, which is implemented as a neural network that determines actions for given states.","centrality":"contribution","entry":"policyNet","entry_sha256":"642892e9419a125d","n_bricks":1,"bricks":[{"entry":"policyNet","code_sha256":"642892e9419a125d","role":"entry","order":0,"level":1,"status":"ran"}],"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":"612af00c2047","n_siblings":26,"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":"612af00c2047","realizes_method":"soft actor-critic","source_kind":"harvested","batch_at":"2026-09-09T22:44:46+00:00","members":["03c32bed08513135","0c993485e821c715","177af73651d6fe84","24fd2c1b4dec60b7","2f2011b782dd98ad","3326fb95331cf825","38e92271f5c0ea06","3f806562f9045e27","42669f5563aa73fe","4a777313f95db1d1","502f495892de7c59","55a8bb1f4bce436c","6d1ab8e8bdfceece","71e70b31947abb15","7afa0732a741d65f","8aeea19ed7035e4d","8ef2b775d0263949","8f0e5a2033e2561b","9adf4f562cd31d82","ab52e9144e49f38b","b9bb35d3946b1c03","bdd0e01576c7006a","d403ed8fc6e6a467","d8d052895ed6eaaa","ea1ea881ec00edf6","f9d74563daee1fbd","fe2e45dc0661c714"]}],"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":"1801.01290"},"call":"assembly(arxiv_id=\"1801.01290\")"},"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/1801.01290.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/1801.01290.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/haarnoja/sac","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ku2482/soft-actor-critic.pytorch","reach":{"status":"ok","spdx":"MIT"}},{"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/baturaysaglam/la3p","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/quantumiracle/Popular-RL-Algorithms","reach":null},{"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/ShawK91/erl_paper_nips18","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kairproject/kair_algorithms_draft","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ku2482/rljax","reach":{"status":"ok","spdx":"MIT"}},{"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/toni-sm/skrl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Kaixhin/imitation-learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dasgringuen/assetto_corsa_gym","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/watchernyu/spinningup-drl-prototyping","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kushagra06/SAC","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/timoklein/car_racer","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MrSyee/pg-is-all-you-need","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/polixir/NeoRL","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/core-robotics-lab/icct","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tmjeong1103/RL_with_RAY","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/flowersteam/rl_stats","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thomashirtz/pytorch-soft-actor-critic","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning","reach":null}],"summary":{"ran":69,"ran_draft_wrong":17,"ran_honours":3,"ran_fixture":1,"ran_violates":1,"unverified":57},"n_samples":148,"n_ran":91,"n_constructed":61,"n_ran_checked":73,"n_instrument":18,"n_unverified":57,"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":148,"ran":91,"n_ran_checked":73,"n_instrument":18,"repositories":27}},"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"},"official_not_harvested":{"repositories":["haarnoja/sac"],"harvested_for_other_papers":[0],"samples_from_other_repositories":148,"other_repositories":27,"samples_unlocated":0},"n_pointer_only_for_licence":66,"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":91,"n_ran_without_level_date":0,"n_ran_signature_not_shown":20,"levels_written_between":{"first":"2026-09-22","last":"2026-09-24","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","samples":[{"code_sha256":"424bf06f8d8eb998","code_sha256_prefix":"424bf06f8d8eb998","entry":"AbstractAgent","repo":"h-aboutalebi/SparceReward","repo_kind":"listed","path":"engine/algorithms/SAC/sac.py","file_url":"https://github.com/h-aboutalebi/SparceReward/blob/HEAD/engine/algorithms/SAC/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":"AbstractAgent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/abstractagent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, h-aboutalebi/SparceReward when it was checked","mcp_get_code":{"code_sha256":"424bf06f8d8eb998"}},{"code_sha256":"de5e64dc2bfc6a33","code_sha256_prefix":"de5e64dc2bfc6a33","entry":"Actor","repo":"MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning","repo_kind":"listed","path":"src/agents.py","file_url":"https://github.com/MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning/blob/HEAD/src/agents.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":"de5e64dc2bfc6a33"},"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":"de5e64dc2bfc6a33"}},{"code_sha256":"5d8f81c210a0aacb","code_sha256_prefix":"5d8f81c210a0aacb","entry":"Actor","repo":"BY571/Soft-Actor-Critic-and-Extensions","repo_kind":"listed","path":"files/Agent.py","file_url":"https://github.com/BY571/Soft-Actor-Critic-and-Extensions/blob/HEAD/files/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":"5d8f81c210a0aacb"},"code_page":"/code/actor","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5d8f81c210a0aacb"}},{"code_sha256":"dc01224a73ea8148","code_sha256_prefix":"dc01224a73ea8148","entry":"Actor","repo":"SaminYeasar/off_policy_ac","repo_kind":"listed","path":"SAC/SAC.py","file_url":"https://github.com/SaminYeasar/off_policy_ac/blob/HEAD/SAC/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":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"dc01224a73ea8148"},"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":"dc01224a73ea8148"}},{"code_sha256":"0918147b61a18074","code_sha256_prefix":"0918147b61a18074","entry":"Agent_ManualTemperature","repo":"MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning","repo_kind":"listed","path":"src/agents.py","file_url":"https://github.com/MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning/blob/HEAD/src/agents.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_ManualTemperature","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":"0918147b61a18074"}},{"code_sha256":"d6b54769dcaa3ec5","code_sha256_prefix":"d6b54769dcaa3ec5","entry":"BaseQNet","repo":"sunfex/weighted-sac","repo_kind":"listed","path":"sac.py","file_url":"https://github.com/sunfex/weighted-sac/blob/HEAD/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":"BaseQNet","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":"d6b54769dcaa3ec5"}},{"code_sha256":"6bb425a4771dc88f","code_sha256_prefix":"6bb425a4771dc88f","entry":"Batch","repo":"yhisaki/average-reward-drl","repo_kind":"listed","path":"average_reward_drl/algorithms/sac.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/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":"Batch","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/batch-2","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, yhisaki/average-reward-drl when it was checked","mcp_get_code":{"code_sha256":"6bb425a4771dc88f"}},{"code_sha256":"e6f3bef6186ec524","code_sha256_prefix":"e6f3bef6186ec524","entry":"BatchQNet","repo":"sunfex/weighted-sac","repo_kind":"listed","path":"sac.py","file_url":"https://github.com/sunfex/weighted-sac/blob/HEAD/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":"BatchQNet","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":"e6f3bef6186ec524"}},{"code_sha256":"94573a894a42ebff","code_sha256_prefix":"94573a894a42ebff","entry":"Buffer","repo":"garyzyr001/rethinking-airl","repo_kind":"listed","path":"airl/algo/sac.py","file_url":"https://github.com/garyzyr001/rethinking-airl/blob/HEAD/airl/algo/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":"Buffer","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/buffer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, garyzyr001/rethinking-airl when it was checked","mcp_get_code":{"code_sha256":"94573a894a42ebff"}},{"code_sha256":"c10734f04f231cb4","code_sha256_prefix":"c10734f04f231cb4","entry":"ConcatStateAction","repo":"yhisaki/average-reward-drl","repo_kind":"listed","path":"average_reward_drl/algorithms/sac.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"state_action:tuple/1/Tensor","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, yhisaki/average-reward-drl when it was checked","mcp_get_code":{"code_sha256":"c10734f04f231cb4"}},{"code_sha256":"7c4433b21cf61a2c","code_sha256_prefix":"7c4433b21cf61a2c","entry":"Critic","repo":"MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning","repo_kind":"listed","path":"src/agents.py","file_url":"https://github.com/MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning/blob/HEAD/src/agents.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":"7c4433b21cf61a2c"}},{"code_sha256":"f8ead4c2c205ecd8","code_sha256_prefix":"f8ead4c2c205ecd8","entry":"Critic","repo":"baturaysaglam/la3p","repo_kind":"listed","path":"Code/SAC/SAC.py","file_url":"https://github.com/baturaysaglam/la3p/blob/HEAD/Code/SAC/SAC.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":"f8ead4c2c205ecd8"}},{"code_sha256":"8f0377d2cad944f3","code_sha256_prefix":"8f0377d2cad944f3","entry":"Critic","repo":"BY571/Soft-Actor-Critic-and-Extensions","repo_kind":"listed","path":"files/Agent.py","file_url":"https://github.com/BY571/Soft-Actor-Critic-and-Extensions/blob/HEAD/files/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":"8f0377d2cad944f3"}},{"code_sha256":"a0a4c6c892e497cd","code_sha256_prefix":"a0a4c6c892e497cd","entry":"Critic","repo":"SaminYeasar/off_policy_ac","repo_kind":"listed","path":"SAC/SAC.py","file_url":"https://github.com/SaminYeasar/off_policy_ac/blob/HEAD/SAC/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":"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, SaminYeasar/off_policy_ac when it was checked","mcp_get_code":{"code_sha256":"a0a4c6c892e497cd"}},{"code_sha256":"9ee95d5b4fc2dd44","code_sha256_prefix":"9ee95d5b4fc2dd44","entry":"DeepActor","repo":"BY571/Soft-Actor-Critic-and-Extensions","repo_kind":"listed","path":"files/Agent.py","file_url":"https://github.com/BY571/Soft-Actor-Critic-and-Extensions/blob/HEAD/files/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":"DeepActor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"9ee95d5b4fc2dd44"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9ee95d5b4fc2dd44"}},{"code_sha256":"a57bb45ab6a0bc51","code_sha256_prefix":"a57bb45ab6a0bc51","entry":"DeepCritic","repo":"BY571/Soft-Actor-Critic-and-Extensions","repo_kind":"listed","path":"files/Agent.py","file_url":"https://github.com/BY571/Soft-Actor-Critic-and-Extensions/blob/HEAD/files/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":"DeepCritic","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":"a57bb45ab6a0bc51"}},{"code_sha256":"693c33a1aa6474c6","code_sha256_prefix":"693c33a1aa6474c6","entry":"DeepIQN","repo":"BY571/Soft-Actor-Critic-and-Extensions","repo_kind":"listed","path":"files/Agent.py","file_url":"https://github.com/BY571/Soft-Actor-Critic-and-Extensions/blob/HEAD/files/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":"DeepIQN","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":"693c33a1aa6474c6"}},{"code_sha256":"7553f61c31debefb","code_sha256_prefix":"7553f61c31debefb","entry":"DeterministicPolicy","repo":"baturaysaglam/la3p","repo_kind":"listed","path":"Code/SAC/SAC.py","file_url":"https://github.com/baturaysaglam/la3p/blob/HEAD/Code/SAC/SAC.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":"DeterministicPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"7553f61c31debefb"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7553f61c31debefb"}},{"code_sha256":"3faeea6e22edd34d","code_sha256_prefix":"3faeea6e22edd34d","entry":"DeterministicPolicy","repo":"h-aboutalebi/SparceReward","repo_kind":"listed","path":"engine/algorithms/SAC/sac.py","file_url":"https://github.com/h-aboutalebi/SparceReward/blob/HEAD/engine/algorithms/SAC/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":"DeterministicPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"3faeea6e22edd34d"},"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, h-aboutalebi/SparceReward when it was checked","mcp_get_code":{"code_sha256":"3faeea6e22edd34d"}},{"code_sha256":"d4dfbbf39952f704","code_sha256_prefix":"d4dfbbf39952f704","entry":"DeterministicPolicy","repo":"MarsEleven/car_racer_RL","repo_kind":"listed","path":"sac/sac.py","file_url":"https://github.com/MarsEleven/car_racer_RL/blob/HEAD/sac/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":"DeterministicPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"d4dfbbf39952f704"},"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, MarsEleven/car_racer_RL when it was checked","mcp_get_code":{"code_sha256":"d4dfbbf39952f704"}},{"code_sha256":"bf0d89394b22e1b6","code_sha256_prefix":"bf0d89394b22e1b6","entry":"GaussianPolicy","repo":"Rafael1s/Deep-Reinforcement-Learning-Udacity","repo_kind":"listed","path":"Ant-PyBulletEnv-Soft-Actor-Critic/sac_agent.py","file_url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity/blob/HEAD/Ant-PyBulletEnv-Soft-Actor-Critic/sac_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":"GaussianPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"bf0d89394b22e1b6"},"code_page":"/code/gaussianpolicy","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Rafael1s/Deep-Reinforcement-Learning-Udacity when it was checked","mcp_get_code":{"code_sha256":"bf0d89394b22e1b6"}},{"code_sha256":"152bc1e449547d23","code_sha256_prefix":"152bc1e449547d23","entry":"GaussianPolicy","repo":"baturaysaglam/la3p","repo_kind":"listed","path":"Code/SAC/SAC.py","file_url":"https://github.com/baturaysaglam/la3p/blob/HEAD/Code/SAC/SAC.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":"GaussianPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"152bc1e449547d23"},"code_page":"/code/gaussianpolicy","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"152bc1e449547d23"}},{"code_sha256":"8761dc745b44dc04","code_sha256_prefix":"8761dc745b44dc04","entry":"GaussianPolicy","repo":"ku2482/discor.pytorch","repo_kind":"listed","path":"discor/algorithm/sac.py","file_url":"https://github.com/ku2482/discor.pytorch/blob/HEAD/discor/algorithm/sac.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":"GaussianPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"8761dc745b44dc04"},"code_page":"/code/gaussianpolicy","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8761dc745b44dc04"}},{"code_sha256":"8ee15fddb3528e86","code_sha256_prefix":"8ee15fddb3528e86","entry":"GaussianPolicy","repo":"h-aboutalebi/SparceReward","repo_kind":"listed","path":"engine/algorithms/SAC/sac.py","file_url":"https://github.com/h-aboutalebi/SparceReward/blob/HEAD/engine/algorithms/SAC/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":"GaussianPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"8ee15fddb3528e86"},"code_page":"/code/gaussianpolicy","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, h-aboutalebi/SparceReward when it was checked","mcp_get_code":{"code_sha256":"8ee15fddb3528e86"}},{"code_sha256":"da8ebd6e9ea11fca","code_sha256_prefix":"da8ebd6e9ea11fca","entry":"GaussianPolicy","repo":"roythuly/obac","repo_kind":"listed","path":"model/algo.py","file_url":"https://github.com/roythuly/obac/blob/HEAD/model/algo.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":"GaussianPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"da8ebd6e9ea11fca"},"code_page":"/code/gaussianpolicy","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, roythuly/obac when it was checked","mcp_get_code":{"code_sha256":"da8ebd6e9ea11fca"}},{"code_sha256":"5722a85a4a153169","code_sha256_prefix":"5722a85a4a153169","entry":"GaussianPolicy","repo":"sunfex/weighted-sac","repo_kind":"listed","path":"sac.py","file_url":"https://github.com/sunfex/weighted-sac/blob/HEAD/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":"GaussianPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5722a85a4a153169"},"code_page":"/code/gaussianpolicy","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5722a85a4a153169"}},{"code_sha256":"57c7562fda9bbab3","code_sha256_prefix":"57c7562fda9bbab3","entry":"GaussianPolicy","repo":"MarsEleven/car_racer_RL","repo_kind":"listed","path":"sac/sac.py","file_url":"https://github.com/MarsEleven/car_racer_RL/blob/HEAD/sac/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":"GaussianPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"57c7562fda9bbab3"},"code_page":"/code/gaussianpolicy","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, MarsEleven/car_racer_RL when it was checked","mcp_get_code":{"code_sha256":"57c7562fda9bbab3"}},{"code_sha256":"94a135edcb95baf2","code_sha256_prefix":"94a135edcb95baf2","entry":"IQN","repo":"BY571/Soft-Actor-Critic-and-Extensions","repo_kind":"listed","path":"files/Agent.py","file_url":"https://github.com/BY571/Soft-Actor-Critic-and-Extensions/blob/HEAD/files/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":"IQN","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":"94a135edcb95baf2"}},{"code_sha256":"4aec8353051fa16d","code_sha256_prefix":"4aec8353051fa16d","entry":"Logger","repo":"yhisaki/average-reward-drl","repo_kind":"listed","path":"average_reward_drl/algorithms/sac.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/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":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, yhisaki/average-reward-drl when it was checked","mcp_get_code":{"code_sha256":"4aec8353051fa16d"}},{"code_sha256":"a830c8ece63f9c57","code_sha256_prefix":"a830c8ece63f9c57","entry":"MLPActorCritic","repo":"tmjeong1103/RL_with_RAY","repo_kind":"listed","path":"SAC_RAY/model.py","file_url":"https://github.com/tmjeong1103/RL_with_RAY/blob/HEAD/SAC_RAY/model.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":"MLPActorCritic","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, tmjeong1103/RL_with_RAY when it was checked","mcp_get_code":{"code_sha256":"a830c8ece63f9c57"}},{"code_sha256":"c02fc6e11c3ba5cf","code_sha256_prefix":"c02fc6e11c3ba5cf","entry":"MLPGaussianPolicy","repo":"tmjeong1103/RL_with_RAY","repo_kind":"listed","path":"SAC_RAY/model.py","file_url":"https://github.com/tmjeong1103/RL_with_RAY/blob/HEAD/SAC_RAY/model.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":"MLPGaussianPolicy","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, tmjeong1103/RL_with_RAY when it was checked","mcp_get_code":{"code_sha256":"c02fc6e11c3ba5cf"}},{"code_sha256":"14211bf5685457cf","code_sha256_prefix":"14211bf5685457cf","entry":"MLPQFunction","repo":"tmjeong1103/RL_with_RAY","repo_kind":"listed","path":"SAC_RAY/model.py","file_url":"https://github.com/tmjeong1103/RL_with_RAY/blob/HEAD/SAC_RAY/model.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":"MLPQFunction","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, tmjeong1103/RL_with_RAY when it was checked","mcp_get_code":{"code_sha256":"14211bf5685457cf"}},{"code_sha256":"5d3a98fbf8446e0c","code_sha256_prefix":"5d3a98fbf8446e0c","entry":"MultiLinear","repo":"yhisaki/average-reward-drl","repo_kind":"listed","path":"average_reward_drl/algorithms/sac.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"MultiLinear","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, yhisaki/average-reward-drl when it was checked","mcp_get_code":{"code_sha256":"5d3a98fbf8446e0c"}},{"code_sha256":"de764e9177884a12","code_sha256_prefix":"de764e9177884a12","entry":"Network","repo":"MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning","repo_kind":"listed","path":"src/agents.py","file_url":"https://github.com/MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning/blob/HEAD/src/agents.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":"Network","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/network","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"de764e9177884a12"}},{"code_sha256":"540316788d2c30c7","code_sha256_prefix":"540316788d2c30c7","entry":"PolicyNetwork","repo":"quantumiracle/Popular-RL-Algorithms","repo_kind":"listed","path":"sac_v2.py","file_url":"https://github.com/quantumiracle/Popular-RL-Algorithms/blob/HEAD/sac_v2.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":"PolicyNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"540316788d2c30c7"},"code_page":"/code/policynetwork","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"540316788d2c30c7"}},{"code_sha256":"ec7050db6c32a43a","code_sha256_prefix":"ec7050db6c32a43a","entry":"PolicyNetwork","repo":"ajaysub110/rl-pytorch","repo_kind":"listed","path":"sac/models/soft_actor_critic.py","file_url":"https://github.com/ajaysub110/rl-pytorch/blob/HEAD/sac/models/soft_actor_critic.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"s: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":"ec7050db6c32a43a"},"code_page":"/code/policynetwork","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ajaysub110/rl-pytorch when it was checked","mcp_get_code":{"code_sha256":"ec7050db6c32a43a"}},{"code_sha256":"91bcdaabd64f8eee","code_sha256_prefix":"91bcdaabd64f8eee","entry":"PrioritizedReplay","repo":"BY571/Soft-Actor-Critic-and-Extensions","repo_kind":"listed","path":"files/Agent.py","file_url":"https://github.com/BY571/Soft-Actor-Critic-and-Extensions/blob/HEAD/files/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":"PrioritizedReplay","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":"91bcdaabd64f8eee"}},{"code_sha256":"f37748964b0cd7da","code_sha256_prefix":"f37748964b0cd7da","entry":"QNetwork","repo":"Rafael1s/Deep-Reinforcement-Learning-Udacity","repo_kind":"listed","path":"Ant-PyBulletEnv-Soft-Actor-Critic/sac_agent.py","file_url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity/blob/HEAD/Ant-PyBulletEnv-Soft-Actor-Critic/sac_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":"QNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/qnetwork","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Rafael1s/Deep-Reinforcement-Learning-Udacity when it was checked","mcp_get_code":{"code_sha256":"f37748964b0cd7da"}},{"code_sha256":"b7030d8d56cd639a","code_sha256_prefix":"b7030d8d56cd639a","entry":"QNetwork","repo":"thomashirtz/soft-actor-critic","repo_kind":"listed","path":"soft_actor_critic/agent.py","file_url":"https://github.com/thomashirtz/soft-actor-critic/blob/HEAD/soft_actor_critic/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":"QNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/qnetwork","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b7030d8d56cd639a"}},{"code_sha256":"0d80189fd77d3aa6","code_sha256_prefix":"0d80189fd77d3aa6","entry":"QNetwork","repo":"roythuly/obac","repo_kind":"listed","path":"model/algo.py","file_url":"https://github.com/roythuly/obac/blob/HEAD/model/algo.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":"QNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/qnetwork","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, roythuly/obac when it was checked","mcp_get_code":{"code_sha256":"0d80189fd77d3aa6"}},{"code_sha256":"e3aca820c0049604","code_sha256_prefix":"e3aca820c0049604","entry":"QNetwork","repo":"MarsEleven/car_racer_RL","repo_kind":"listed","path":"sac/sac.py","file_url":"https://github.com/MarsEleven/car_racer_RL/blob/HEAD/sac/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":"QNetwork","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/qnetwork","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, MarsEleven/car_racer_RL when it was checked","mcp_get_code":{"code_sha256":"e3aca820c0049604"}},{"code_sha256":"e182a5c8f1d1e16f","code_sha256_prefix":"e182a5c8f1d1e16f","entry":"QNetwork","repo":"ajaysub110/rl-pytorch","repo_kind":"listed","path":"sac/models/soft_actor_critic.py","file_url":"https://github.com/ajaysub110/rl-pytorch/blob/HEAD/sac/models/soft_actor_critic.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"s:Tensor/2/float, a:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/qnetwork","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ajaysub110/rl-pytorch when it was checked","mcp_get_code":{"code_sha256":"e182a5c8f1d1e16f"}},{"code_sha256":"ac5ecca5b7705f8a","code_sha256_prefix":"ac5ecca5b7705f8a","entry":"ReplayBuffer","repo":"MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning","repo_kind":"listed","path":"src/agents.py","file_url":"https://github.com/MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning/blob/HEAD/src/agents.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":"ac5ecca5b7705f8a"}},{"code_sha256":"8119b0afbe2d940e","code_sha256_prefix":"8119b0afbe2d940e","entry":"ReplayBuffer","repo":"kdally/fault-tolerant-flight-control-drl","repo_kind":"listed","path":"fault_tolerant_flight_control_drl/agent/sac.py","file_url":"https://github.com/kdally/fault-tolerant-flight-control-drl/blob/HEAD/fault_tolerant_flight_control_drl/agent/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":"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":"8119b0afbe2d940e"}},{"code_sha256":"a6c39d1200737d3f","code_sha256_prefix":"a6c39d1200737d3f","entry":"ReplayBuffer","repo":"BY571/Soft-Actor-Critic-and-Extensions","repo_kind":"listed","path":"files/Agent.py","file_url":"https://github.com/BY571/Soft-Actor-Critic-and-Extensions/blob/HEAD/files/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":"a6c39d1200737d3f"}},{"code_sha256":"e9664791458e5ade","code_sha256_prefix":"e9664791458e5ade","entry":"ReplayBuffer","repo":"yhisaki/average-reward-drl","repo_kind":"listed","path":"average_reward_drl/algorithms/sac.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/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":"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, yhisaki/average-reward-drl when it was checked","mcp_get_code":{"code_sha256":"e9664791458e5ade"}},{"code_sha256":"70249df825c62d7e","code_sha256_prefix":"70249df825c62d7e","entry":"ReplayBuffer","repo":"quantumiracle/Popular-RL-Algorithms","repo_kind":"listed","path":"sac_v2.py","file_url":"https://github.com/quantumiracle/Popular-RL-Algorithms/blob/HEAD/sac_v2.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":"70249df825c62d7e"}},{"code_sha256":"0020d85f4dbfb10b","code_sha256_prefix":"0020d85f4dbfb10b","entry":"ReplayBuffer","repo":"thomashirtz/soft-actor-critic","repo_kind":"listed","path":"soft_actor_critic/agent.py","file_url":"https://github.com/thomashirtz/soft-actor-critic/blob/HEAD/soft_actor_critic/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":"0020d85f4dbfb10b"}},{"code_sha256":"217cd7f6f86864da","code_sha256_prefix":"217cd7f6f86864da","entry":"SAC","repo":"ShawK91/Evolutionary-Reinforcement-Learning","repo_kind":"listed","path":"algos/sac.py","file_url":"https://github.com/ShawK91/Evolutionary-Reinforcement-Learning/blob/HEAD/algos/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":"SAC","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/sac","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ShawK91/Evolutionary-Reinforcement-Learning when it was checked","mcp_get_code":{"code_sha256":"217cd7f6f86864da"}},{"code_sha256":"43d63d9b3b6240a1","code_sha256_prefix":"43d63d9b3b6240a1","entry":"SAC","repo":"SaminYeasar/off_policy_ac","repo_kind":"listed","path":"SAC/SAC.py","file_url":"https://github.com/SaminYeasar/off_policy_ac/blob/HEAD/SAC/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":"SAC","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/sac","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":"43d63d9b3b6240a1"}},{"code_sha256":"e5d43066162708ff","code_sha256_prefix":"e5d43066162708ff","entry":"SACActor","repo":"kushagra06/SAC","repo_kind":"listed","path":"model.py","file_url":"https://github.com/kushagra06/SAC/blob/HEAD/model.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":"SACActor","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, kushagra06/SAC when it was checked","mcp_get_code":{"code_sha256":"e5d43066162708ff"}},{"code_sha256":"33ec92b652664841","code_sha256_prefix":"33ec92b652664841","entry":"ScalarHolder","repo":"yhisaki/average-reward-drl","repo_kind":"listed","path":"average_reward_drl/algorithms/sac.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/sac.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":"ScalarHolder","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, yhisaki/average-reward-drl when it was checked","mcp_get_code":{"code_sha256":"33ec92b652664841"}},{"code_sha256":"c74fba5d30037b69","code_sha256_prefix":"c74fba5d30037b69","entry":"SerializedBuffer","repo":"garyzyr001/rethinking-airl","repo_kind":"listed","path":"airl/algo/sac.py","file_url":"https://github.com/garyzyr001/rethinking-airl/blob/HEAD/airl/algo/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":"SerializedBuffer","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, garyzyr001/rethinking-airl when it was checked","mcp_get_code":{"code_sha256":"c74fba5d30037b69"}},{"code_sha256":"eb9bc09b3ca641cb","code_sha256_prefix":"eb9bc09b3ca641cb","entry":"SerializedBuffer","repo":"ku2482/gail-airl-ppo.pytorch","repo_kind":"listed","path":"gail_airl_ppo/algo/sac.py","file_url":"https://github.com/ku2482/gail-airl-ppo.pytorch/blob/HEAD/gail_airl_ppo/algo/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","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":"eb9bc09b3ca641cb"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"eb9bc09b3ca641cb"}},{"code_sha256":"b473c449b3da39cc","code_sha256_prefix":"b473c449b3da39cc","entry":"SoftActor","repo":"Kaixhin/imitation-learning","repo_kind":"listed","path":"models.py","file_url":"https://github.com/Kaixhin/imitation-learning/blob/HEAD/models.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":"SoftActor","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":"b473c449b3da39cc"}},{"code_sha256":"0688d4da92feee38","code_sha256_prefix":"0688d4da92feee38","entry":"SoftQNetwork","repo":"quantumiracle/Popular-RL-Algorithms","repo_kind":"listed","path":"sac_v2.py","file_url":"https://github.com/quantumiracle/Popular-RL-Algorithms/blob/HEAD/sac_v2.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":"SoftQNetwork","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":"0688d4da92feee38"}},{"code_sha256":"02a45597a277afab","code_sha256_prefix":"02a45597a277afab","entry":"SquashedDiagonalGaussianHead","repo":"yhisaki/average-reward-drl","repo_kind":"listed","path":"average_reward_drl/algorithms/sac.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature_not_shown":true,"signature_not_shown_because":"signature_is_harness_probe_not_fixture_args","fixture_out_type":"SquashedDiagonalGaussianHead","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, yhisaki/average-reward-drl when it was checked","mcp_get_code":{"code_sha256":"02a45597a277afab"}},{"code_sha256":"b1e066bc1ff4b61b","code_sha256_prefix":"b1e066bc1ff4b61b","entry":"StateActionFunction","repo":"ku2482/discor.pytorch","repo_kind":"listed","path":"discor/algorithm/sac.py","file_url":"https://github.com/ku2482/discor.pytorch/blob/HEAD/discor/algorithm/sac.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":"StateActionFunction","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":"b1e066bc1ff4b61b"}},{"code_sha256":"f0f9d0b00b3e9632","code_sha256_prefix":"f0f9d0b00b3e9632","entry":"StateDependentPolicy","repo":"garyzyr001/rethinking-airl","repo_kind":"listed","path":"airl/algo/sac.py","file_url":"https://github.com/garyzyr001/rethinking-airl/blob/HEAD/airl/algo/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":"StateDependentPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"f0f9d0b00b3e9632"},"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, garyzyr001/rethinking-airl when it was checked","mcp_get_code":{"code_sha256":"f0f9d0b00b3e9632"}},{"code_sha256":"77baa7a1a168fc24","code_sha256_prefix":"77baa7a1a168fc24","entry":"StateDependentPolicy","repo":"ku2482/gail-airl-ppo.pytorch","repo_kind":"listed","path":"gail_airl_ppo/algo/sac.py","file_url":"https://github.com/ku2482/gail-airl-ppo.pytorch/blob/HEAD/gail_airl_ppo/algo/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"states:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"77baa7a1a168fc24"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"77baa7a1a168fc24"}},{"code_sha256":"7e61ac4f70c90628","code_sha256_prefix":"7e61ac4f70c90628","entry":"StochasticPolicy","repo":"thomashirtz/soft-actor-critic","repo_kind":"listed","path":"soft_actor_critic/agent.py","file_url":"https://github.com/thomashirtz/soft-actor-critic/blob/HEAD/soft_actor_critic/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":"StochasticPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"7e61ac4f70c90628"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7e61ac4f70c90628"}},{"code_sha256":"f552f5cc13186908","code_sha256_prefix":"f552f5cc13186908","entry":"TanhGaussianPolicySACAdapt","repo":"autumnwu/aggressive-q-learning-with-ensembles","repo_kind":"listed","path":"spinup/algos/aqe/core_aqe.py","file_url":"https://github.com/autumnwu/aggressive-q-learning-with-ensembles/blob/HEAD/spinup/algos/aqe/core_aqe.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"obs:Tensor/2/float, deterministic:bool/0/bool, return_log_prob:bool/0/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"f552f5cc13186908"},"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, autumnwu/aggressive-q-learning-with-ensembles when it was checked","mcp_get_code":{"code_sha256":"f552f5cc13186908"}},{"code_sha256":"5b2e9a4c85bbab7d","code_sha256_prefix":"5b2e9a4c85bbab7d","entry":"TwinnedQNetworks","repo":"thomashirtz/soft-actor-critic","repo_kind":"listed","path":"soft_actor_critic/agent.py","file_url":"https://github.com/thomashirtz/soft-actor-critic/blob/HEAD/soft_actor_critic/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":"TwinnedQNetworks","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":"5b2e9a4c85bbab7d"}},{"code_sha256":"5d13132d2e3c5ef0","code_sha256_prefix":"5d13132d2e3c5ef0","entry":"TwinnedStateActionFunction","repo":"ku2482/discor.pytorch","repo_kind":"listed","path":"discor/algorithm/sac.py","file_url":"https://github.com/ku2482/discor.pytorch/blob/HEAD/discor/algorithm/sac.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":"TwinnedStateActionFunction","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":"5d13132d2e3c5ef0"}},{"code_sha256":"e42d91ba746c3a14","code_sha256_prefix":"e42d91ba746c3a14","entry":"TwinnedStateActionFunction","repo":"garyzyr001/rethinking-airl","repo_kind":"listed","path":"airl/algo/sac.py","file_url":"https://github.com/garyzyr001/rethinking-airl/blob/HEAD/airl/algo/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":"TwinnedStateActionFunction","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, garyzyr001/rethinking-airl when it was checked","mcp_get_code":{"code_sha256":"e42d91ba746c3a14"}},{"code_sha256":"f8845c35735f20bc","code_sha256_prefix":"f8845c35735f20bc","entry":"Value","repo":"MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning","repo_kind":"listed","path":"src/agents.py","file_url":"https://github.com/MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning/blob/HEAD/src/agents.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":"Value","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"f8845c35735f20bc"},"code_page":"/code/value","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f8845c35735f20bc"}},{"code_sha256":"18ecb1311366b8cb","code_sha256_prefix":"18ecb1311366b8cb","entry":"ValueNetwork","repo":"roythuly/obac","repo_kind":"listed","path":"model/algo.py","file_url":"https://github.com/roythuly/obac/blob/HEAD/model/algo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"state:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"18ecb1311366b8cb"},"code_page":"/code/valuenetwork","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, roythuly/obac when it was checked","mcp_get_code":{"code_sha256":"18ecb1311366b8cb"}},{"code_sha256":"b7fc01f37cbb0eb1","code_sha256_prefix":"b7fc01f37cbb0eb1","entry":"_create_fcnn","repo":"Kaixhin/imitation-learning","repo_kind":"listed","path":"models.py","file_url":"https://github.com/Kaixhin/imitation-learning/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"input_size:int/0/int, hidden_size:int/0/int, depth:int/0/int, output_size:int/0/int, activation_function:str/0/str, input_dropout:float/0/float, dropout:float/0/float, final_gain:float/0/float, spectral_norm:bool/0/bool","fixture_out_type":"Sequential","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":"b7fc01f37cbb0eb1"}},{"code_sha256":"52028903a218ba91","code_sha256_prefix":"52028903a218ba91","entry":"apply_squashing_func","repo":"SaminYeasar/off_policy_ac","repo_kind":"listed","path":"SAC/SAC.py","file_url":"https://github.com/SaminYeasar/off_policy_ac/blob/HEAD/SAC/SAC.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"mu:Tensor/2/float, pi:Tensor/2/float, log_pi: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":"52028903a218ba91"},"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":"52028903a218ba91"}},{"code_sha256":"fa8517ef05057c7f","code_sha256_prefix":"fa8517ef05057c7f","entry":"bytes_to_params","repo":"kdally/fault-tolerant-flight-control-drl","repo_kind":"listed","path":"fault_tolerant_flight_control_drl/agent/sac.py","file_url":"https://github.com/kdally/fault-tolerant-flight-control-drl/blob/HEAD/fault_tolerant_flight_control_drl/agent/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"serialized_params:bytes/0/?, param_list:list/1/str","fixture_out_type":"OrderedDict","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":"fa8517ef05057c7f"}},{"code_sha256":"d9d455622c2dcd61","code_sha256_prefix":"d9d455622c2dcd61","entry":"calculate_huber_loss","repo":"BY571/Soft-Actor-Critic-and-Extensions","repo_kind":"listed","path":"files/Agent.py","file_url":"https://github.com/BY571/Soft-Actor-Critic-and-Extensions/blob/HEAD/files/Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"td_errors:Tensor/3/float, k:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/calculate-huber-loss","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d9d455622c2dcd61"}},{"code_sha256":"4731ca1d377b8284","code_sha256_prefix":"4731ca1d377b8284","entry":"clip_but_pass_gradient","repo":"watchernyu/spinningup-drl-prototyping","repo_kind":"listed","path":"spinup/algos/sac/core.py","file_url":"https://github.com/watchernyu/spinningup-drl-prototyping/blob/HEAD/spinup/algos/sac/core.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:EagerTensor/2/float, l:float/0/float, u:float/0/float","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"4731ca1d377b8284"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4731ca1d377b8284"}},{"code_sha256":"a2697a9ea209c680","code_sha256_prefix":"a2697a9ea209c680","entry":"compute_weight_X","repo":"hyunin-lee/ForecasterSAC","repo_kind":"listed","path":"sac.py","file_url":"https://github.com/hyunin-lee/ForecasterSAC/blob/HEAD/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"past_length: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":"a2697a9ea209c680"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a2697a9ea209c680"}},{"code_sha256":"cdf94e91c8746537","code_sha256_prefix":"cdf94e91c8746537","entry":"convert_to_tensor","repo":"yhisaki/average-reward-drl","repo_kind":"listed","path":"average_reward_drl/algorithms/sac.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"arr:ndarray/2/float, device:str/0/str, dtype:dtype/0/?","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/convert-to-tensor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, yhisaki/average-reward-drl when it was checked","mcp_get_code":{"code_sha256":"cdf94e91c8746537"}},{"code_sha256":"248f63c9cf4d972e","code_sha256_prefix":"248f63c9cf4d972e","entry":"create_linear_network","repo":"ku2482/discor.pytorch","repo_kind":"listed","path":"discor/algorithm/sac.py","file_url":"https://github.com/ku2482/discor.pytorch/blob/HEAD/discor/algorithm/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"input_dim:int/0/int, output_dim:int/0/int, hidden_units:list/1/int, hidden_activation:callable/0/?, output_activation:callable/0/?, initializer:callable/0/?","fixture_out_type":"Sequential","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":"248f63c9cf4d972e"}},{"code_sha256":"36b66092679a3132","code_sha256_prefix":"36b66092679a3132","entry":"data_to_json","repo":"kdally/fault-tolerant-flight-control-drl","repo_kind":"listed","path":"fault_tolerant_flight_control_drl/agent/sac.py","file_url":"https://github.com/kdally/fault-tolerant-flight-control-drl/blob/HEAD/fault_tolerant_flight_control_drl/agent/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"none","behaviour_fingerprint":false,"signature":"data:dict/0/?","fixture_out_type":"str","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":"36b66092679a3132"}},{"code_sha256":"298e84cf1d9ed36c","code_sha256_prefix":"298e84cf1d9ed36c","entry":"eval_mode","repo":"thomashirtz/soft-actor-critic","repo_kind":"listed","path":"soft_actor_critic/agent.py","file_url":"https://github.com/thomashirtz/soft-actor-critic/blob/HEAD/soft_actor_critic/agent.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":"net:callable/0/?","fixture_out_type":"_GeneratorContextManager","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":"298e84cf1d9ed36c"}},{"code_sha256":"5c26c93931dce503","code_sha256_prefix":"5c26c93931dce503","entry":"gaussian_likelihood","repo":"watchernyu/spinningup-drl-prototyping","repo_kind":"listed","path":"spinup/algos/sac/core.py","file_url":"https://github.com/watchernyu/spinningup-drl-prototyping/blob/HEAD/spinup/algos/sac/core.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:EagerTensor/2/float, mu:EagerTensor/2/float, log_std:EagerTensor/2/float","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5c26c93931dce503"},"code_page":"/code/gaussian-likelihood","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5c26c93931dce503"}},{"code_sha256":"958cab9f3ba6af81","code_sha256_prefix":"958cab9f3ba6af81","entry":"gaussian_likelihood","repo":"SaminYeasar/off_policy_ac","repo_kind":"listed","path":"SAC/SAC.py","file_url":"https://github.com/SaminYeasar/off_policy_ac/blob/HEAD/SAC/SAC.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"noise:Tensor/2/float, log_std: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":"958cab9f3ba6af81"},"code_page":"/code/gaussian-likelihood","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":"958cab9f3ba6af81"}},{"code_sha256":"d4978950888874f4","code_sha256_prefix":"d4978950888874f4","entry":"get_device","repo":"thomashirtz/soft-actor-critic","repo_kind":"listed","path":"soft_actor_critic/agent.py","file_url":"https://github.com/thomashirtz/soft-actor-critic/blob/HEAD/soft_actor_critic/agent.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":"overwrite:NoneType/0/?, device:str/0/str, fallback_device:str/0/str","fixture_out_type":"device","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/get-device","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d4978950888874f4"}},{"code_sha256":"1afbe631504fbaf7","code_sha256_prefix":"1afbe631504fbaf7","entry":"get_multilayer_perceptron","repo":"thomashirtz/soft-actor-critic","repo_kind":"listed","path":"soft_actor_critic/agent.py","file_url":"https://github.com/thomashirtz/soft-actor-critic/blob/HEAD/soft_actor_critic/agent.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":"unit_list:list/1/int, keep_last_relu:bool/0/bool","fixture_out_type":"Sequential","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":"1afbe631504fbaf7"}},{"code_sha256":"1dd9b9ae9fa9426f","code_sha256_prefix":"1dd9b9ae9fa9426f","entry":"group_by_keys","repo":"yhisaki/average-reward-drl","repo_kind":"listed","path":"average_reward_drl/algorithms/sac.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"lst:list/1/dict, use_all_keys:bool/0/bool","fixture_out_type":"dict","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, yhisaki/average-reward-drl when it was checked","mcp_get_code":{"code_sha256":"1dd9b9ae9fa9426f"}},{"code_sha256":"c70b5621a0ca8047","code_sha256_prefix":"c70b5621a0ca8047","entry":"is_json_serializable","repo":"kdally/fault-tolerant-flight-control-drl","repo_kind":"listed","path":"fault_tolerant_flight_control_drl/agent/sac.py","file_url":"https://github.com/kdally/fault-tolerant-flight-control-drl/blob/HEAD/fault_tolerant_flight_control_drl/agent/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"item:dict/0/?","fixture_out_type":"bool","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/is-json-serializable","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c70b5621a0ca8047"}},{"code_sha256":"ad86f46cc9af956b","code_sha256_prefix":"ad86f46cc9af956b","entry":"json_to_data","repo":"kdally/fault-tolerant-flight-control-drl","repo_kind":"listed","path":"fault_tolerant_flight_control_drl/agent/sac.py","file_url":"https://github.com/kdally/fault-tolerant-flight-control-drl/blob/HEAD/fault_tolerant_flight_control_drl/agent/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":"json_string:str/0/str, custom_objects:dict/0/?","fixture_out_type":"dict","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":"ad86f46cc9af956b"}},{"code_sha256":"a1e9dc4773ffeba5","code_sha256_prefix":"a1e9dc4773ffeba5","entry":"mlp","repo":"tmjeong1103/RL_with_RAY","repo_kind":"listed","path":"SAC_RAY/model.py","file_url":"https://github.com/tmjeong1103/RL_with_RAY/blob/HEAD/SAC_RAY/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"odim:int/0/int, hdims:list/1/int, actv:callable/0/?, output_actv:NoneType/0/?","fixture_out_type":"Sequential","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/mlp-2","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, tmjeong1103/RL_with_RAY when it was checked","mcp_get_code":{"code_sha256":"a1e9dc4773ffeba5"}},{"code_sha256":"5c5bce3523ed4d69","code_sha256_prefix":"5c5bce3523ed4d69","entry":"ortho_init","repo":"yhisaki/average-reward-drl","repo_kind":"listed","path":"average_reward_drl/algorithms/sac.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"layer:callable/0/?, gain:float/0/float","fixture_out_type":"Linear","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/ortho-init","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, yhisaki/average-reward-drl when it was checked","mcp_get_code":{"code_sha256":"5c5bce3523ed4d69"}},{"code_sha256":"1d75daad61f15424","code_sha256_prefix":"1d75daad61f15424","entry":"params_to_bytes","repo":"kdally/fault-tolerant-flight-control-drl","repo_kind":"listed","path":"fault_tolerant_flight_control_drl/agent/sac.py","file_url":"https://github.com/kdally/fault-tolerant-flight-control-drl/blob/HEAD/fault_tolerant_flight_control_drl/agent/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"params:dict/0/?","fixture_out_type":"bytes","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":"1d75daad61f15424"}},{"code_sha256":"642892e9419a125d","code_sha256_prefix":"642892e9419a125d","entry":"policyNet","repo":"tarod13/SAC","repo_kind":"listed","path":"nets.py","file_url":"https://github.com/tarod13/SAC/blob/HEAD/nets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"s:Tensor/2/float","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, tarod13/SAC when it was checked","mcp_get_code":{"code_sha256":"642892e9419a125d"}},{"code_sha256":"4a486e5048778576","code_sha256_prefix":"4a486e5048778576","entry":"scale_action","repo":"kdally/fault-tolerant-flight-control-drl","repo_kind":"listed","path":"fault_tolerant_flight_control_drl/agent/sac.py","file_url":"https://github.com/kdally/fault-tolerant-flight-control-drl/blob/HEAD/fault_tolerant_flight_control_drl/agent/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"action_space:Box/1/float, action:ndarray/1/float","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":"4a486e5048778576"}},{"code_sha256":"3a0835e6ce008741","code_sha256_prefix":"3a0835e6ce008741","entry":"soft_actor_critic_agent","repo":"Rafael1s/Deep-Reinforcement-Learning-Udacity","repo_kind":"listed","path":"Ant-PyBulletEnv-Soft-Actor-Critic/sac_agent.py","file_url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity/blob/HEAD/Ant-PyBulletEnv-Soft-Actor-Critic/sac_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":"soft_actor_critic_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, Rafael1s/Deep-Reinforcement-Learning-Udacity when it was checked","mcp_get_code":{"code_sha256":"3a0835e6ce008741"}},{"code_sha256":"5a4d3fd6b28ecaf4","code_sha256_prefix":"5a4d3fd6b28ecaf4","entry":"unscale_action","repo":"kdally/fault-tolerant-flight-control-drl","repo_kind":"listed","path":"fault_tolerant_flight_control_drl/agent/sac.py","file_url":"https://github.com/kdally/fault-tolerant-flight-control-drl/blob/HEAD/fault_tolerant_flight_control_drl/agent/sac.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"action_space:Box/1/float, scaled_action:ndarray/1/float","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":"5a4d3fd6b28ecaf4"}},{"code_sha256":"b0e759b2d521e146","code_sha256_prefix":"b0e759b2d521e146","entry":"Agent","repo":"MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning","repo_kind":"listed","path":"src/agents.py","file_url":"https://github.com/MatthieuSarkis/Portfolio-Optimization-and-Goal-Based-Investment-with-Reinforcement-Learning/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/agent","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b0e759b2d521e146"}},{"code_sha256":"2ae117303c9ac594","code_sha256_prefix":"2ae117303c9ac594","entry":"Agent","repo":"BY571/Soft-Actor-Critic-and-Extensions","repo_kind":"listed","path":"files/Agent.py","file_url":"https://github.com/BY571/Soft-Actor-Critic-and-Extensions/blob/HEAD/files/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":"2ae117303c9ac594"}},{"code_sha256":"05437b66f08eb4d6","code_sha256_prefix":"05437b66f08eb4d6","entry":"Agent","repo":"thomashirtz/soft-actor-critic","repo_kind":"listed","path":"soft_actor_critic/agent.py","file_url":"https://github.com/thomashirtz/soft-actor-critic/blob/HEAD/soft_actor_critic/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":"05437b66f08eb4d6"}},{"code_sha256":"eaf547baf5f33e43","code_sha256_prefix":"eaf547baf5f33e43","entry":"Algorithm","repo":"ku2482/discor.pytorch","repo_kind":"listed","path":"discor/algorithm/sac.py","file_url":"https://github.com/ku2482/discor.pytorch/blob/HEAD/discor/algorithm/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/algorithm","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"eaf547baf5f33e43"}},{"code_sha256":"803d90cd603ff8c0","code_sha256_prefix":"803d90cd603ff8c0","entry":"Algorithm","repo":"garyzyr001/rethinking-airl","repo_kind":"listed","path":"airl/algo/sac.py","file_url":"https://github.com/garyzyr001/rethinking-airl/blob/HEAD/airl/algo/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/algorithm","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, garyzyr001/rethinking-airl when it was checked","mcp_get_code":{"code_sha256":"803d90cd603ff8c0"}},{"code_sha256":"ff7a80131e64a08d","code_sha256_prefix":"ff7a80131e64a08d","entry":"Algorithm","repo":"ku2482/gail-airl-ppo.pytorch","repo_kind":"listed","path":"gail_airl_ppo/algo/sac.py","file_url":"https://github.com/ku2482/gail-airl-ppo.pytorch/blob/HEAD/gail_airl_ppo/algo/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/algorithm","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ff7a80131e64a08d"}},{"code_sha256":"110041979f3c0cb8","code_sha256_prefix":"110041979f3c0cb8","entry":"AlgorithmBase","repo":"yhisaki/average-reward-drl","repo_kind":"listed","path":"average_reward_drl/algorithms/sac.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/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":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, yhisaki/average-reward-drl when it was checked","mcp_get_code":{"code_sha256":"110041979f3c0cb8"}},{"code_sha256":"d6d4b5a5d84ba8ad","code_sha256_prefix":"d6d4b5a5d84ba8ad","entry":"BaseNetwork","repo":"ku2482/discor.pytorch","repo_kind":"listed","path":"discor/algorithm/sac.py","file_url":"https://github.com/ku2482/discor.pytorch/blob/HEAD/discor/algorithm/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/basenetwork","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d6d4b5a5d84ba8ad"}},{"code_sha256":"b6b1a23b07a627dd","code_sha256_prefix":"b6b1a23b07a627dd","entry":"Buffer","repo":"ku2482/gail-airl-ppo.pytorch","repo_kind":"listed","path":"gail_airl_ppo/algo/sac.py","file_url":"https://github.com/ku2482/gail-airl-ppo.pytorch/blob/HEAD/gail_airl_ppo/algo/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/buffer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b6b1a23b07a627dd"}},{"code_sha256":"3ef56075bad93ec9","code_sha256_prefix":"3ef56075bad93ec9","entry":"Model","repo":"ikostrikov/jax-rl","repo_kind":"listed","path":"jaxrl/agents/sac/sac_learner.py","file_url":"https://github.com/ikostrikov/jax-rl/blob/HEAD/jaxrl/agents/sac/sac_learner.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/model","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3ef56075bad93ec9"}},{"code_sha256":"7524ef9f7598dd6f","code_sha256_prefix":"7524ef9f7598dd6f","entry":"OBAC","repo":"roythuly/obac","repo_kind":"listed","path":"model/algo.py","file_url":"https://github.com/roythuly/obac/blob/HEAD/model/algo.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, roythuly/obac when it was checked","mcp_get_code":{"code_sha256":"7524ef9f7598dd6f"}},{"code_sha256":"b36d35fd411b0150","code_sha256_prefix":"b36d35fd411b0150","entry":"RLNetwork","repo":"kushagra06/SAC","repo_kind":"listed","path":"model.py","file_url":"https://github.com/kushagra06/SAC/blob/HEAD/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":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, kushagra06/SAC when it was checked","mcp_get_code":{"code_sha256":"b36d35fd411b0150"}},{"code_sha256":"995a5d6382ee476d","code_sha256_prefix":"995a5d6382ee476d","entry":"ReplayMemory","repo":"ajaysub110/rl-pytorch","repo_kind":"listed","path":"sac/models/soft_actor_critic.py","file_url":"https://github.com/ajaysub110/rl-pytorch/blob/HEAD/sac/models/soft_actor_critic.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, ajaysub110/rl-pytorch when it was checked","mcp_get_code":{"code_sha256":"995a5d6382ee476d"}},{"code_sha256":"569d921eb9b51536","code_sha256_prefix":"569d921eb9b51536","entry":"SAC","repo":"kdally/fault-tolerant-flight-control-drl","repo_kind":"listed","path":"fault_tolerant_flight_control_drl/agent/sac.py","file_url":"https://github.com/kdally/fault-tolerant-flight-control-drl/blob/HEAD/fault_tolerant_flight_control_drl/agent/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":"569d921eb9b51536"}},{"code_sha256":"0edd4b0f90be8f84","code_sha256_prefix":"0edd4b0f90be8f84","entry":"SAC","repo":"baturaysaglam/la3p","repo_kind":"listed","path":"Code/SAC/SAC.py","file_url":"https://github.com/baturaysaglam/la3p/blob/HEAD/Code/SAC/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":"0edd4b0f90be8f84"}},{"code_sha256":"4849ba61ae47dd70","code_sha256_prefix":"4849ba61ae47dd70","entry":"SAC","repo":"yhisaki/average-reward-drl","repo_kind":"listed","path":"average_reward_drl/algorithms/sac.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/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":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, yhisaki/average-reward-drl when it was checked","mcp_get_code":{"code_sha256":"4849ba61ae47dd70"}},{"code_sha256":"348b1924f106de50","code_sha256_prefix":"348b1924f106de50","entry":"SAC","repo":"ku2482/discor.pytorch","repo_kind":"listed","path":"discor/algorithm/sac.py","file_url":"https://github.com/ku2482/discor.pytorch/blob/HEAD/discor/algorithm/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":"348b1924f106de50"}},{"code_sha256":"9e2e2c85eabbd88f","code_sha256_prefix":"9e2e2c85eabbd88f","entry":"SAC","repo":"h-aboutalebi/SparceReward","repo_kind":"listed","path":"engine/algorithms/SAC/sac.py","file_url":"https://github.com/h-aboutalebi/SparceReward/blob/HEAD/engine/algorithms/SAC/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":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, h-aboutalebi/SparceReward when it was checked","mcp_get_code":{"code_sha256":"9e2e2c85eabbd88f"}},{"code_sha256":"1cb5a8aa4ee6cb43","code_sha256_prefix":"1cb5a8aa4ee6cb43","entry":"SAC","repo":"sunfex/weighted-sac","repo_kind":"listed","path":"sac.py","file_url":"https://github.com/sunfex/weighted-sac/blob/HEAD/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":"1cb5a8aa4ee6cb43"}},{"code_sha256":"9efbd1e63c6644e5","code_sha256_prefix":"9efbd1e63c6644e5","entry":"SAC","repo":"hyunin-lee/ForecasterSAC","repo_kind":"listed","path":"sac.py","file_url":"https://github.com/hyunin-lee/ForecasterSAC/blob/HEAD/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":"9efbd1e63c6644e5"}},{"code_sha256":"6af70c8a2239d7c5","code_sha256_prefix":"6af70c8a2239d7c5","entry":"SAC","repo":"garyzyr001/rethinking-airl","repo_kind":"listed","path":"airl/algo/sac.py","file_url":"https://github.com/garyzyr001/rethinking-airl/blob/HEAD/airl/algo/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":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, garyzyr001/rethinking-airl when it was checked","mcp_get_code":{"code_sha256":"6af70c8a2239d7c5"}},{"code_sha256":"fa07dbb92f6c222b","code_sha256_prefix":"fa07dbb92f6c222b","entry":"SAC","repo":"MarsEleven/car_racer_RL","repo_kind":"listed","path":"sac/sac.py","file_url":"https://github.com/MarsEleven/car_racer_RL/blob/HEAD/sac/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":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, MarsEleven/car_racer_RL when it was checked","mcp_get_code":{"code_sha256":"fa07dbb92f6c222b"}},{"code_sha256":"104ef2d3e37baa21","code_sha256_prefix":"104ef2d3e37baa21","entry":"SAC","repo":"ku2482/gail-airl-ppo.pytorch","repo_kind":"listed","path":"gail_airl_ppo/algo/sac.py","file_url":"https://github.com/ku2482/gail-airl-ppo.pytorch/blob/HEAD/gail_airl_ppo/algo/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":"104ef2d3e37baa21"}},{"code_sha256":"d77f61cb28da8383","code_sha256_prefix":"d77f61cb28da8383","entry":"SAC","repo":"pranz24/pytorch-soft-actor-critic","repo_kind":"listed","path":"sac.py","file_url":"https://github.com/pranz24/pytorch-soft-actor-critic/blob/HEAD/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":"d77f61cb28da8383"}},{"code_sha256":"6bc96035de025e83","code_sha256_prefix":"6bc96035de025e83","entry":"SACLearner","repo":"ikostrikov/jax-rl","repo_kind":"listed","path":"jaxrl/agents/sac/sac_learner.py","file_url":"https://github.com/ikostrikov/jax-rl/blob/HEAD/jaxrl/agents/sac/sac_learner.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":"6bc96035de025e83"}},{"code_sha256":"3e1e70dd1d5f3958","code_sha256_prefix":"3e1e70dd1d5f3958","entry":"SAC_Trainer","repo":"quantumiracle/Popular-RL-Algorithms","repo_kind":"listed","path":"sac_v2.py","file_url":"https://github.com/quantumiracle/Popular-RL-Algorithms/blob/HEAD/sac_v2.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":"3e1e70dd1d5f3958"}},{"code_sha256":"ecf34b65e8d9d3bb","code_sha256_prefix":"ecf34b65e8d9d3bb","entry":"SoftActorCritic","repo":"ajaysub110/rl-pytorch","repo_kind":"listed","path":"sac/models/soft_actor_critic.py","file_url":"https://github.com/ajaysub110/rl-pytorch/blob/HEAD/sac/models/soft_actor_critic.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, ajaysub110/rl-pytorch when it was checked","mcp_get_code":{"code_sha256":"ecf34b65e8d9d3bb"}},{"code_sha256":"231f633be51bd617","code_sha256_prefix":"231f633be51bd617","entry":"_soft_update","repo":"ku2482/discor.pytorch","repo_kind":"listed","path":"discor/algorithm/sac.py","file_url":"https://github.com/ku2482/discor.pytorch/blob/HEAD/discor/algorithm/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":"231f633be51bd617"}},{"code_sha256":"f07528bc5e071757","code_sha256_prefix":"f07528bc5e071757","entry":"_update_jit","repo":"ikostrikov/jax-rl","repo_kind":"listed","path":"jaxrl/agents/sac/sac_learner.py","file_url":"https://github.com/ikostrikov/jax-rl/blob/HEAD/jaxrl/agents/sac/sac_learner.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":"f07528bc5e071757"}},{"code_sha256":"198be549ce9696ef","code_sha256_prefix":"198be549ce9696ef","entry":"apply_squashing_func","repo":"watchernyu/spinningup-drl-prototyping","repo_kind":"listed","path":"spinup/algos/sac/core.py","file_url":"https://github.com/watchernyu/spinningup-drl-prototyping/blob/HEAD/spinup/algos/sac/core.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":"198be549ce9696ef"}},{"code_sha256":"ded76544fe9d6607","code_sha256_prefix":"ded76544fe9d6607","entry":"assert_action","repo":"ku2482/discor.pytorch","repo_kind":"listed","path":"discor/algorithm/sac.py","file_url":"https://github.com/ku2482/discor.pytorch/blob/HEAD/discor/algorithm/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":"ded76544fe9d6607"}},{"code_sha256":"d1076220e33b55ba","code_sha256_prefix":"d1076220e33b55ba","entry":"copy_params","repo":"ajaysub110/rl-pytorch","repo_kind":"listed","path":"sac/models/soft_actor_critic.py","file_url":"https://github.com/ajaysub110/rl-pytorch/blob/HEAD/sac/models/soft_actor_critic.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/copy-params","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ajaysub110/rl-pytorch when it was checked","mcp_get_code":{"code_sha256":"d1076220e33b55ba"}},{"code_sha256":"ed542fae5c7f2c04","code_sha256_prefix":"ed542fae5c7f2c04","entry":"disable_gradient","repo":"garyzyr001/rethinking-airl","repo_kind":"listed","path":"airl/algo/sac.py","file_url":"https://github.com/garyzyr001/rethinking-airl/blob/HEAD/airl/algo/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":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, garyzyr001/rethinking-airl when it was checked","mcp_get_code":{"code_sha256":"ed542fae5c7f2c04"}},{"code_sha256":"799c08d64f58d9ef","code_sha256_prefix":"799c08d64f58d9ef","entry":"hard_update","repo":"Rafael1s/Deep-Reinforcement-Learning-Udacity","repo_kind":"listed","path":"Ant-PyBulletEnv-Soft-Actor-Critic/sac_agent.py","file_url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity/blob/HEAD/Ant-PyBulletEnv-Soft-Actor-Critic/sac_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, Rafael1s/Deep-Reinforcement-Learning-Udacity when it was checked","mcp_get_code":{"code_sha256":"799c08d64f58d9ef"}},{"code_sha256":"7abe222eb3afeb6f","code_sha256_prefix":"7abe222eb3afeb6f","entry":"hard_update","repo":"ShawK91/Evolutionary-Reinforcement-Learning","repo_kind":"listed","path":"algos/sac.py","file_url":"https://github.com/ShawK91/Evolutionary-Reinforcement-Learning/blob/HEAD/algos/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":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ShawK91/Evolutionary-Reinforcement-Learning when it was checked","mcp_get_code":{"code_sha256":"7abe222eb3afeb6f"}},{"code_sha256":"1adf91cc413cf6c2","code_sha256_prefix":"1adf91cc413cf6c2","entry":"hard_update","repo":"MarsEleven/car_racer_RL","repo_kind":"listed","path":"sac/sac.py","file_url":"https://github.com/MarsEleven/car_racer_RL/blob/HEAD/sac/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":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, MarsEleven/car_racer_RL when it was checked","mcp_get_code":{"code_sha256":"1adf91cc413cf6c2"}},{"code_sha256":"8576d4b41e6ed12f","code_sha256_prefix":"8576d4b41e6ed12f","entry":"init_weights","repo":"ajaysub110/rl-pytorch","repo_kind":"listed","path":"sac/models/soft_actor_critic.py","file_url":"https://github.com/ajaysub110/rl-pytorch/blob/HEAD/sac/models/soft_actor_critic.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, ajaysub110/rl-pytorch when it was checked","mcp_get_code":{"code_sha256":"8576d4b41e6ed12f"}},{"code_sha256":"544fe1f08a36cc62","code_sha256_prefix":"544fe1f08a36cc62","entry":"initialize_weights_xavier","repo":"ku2482/discor.pytorch","repo_kind":"listed","path":"discor/algorithm/sac.py","file_url":"https://github.com/ku2482/discor.pytorch/blob/HEAD/discor/algorithm/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":"544fe1f08a36cc62"}},{"code_sha256":"706459e26fbb0b4c","code_sha256_prefix":"706459e26fbb0b4c","entry":"load_model","repo":"thomashirtz/soft-actor-critic","repo_kind":"listed","path":"soft_actor_critic/agent.py","file_url":"https://github.com/thomashirtz/soft-actor-critic/blob/HEAD/soft_actor_critic/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/load-model","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"706459e26fbb0b4c"}},{"code_sha256":"e68b07bcdded00fa","code_sha256_prefix":"e68b07bcdded00fa","entry":"mlp","repo":"watchernyu/spinningup-drl-prototyping","repo_kind":"listed","path":"spinup/algos/sac/core.py","file_url":"https://github.com/watchernyu/spinningup-drl-prototyping/blob/HEAD/spinup/algos/sac/core.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/mlp-2","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e68b07bcdded00fa"}},{"code_sha256":"8498689f07030ac8","code_sha256_prefix":"8498689f07030ac8","entry":"mlp_actor_critic","repo":"watchernyu/spinningup-drl-prototyping","repo_kind":"listed","path":"spinup/algos/sac/core.py","file_url":"https://github.com/watchernyu/spinningup-drl-prototyping/blob/HEAD/spinup/algos/sac/core.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":"8498689f07030ac8"}},{"code_sha256":"a860fee8188a0218","code_sha256_prefix":"a860fee8188a0218","entry":"mlp_gaussian_policy","repo":"watchernyu/spinningup-drl-prototyping","repo_kind":"listed","path":"spinup/algos/sac/core.py","file_url":"https://github.com/watchernyu/spinningup-drl-prototyping/blob/HEAD/spinup/algos/sac/core.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":"a860fee8188a0218"}},{"code_sha256":"f299a2900b4034fa","code_sha256_prefix":"f299a2900b4034fa","entry":"polyak_update","repo":"yhisaki/average-reward-drl","repo_kind":"listed","path":"average_reward_drl/algorithms/sac.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/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":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, yhisaki/average-reward-drl when it was checked","mcp_get_code":{"code_sha256":"f299a2900b4034fa"}},{"code_sha256":"7d297778525c40d1","code_sha256_prefix":"7d297778525c40d1","entry":"save_model","repo":"thomashirtz/soft-actor-critic","repo_kind":"listed","path":"soft_actor_critic/agent.py","file_url":"https://github.com/thomashirtz/soft-actor-critic/blob/HEAD/soft_actor_critic/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/save-model","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7d297778525c40d1"}},{"code_sha256":"0dfad75cd2d202d6","code_sha256_prefix":"0dfad75cd2d202d6","entry":"set_global_seeds","repo":"kdally/fault-tolerant-flight-control-drl","repo_kind":"listed","path":"fault_tolerant_flight_control_drl/agent/sac.py","file_url":"https://github.com/kdally/fault-tolerant-flight-control-drl/blob/HEAD/fault_tolerant_flight_control_drl/agent/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":"0dfad75cd2d202d6"}},{"code_sha256":"f735812881238a1f","code_sha256_prefix":"f735812881238a1f","entry":"soft_update","repo":"Rafael1s/Deep-Reinforcement-Learning-Udacity","repo_kind":"listed","path":"Ant-PyBulletEnv-Soft-Actor-Critic/sac_agent.py","file_url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity/blob/HEAD/Ant-PyBulletEnv-Soft-Actor-Critic/sac_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/soft-update","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Rafael1s/Deep-Reinforcement-Learning-Udacity when it was checked","mcp_get_code":{"code_sha256":"f735812881238a1f"}},{"code_sha256":"e8abbe917721f0c8","code_sha256_prefix":"e8abbe917721f0c8","entry":"soft_update","repo":"ku2482/discor.pytorch","repo_kind":"listed","path":"discor/algorithm/sac.py","file_url":"https://github.com/ku2482/discor.pytorch/blob/HEAD/discor/algorithm/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/soft-update","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e8abbe917721f0c8"}},{"code_sha256":"fcdeb82694a504e1","code_sha256_prefix":"fcdeb82694a504e1","entry":"soft_update","repo":"ShawK91/Evolutionary-Reinforcement-Learning","repo_kind":"listed","path":"algos/sac.py","file_url":"https://github.com/ShawK91/Evolutionary-Reinforcement-Learning/blob/HEAD/algos/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/soft-update","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ShawK91/Evolutionary-Reinforcement-Learning when it was checked","mcp_get_code":{"code_sha256":"fcdeb82694a504e1"}},{"code_sha256":"8dc0540b8dfe9b97","code_sha256_prefix":"8dc0540b8dfe9b97","entry":"soft_update","repo":"garyzyr001/rethinking-airl","repo_kind":"listed","path":"airl/algo/sac.py","file_url":"https://github.com/garyzyr001/rethinking-airl/blob/HEAD/airl/algo/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/soft-update","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, garyzyr001/rethinking-airl when it was checked","mcp_get_code":{"code_sha256":"8dc0540b8dfe9b97"}},{"code_sha256":"ace24484ab1d6b7f","code_sha256_prefix":"ace24484ab1d6b7f","entry":"soft_update","repo":"MarsEleven/car_racer_RL","repo_kind":"listed","path":"sac/sac.py","file_url":"https://github.com/MarsEleven/car_racer_RL/blob/HEAD/sac/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/soft-update","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, MarsEleven/car_racer_RL when it was checked","mcp_get_code":{"code_sha256":"ace24484ab1d6b7f"}},{"code_sha256":"54ab8d446018b958","code_sha256_prefix":"54ab8d446018b958","entry":"soft_update","repo":"ajaysub110/rl-pytorch","repo_kind":"listed","path":"sac/models/soft_actor_critic.py","file_url":"https://github.com/ajaysub110/rl-pytorch/blob/HEAD/sac/models/soft_actor_critic.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/soft-update","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, ajaysub110/rl-pytorch when it was checked","mcp_get_code":{"code_sha256":"54ab8d446018b958"}},{"code_sha256":"f62b5d3c6983e5aa","code_sha256_prefix":"f62b5d3c6983e5aa","entry":"target_update","repo":"ikostrikov/jax-rl","repo_kind":"listed","path":"jaxrl/agents/sac/sac_learner.py","file_url":"https://github.com/ikostrikov/jax-rl/blob/HEAD/jaxrl/agents/sac/sac_learner.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/target-update","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f62b5d3c6983e5aa"}},{"code_sha256":"85fff8ae028fc1dd","code_sha256_prefix":"85fff8ae028fc1dd","entry":"update_network_parameters","repo":"thomashirtz/soft-actor-critic","repo_kind":"listed","path":"soft_actor_critic/agent.py","file_url":"https://github.com/thomashirtz/soft-actor-critic/blob/HEAD/soft_actor_critic/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":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"85fff8ae028fc1dd"}},{"code_sha256":"68c08ef9d5d473a7","code_sha256_prefix":"68c08ef9d5d473a7","entry":"weight_init","repo":"SaminYeasar/off_policy_ac","repo_kind":"listed","path":"SAC/SAC.py","file_url":"https://github.com/SaminYeasar/off_policy_ac/blob/HEAD/SAC/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/weight-init","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":"68c08ef9d5d473a7"}},{"code_sha256":"6ae1b395aeb4e7d3","code_sha256_prefix":"6ae1b395aeb4e7d3","entry":"weight_initialization","repo":"thomashirtz/soft-actor-critic","repo_kind":"listed","path":"soft_actor_critic/agent.py","file_url":"https://github.com/thomashirtz/soft-actor-critic/blob/HEAD/soft_actor_critic/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":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6ae1b395aeb4e7d3"}},{"code_sha256":"0537c4bc8300d410","code_sha256_prefix":"0537c4bc8300d410","entry":"weights_init_","repo":"Rafael1s/Deep-Reinforcement-Learning-Udacity","repo_kind":"listed","path":"Ant-PyBulletEnv-Soft-Actor-Critic/sac_agent.py","file_url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity/blob/HEAD/Ant-PyBulletEnv-Soft-Actor-Critic/sac_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, Rafael1s/Deep-Reinforcement-Learning-Udacity when it was checked","mcp_get_code":{"code_sha256":"0537c4bc8300d410"}},{"code_sha256":"abe2b5a0b5e817fd","code_sha256_prefix":"abe2b5a0b5e817fd","entry":"weights_init_","repo":"MarsEleven/car_racer_RL","repo_kind":"listed","path":"sac/sac.py","file_url":"https://github.com/MarsEleven/car_racer_RL/blob/HEAD/sac/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":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, MarsEleven/car_racer_RL when it was checked","mcp_get_code":{"code_sha256":"abe2b5a0b5e817fd"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"00a64cc5d49ad6c1d05d2d10b885f4286fad7d25759d6764aad2c7dae3bf7069","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}