{"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/proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","arxiv_id":"1707.06347","date":"2017-07-20","proceeding":null,"authors":["John Schulman","Filip Wolski","Prafulla Dhariwal","Alec Radford","Oleg Klimov"],"abstract":"We propose a new family of policy gradient methods for reinforcement\nlearning, which alternate between sampling data through interaction with the\nenvironment, and optimizing a \"surrogate\" objective function using stochastic\ngradient ascent. Whereas standard policy gradient methods perform one gradient\nupdate per data sample, we propose a novel objective function that enables\nmultiple epochs of minibatch updates. The new methods, which we call proximal\npolicy optimization (PPO), have some of the benefits of trust region policy\noptimization (TRPO), but they are much simpler to implement, more general, and\nhave better sample complexity (empirically). Our experiments test PPO on a\ncollection of benchmark tasks, including simulated robotic locomotion and Atari\ngame playing, and we show that PPO outperforms other online policy gradient\nmethods, and overall strikes a favorable balance between sample complexity,\nsimplicity, and wall-time.","url_abs":"http://arxiv.org/abs/1707.06347v2","url_pdf":"http://arxiv.org/pdf/1707.06347v2.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":"proximal-policy-optimization-algorithms","repo_url":"https://bitbucket.org/act-lab/release","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/170928/-Review-Generative-Adversarial-Imitation-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/170928/-Review-Proximal-Policy-Optimization-Algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/2mawi2/master-thesis-experiments","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/ASzot/ppo-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Aravind-11/AI-Gaming","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Aravind-11/IITM_Saastra","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Aravind-11/Multi-Agent-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/BerkeleyLearnVerify/VerifAI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/BrianPulfer/PapersReimplementations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/CSautier/Breakout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/CSautier/PongBot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Crevass/Hybrid-Agent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/DMIU-ShELL/MOSAIC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/DavidCastilloAlvarado/Path-planning-and-Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/EconomistGrant/HTFE-tensortrade","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/FMArduini/python-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/GiadaSimionato/Reasoning_Agents_2020","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Gouet/Acrobot-PPO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Gouet/Breakout-V0","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Gouet/PPO-gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Gouet/PPO-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Gregory-Eales/proximal-policy-optimization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/InSpaceAI/RL-Zoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/JL321/Proximal-Policy-Optimization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/JonasRSV/PPO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Khrylx/PyTorch-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/LuEE-C/PPO-Keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/MatteoBrentegani/PPO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Michaelrising/Prog-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","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":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/NACLab/robust-active-inference","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Narsil/rl-baselines","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/NervanaSystems/coach","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Nordeus/heroic-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/OctThe16th/PPO-Keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Ostyk/walk-bot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","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":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/SPark9625/PyTorch-Proximal-Policy-Optimization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/SalvatoreCognetta/reasoning-agent-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Stippler/cow-simulator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/UesugiErii/tf2-PPO-atari","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/Zartris/TD3_continuous_control","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/adamos581/ppo-keras-football","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/adik993/ppo-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/ailab-pku/rl-framework","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/alecfilios/Training-Intelligent-game-Agents-through-Competitive-Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/alex-petrenko/sample-factory","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/alexbaumi/PPO-Algorithm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/alexbaumi/PPO-Algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/alexmlamb/blocks_rl_gru_setup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/alirezakazemipour/ppo-rnd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/amanda-lambda/drl-experiments","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/amanda-lambda/hack-flappy-bird-drl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/amartyamukherjee/ppo-packcooling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/amaudruz/RL_openaigym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/amzoyang/CS-221-Final-Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/andyljones/zonotable","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/anthonysong98/super-mario-bros-ppo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/araffin/sbx","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/automl/learna","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/bay3s/ppo-parallel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/bay3s/ppo-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/benevolentAI/guacamol_baselines","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/benpetit/cs379c","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/bentrevett/pytorch-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/bonniesjli/PPO-Reacher_UnityML","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/bonniesjli/PPO_Reacher","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/chainer/chainerrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/cipher982/ppo-exploration","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/clwainwright/proximal_policy_optimization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/danelee2601/rl-based-automatic-berthing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/decoderkurt/research_project_school_of_ai_2019","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/deconlabs/Binanace-trading-simulation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/deconlabs/Binanace_trading_simulation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/deconlabs/TradingZoo-Dynamic-fee-simulation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/dickreuter/neuron_poker","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/dmiu-shell/deeprl-shell","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","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":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/downingbots/RLDonkeycar","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/eladsar/rbi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/emerge-lab/nocturne_lab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/evieq01/oodil","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/facebookresearch/Horizon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","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":"proximal-policy-optimization-algorithms","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":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/gaetanserre/l2rpn-2022_ppo-baseline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/georgkruse/cleanqrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/gmoss1/Kaggle-Halite-IV-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/goncharom/PPOv1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/gstoica27/cpg_ppo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/guofeng201507/ISA-IPA-2020-05-05-IS1PT-GRP-High5-StockTrading","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/gwthomas/gtml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/hamishs/JAX-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/harruff/Senior_Project_Repository","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/hdparks/AsteroidsDeepReinforcement","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/hmhuy0/SIM-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/ifestus/rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/ikostrikov/pytorch-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/inoryy/reaver","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/intellisys-lab/stellaris-sc24","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/jcwleo/curiosity-driven-exploration-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/jcwleo/random-network-distillation-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/jfpettit/flare","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/jhare96/reinforcement-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/jongornet14/HyperController","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/jsztompka/MultiAgent-PPO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/jsztompka/PPO-demo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/juliusfrost/Research-Paper-Implementations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/jvidals09/Decentralized-and-multi-agent-control-of-Franka-Emika-Panda-robot-in-continuous-task-execution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/jw1401/PPO-Tensorflow-2.0","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","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":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/lcswillems/torch-ac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/lgerrets/rl18-curiosity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/liuyuezhang/pyrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/liyiyuian/Deep-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/llSourcell/OpenAI_Five_vs_Dota2_Explained","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/mark-gluzman/NmodelPPO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","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":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/michael-snower/ppo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/microsoft/strategically_efficient_rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/mightypirate1/PPO_homebrew","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/miroblog/tf_deep_rl_trader","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/mit-realm/neuriss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/montaserFath/Reinforcement-Learning-for-Prosthetics","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/morikatron/GAIL_PPO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/morikatron/PPO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/near32/regym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/nikhilbarhate99/PPO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/nikhilbarhate99/PPO-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/nitthilan/pommerman","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/nric/ProximalPolicyOptimizationContinuousKeras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/nvlabs/gbrl_sb3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/openpsi-projects/srl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/reinforcement-learning-kr/pg_travel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/rshnn/battleship","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/s-sd/task-amenability","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/saschaschramm/Pong","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/sc2crazy/StarCrackRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/seungjaeryanlee/osim-rl-helper","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/shiningsunnyday/mcts-chess","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/shreyesss/PPO-implementation-keras-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/shuishida/soaprl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/siddharthverma314/proximalpolicyoptimization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/silvialuu/DRL-2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/sirakik/mprg_fc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/sirakik/ppo_football","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/synthlabsai/big-math","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/taku-y/20181125-pybullet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/takuseno/ppo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/tatsu-lab/linguistic_calibration","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/tcmxx/CNTKUnityTools","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/tensorlayer/RLzoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/theresearchai/vehicle_routing_rl_2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/tidedra/vl-rlhf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/tilkb/thermoai","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","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":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/tobiasemrich/SchafkopfRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/tommyvsfu1/RL-NTU","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/tuanpnm99/RLPongAgent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/uvipen/super-mario-bros-ppo-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/vcadillog/PPO-Mario-Bros-Tensorflow-2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/vermashresth/damage-aware-PPO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/vheuthe/microbot_rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/wangshub/RL-Stock","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/wangzhengfei0730/NIPS2018-AIforProsthetics","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/xiawenwen49/ppo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/xtma/simple-pytorch-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/yoavalon/Quadcopter-env","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/yoavalon/QuadcopterReinforcementLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/zjlab-ammi/llm4rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/zsz-hst/RL_single_chase_point","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/BIT-aerial-robotics/AquaML/blob/2.1.11/AquaML/rlalgo/PPOAgent.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","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":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/DevSlem/AINE-DRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"proximal-policy-optimization-algorithms","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":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Proximal_Policy_Optimization_Algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/OctopusMind/RLHF_PPO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/arnomoonens/yarll","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/dyabel/handson_rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","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":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/pytorch/rl/tree/main/examples/ppo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"proximal-policy-optimization-algorithms","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":"proximal-policy-optimization-algorithms","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":"proximal-policy-optimization-algorithms","repo_url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/ppo","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":"dota-2","task_name":"Dota 2"},{"task_slug":"multi-goal-reinforcement-learning","task_name":"Multi-Goal Reinforcement Learning"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"openai-gym","task_name":"OpenAI Gym"},{"task_slug":"policy-gradient-methods","task_name":"Policy Gradient Methods"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"ppo","method_name":"PPO"}],"datasets_introduced":[],"methods_introduced":[{"slug":"ppo","name":"PPO","full_name":"Proximal Policy Optimization"}],"results":[{"leaderboard":"/sota/continuous-control-on-lunar-lander-openai-gym","task":"Continuous Control","dataset":"Lunar Lander (OpenAI Gym)","model":"PPO","rank_in_archive_order":4,"of":5,"metrics":{"Score":"175.14±44.94"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench-1","task":"Neural Architecture Search","dataset":"NATS-Bench Topology, CIFAR-10","model":"PPO (Schulman et al., 2017)","rank_in_archive_order":3,"of":11,"metrics":{"Test Accuracy":"94.02"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench-2","task":"Neural Architecture Search","dataset":"NATS-Bench Topology, CIFAR-100","model":"PPO (Schulman et al., 2017)","rank_in_archive_order":2,"of":11,"metrics":{"Test Accuracy":"71.68"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nats-bench","task":"Neural Architecture Search","dataset":"NATS-Bench Topology, ImageNet16-120","model":"PPO (Schulman et al., 2017)","rank_in_archive_order":3,"of":11,"metrics":{"Test Accuracy":"44.95"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-ant-v4","task":"OpenAI Gym","dataset":"Ant-v4","model":"PPO","rank_in_archive_order":5,"of":5,"metrics":{"Average Return":"608.97"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-halfcheetah-v4","task":"OpenAI Gym","dataset":"HalfCheetah-v4","model":"PPO","rank_in_archive_order":5,"of":5,"metrics":{"Average Return":"6006.11"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-hopper-v4","task":"OpenAI Gym","dataset":"Hopper-v4","model":"PPO","rank_in_archive_order":5,"of":5,"metrics":{"Average Return":"790.77"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-humanoid-v4","task":"OpenAI Gym","dataset":"Humanoid-v4","model":"PPO","rank_in_archive_order":3,"of":5,"metrics":{"Average Return":"925.89"},"uses_additional_data":false},{"leaderboard":"/sota/openai-gym-on-walker2d-v4","task":"OpenAI Gym","dataset":"Walker2d-v4","model":"PPO","rank_in_archive_order":4,"of":5,"metrics":{"Average Return":"2739.81"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1707.06347","atlas_url":"https://app.syntology.ai/?focus=1707.06347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.06347"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1707.06347"},"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":"1707.06347"},"call":"get_harvested_code_for_paper(arxiv_id=\"1707.06347\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"1707.06347"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1707.06347\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1707.06347"},"call":"get_concepts_for_paper(arxiv_id=\"1707.06347\")"}],"by_repo":[{"repo":"bitbucket.org/act-lab/release","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"170928/-Review-Generative-Adversarial-Imitation-Learning","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"170928/-Review-Proximal-Policy-Optimization-Algorithms","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"2mawi2/master-thesis-experiments","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ASzot/ppo-pytorch","kind":"listed","samples":3,"ran":3,"instrument":1,"unverified":0},{"repo":"Aravind-11/AI-Gaming","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Aravind-11/IITM_Saastra","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Aravind-11/Multi-Agent-RL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"BerkeleyLearnVerify/VerifAI","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"BrianPulfer/PapersReimplementations","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"CSautier/Breakout","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"CSautier/PongBot","kind":"listed","samples":1,"ran":1,"instrument":1,"unverified":0},{"repo":"Crevass/Hybrid-Agent","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":"DMIU-ShELL/MOSAIC","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"DavidCastilloAlvarado/Path-planning-and-Reinforcement-Learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"EconomistGrant/HTFE-tensortrade","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"FMArduini/python-rl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"GiadaSimionato/Reasoning_Agents_2020","kind":"listed","samples":7,"ran":4,"instrument":1,"unverified":3},{"repo":"Gouet/Acrobot-PPO","kind":"listed","samples":2,"ran":1,"instrument":1,"unverified":1},{"repo":"Gouet/Breakout-V0","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Gouet/PPO-gym","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"Gouet/PPO-pytorch","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"Gregory-Eales/proximal-policy-optimization","kind":"listed","samples":4,"ran":3,"instrument":0,"unverified":1},{"repo":"InSpaceAI/RL-Zoo","kind":"listed","samples":4,"ran":1,"instrument":0,"unverified":3},{"repo":"JL321/Proximal-Policy-Optimization","kind":"listed","samples":3,"ran":0,"instrument":0,"unverified":3},{"repo":"JonasRSV/PPO","kind":"listed","samples":3,"ran":2,"instrument":0,"unverified":1},{"repo":"Khrylx/PyTorch-RL","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"LuEE-C/PPO-Keras","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MatteoBrentegani/PPO","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"Michaelrising/Prog-RL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MrSyee/pg-is-all-you-need","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"NACLab/robust-active-inference","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Narsil/rl-baselines","kind":"listed","samples":4,"ran":3,"instrument":0,"unverified":1},{"repo":"NervanaSystems/coach","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Nordeus/heroic-rl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"OctThe16th/PPO-Keras","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Ostyk/walk-bot","kind":"listed","samples":2,"ran":1,"instrument":1,"unverified":1},{"repo":"Rafael1s/Deep-Reinforcement-Learning-Udacity","kind":"listed","samples":2,"ran":1,"instrument":1,"unverified":1},{"repo":"SPark9625/PyTorch-Proximal-Policy-Optimization","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"SalvatoreCognetta/reasoning-agent-project","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Stippler/cow-simulator","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"UesugiErii/tf2-PPO-atari","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Zartris/TD3_continuous_control","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"adamos581/ppo-keras-football","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"adik993/ppo-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ailab-pku/rl-framework","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":"alecfilios/Training-Intelligent-game-Agents-through-Competitive-Reinforcement-Learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"alex-petrenko/sample-factory","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2006.11751"],"harvested_for_calls":[{"arxiv_id":"2006.11751","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.11751"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.11751\")"}]},{"repo":"alexbaumi/PPO-Algorithm","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"alexbaumi/PPO-Algorithms","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"alexmlamb/blocks_rl_gru_setup","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"alirezakazemipour/ppo-rnd","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1810.12894"],"harvested_for_calls":[{"arxiv_id":"1810.12894","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1810.12894"},"call":"get_harvested_code_for_paper(arxiv_id=\"1810.12894\")"}]},{"repo":"amanda-lambda/drl-experiments","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"amanda-lambda/hack-flappy-bird-drl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"amartyamukherjee/ppo-packcooling","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"amaudruz/RL_openaigym","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"amzoyang/CS-221-Final-Project","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"andyljones/zonotable","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"anthonysong98/super-mario-bros-ppo","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"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":"automl/learna","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1812.11951"],"harvested_for_calls":[{"arxiv_id":"1812.11951","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1812.11951"},"call":"get_harvested_code_for_paper(arxiv_id=\"1812.11951\")"}]},{"repo":"bay3s/ppo-parallel","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"bay3s/ppo-rl","kind":"listed","samples":3,"ran":2,"instrument":0,"unverified":1},{"repo":"benevolentAI/guacamol_baselines","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"benpetit/cs379c","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"bentrevett/pytorch-rl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1602.01783"],"harvested_for_calls":[{"arxiv_id":"1602.01783","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1602.01783"},"call":"get_harvested_code_for_paper(arxiv_id=\"1602.01783\")"}]},{"repo":"bonniesjli/PPO-Reacher_UnityML","kind":"listed","samples":4,"ran":4,"instrument":0,"unverified":0},{"repo":"bonniesjli/PPO_Reacher","kind":"listed","samples":3,"ran":3,"instrument":0,"unverified":0},{"repo":"chainer/chainerrl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1912.03905"],"harvested_for_calls":[{"arxiv_id":"1912.03905","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1912.03905"},"call":"get_harvested_code_for_paper(arxiv_id=\"1912.03905\")"}]},{"repo":"cipher982/ppo-exploration","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"clwainwright/proximal_policy_optimization","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"danelee2601/rl-based-automatic-berthing","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"decoderkurt/research_project_school_of_ai_2019","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"deconlabs/Binanace-trading-simulation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1710.02298"],"harvested_for_calls":[{"arxiv_id":"1710.02298","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1710.02298"},"call":"get_harvested_code_for_paper(arxiv_id=\"1710.02298\")"}]},{"repo":"deconlabs/Binanace_trading_simulation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"deconlabs/TradingZoo-Dynamic-fee-simulation","kind":"listed","samples":2,"ran":1,"instrument":1,"unverified":1},{"repo":"dickreuter/neuron_poker","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"dmiu-shell/deeprl-shell","kind":"listed","samples":4,"ran":4,"instrument":1,"unverified":0},{"repo":"donamin/llc","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"downingbots/RLDonkeycar","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"eladsar/rbi","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"emerge-lab/nocturne_lab","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2103.01955"],"harvested_for_calls":[{"arxiv_id":"2103.01955","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.01955"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.01955\")"}]},{"repo":"evieq01/oodil","kind":"listed","samples":7,"ran":5,"instrument":2,"unverified":2},{"repo":"facebookresearch/Horizon","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":"gaetanserre/l2rpn-2022_ppo-baseline","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"georgkruse/cleanqrl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"gmoss1/Kaggle-Halite-IV-RL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"goncharom/PPOv1","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"gstoica27/cpg_ppo","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"guofeng201507/ISA-IPA-2020-05-05-IS1PT-GRP-High5-StockTrading","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"gwthomas/gtml","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"hamishs/JAX-RL","kind":"listed","samples":5,"ran":3,"instrument":1,"unverified":2},{"repo":"harruff/Senior_Project_Repository","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"hdparks/AsteroidsDeepReinforcement","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"hmhuy0/SIM-RL","kind":"listed","samples":12,"ran":10,"instrument":4,"unverified":2},{"repo":"ifestus/rl","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"ikostrikov/pytorch-a2c-ppo-acktr-gail","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2210.03104"],"harvested_for_calls":[{"arxiv_id":"2210.03104","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.03104"},"call":"get_harvested_code_for_paper(arxiv_id=\"2210.03104\")"}]},{"repo":"ikostrikov/pytorch-rl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"inoryy/reaver","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1806.01830"],"harvested_for_calls":[{"arxiv_id":"1806.01830","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1806.01830"},"call":"get_harvested_code_for_paper(arxiv_id=\"1806.01830\")"}]},{"repo":"intellisys-lab/stellaris-sc24","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jcwleo/curiosity-driven-exploration-pytorch","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":"jcwleo/random-network-distillation-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1810.12894"],"harvested_for_calls":[{"arxiv_id":"1810.12894","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1810.12894"},"call":"get_harvested_code_for_paper(arxiv_id=\"1810.12894\")"}]},{"repo":"jfpettit/flare","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jhare96/reinforcement-learning","kind":"listed","samples":3,"ran":0,"instrument":0,"unverified":3},{"repo":"jongornet14/HyperController","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jsztompka/MultiAgent-PPO","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jsztompka/PPO-demo","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"juliusfrost/Research-Paper-Implementations","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jvidals09/Decentralized-and-multi-agent-control-of-Franka-Emika-Panda-robot-in-continuous-task-execution","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jw1401/PPO-Tensorflow-2.0","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ku2482/gail-airl-ppo.pytorch","kind":"listed","samples":8,"ran":6,"instrument":3,"unverified":2},{"repo":"lcswillems/torch-ac","kind":"listed","samples":4,"ran":1,"instrument":0,"unverified":3},{"repo":"lgerrets/rl18-curiosity","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"liuyuezhang/pyrl","kind":"listed","samples":3,"ran":1,"instrument":0,"unverified":2},{"repo":"liyiyuian/Deep-Learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"llSourcell/OpenAI_Five_vs_Dota2_Explained","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"mark-gluzman/NmodelPPO","kind":"listed","samples":3,"ran":3,"instrument":1,"unverified":0,"placed_by_identical_code":1},{"repo":"marload/DeepRL-TensorFlow2","kind":"listed","samples":3,"ran":0,"instrument":0,"unverified":3},{"repo":"michael-snower/ppo","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1803.02811"],"harvested_for_calls":[{"arxiv_id":"1803.02811","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1803.02811"},"call":"get_harvested_code_for_paper(arxiv_id=\"1803.02811\")"}]},{"repo":"microsoft/strategically_efficient_rl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1810.12894"],"harvested_for_calls":[{"arxiv_id":"1810.12894","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1810.12894"},"call":"get_harvested_code_for_paper(arxiv_id=\"1810.12894\")"}]},{"repo":"mightypirate1/PPO_homebrew","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"miroblog/tf_deep_rl_trader","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"mit-realm/neuriss","kind":"listed","samples":12,"ran":8,"instrument":5,"unverified":4},{"repo":"montaserFath/Reinforcement-Learning-for-Prosthetics","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"morikatron/GAIL_PPO","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"morikatron/PPO","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"near32/regym","kind":"listed","samples":3,"ran":3,"instrument":1,"unverified":0},{"repo":"nikhilbarhate99/PPO","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"nikhilbarhate99/PPO-PyTorch","kind":"listed","samples":3,"ran":3,"instrument":0,"unverified":0},{"repo":"nitthilan/pommerman","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"nric/ProximalPolicyOptimizationContinuousKeras","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"nvlabs/gbrl_sb3","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"openpsi-projects/srl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"reinforcement-learning-kr/pg_travel","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"rshnn/battleship","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"s-sd/task-amenability","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"saschaschramm/Pong","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"sc2crazy/StarCrackRL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"seungjaeryanlee/osim-rl-helper","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"shiningsunnyday/mcts-chess","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"shreyesss/PPO-implementation-keras-tensorflow","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"shuishida/soaprl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"siddharthverma314/proximalpolicyoptimization","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"silvialuu/DRL-2018","kind":"listed","samples":3,"ran":2,"instrument":1,"unverified":1},{"repo":"sirakik/mprg_fc","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sirakik/ppo_football","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"synthlabsai/big-math","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2502.17387"],"harvested_for_calls":[{"arxiv_id":"2502.17387","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.17387"},"call":"get_harvested_code_for_paper(arxiv_id=\"2502.17387\")"}]},{"repo":"taku-y/20181125-pybullet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"takuseno/ppo","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tatsu-lab/linguistic_calibration","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2305.14251"],"harvested_for_calls":[{"arxiv_id":"2305.14251","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.14251"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.14251\")"}]},{"repo":"tcmxx/CNTKUnityTools","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tensorlayer/RLzoo","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"theresearchai/vehicle_routing_rl_2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1803.08475"],"harvested_for_calls":[{"arxiv_id":"1803.08475","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1803.08475"},"call":"get_harvested_code_for_paper(arxiv_id=\"1803.08475\")"}]},{"repo":"tidedra/vl-rlhf","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2025.naacl-long.447"],"harvested_for_calls":[]},{"repo":"tilkb/thermoai","kind":"listed","samples":2,"ran":2,"instrument":1,"unverified":0},{"repo":"tmjeong1103/RL_with_RAY","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1801.01290"],"harvested_for_calls":[{"arxiv_id":"1801.01290","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1801.01290"},"call":"get_harvested_code_for_paper(arxiv_id=\"1801.01290\")"}]},{"repo":"tobiasemrich/SchafkopfRL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tommyvsfu1/RL-NTU","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"tuanpnm99/RLPongAgent","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"uvipen/super-mario-bros-ppo-pytorch","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"vcadillog/PPO-Mario-Bros-Tensorflow-2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"vermashresth/damage-aware-PPO","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"vheuthe/microbot_rl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"wangshub/RL-Stock","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"wangzhengfei0730/NIPS2018-AIforProsthetics","kind":"listed","samples":4,"ran":1,"instrument":0,"unverified":3},{"repo":"xiawenwen49/ppo","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"xtma/simple-pytorch-rl","kind":"listed","samples":3,"ran":2,"instrument":0,"unverified":1},{"repo":"yoavalon/Quadcopter-env","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"yoavalon/QuadcopterReinforcementLearning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"zjlab-ammi/llm4rl","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"zsz-hst/RL_single_chase_point","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"BIT-aerial-robotics/AquaML","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"DLR-RM/stable-baselines3","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2603.01771"],"harvested_for_calls":[{"arxiv_id":"2603.01771","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2603.01771"},"call":"get_harvested_code_for_paper(arxiv_id=\"2603.01771\")"}]},{"repo":"DevSlem/AINE-DRL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Ipsedo/EvoMotion","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MaximeVandegar/Papers-in-100-Lines-of-Code","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"OctopusMind/RLHF_PPO","kind":"listed","samples":3,"ran":1,"instrument":0,"unverified":2},{"repo":"arnomoonens/yarll","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"repo":"dyabel/handson_rl","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0},{"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":"labmlai/annotated_deep_learning_paper_implementations","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":15,"harvested_for":["1312.5602","1412.6980","1502.03167","1505.04597","1511.05952","1511.06434","1710.10903","1803.08494","1904.09751","2104.09864","2105.14491","2106.09685","2112.04426","2112.10752","2305.14342"],"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":"1412.6980","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1412.6980"},"call":"get_harvested_code_for_paper(arxiv_id=\"1412.6980\")"},{"arxiv_id":"1502.03167","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1502.03167"},"call":"get_harvested_code_for_paper(arxiv_id=\"1502.03167\")"},{"arxiv_id":"1505.04597","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1505.04597"},"call":"get_harvested_code_for_paper(arxiv_id=\"1505.04597\")"},{"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":"1511.06434","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1511.06434"},"call":"get_harvested_code_for_paper(arxiv_id=\"1511.06434\")"},{"arxiv_id":"1710.10903","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1710.10903"},"call":"get_harvested_code_for_paper(arxiv_id=\"1710.10903\")"},{"arxiv_id":"1803.08494","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1803.08494"},"call":"get_harvested_code_for_paper(arxiv_id=\"1803.08494\")"},{"arxiv_id":"1904.09751","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1904.09751"},"call":"get_harvested_code_for_paper(arxiv_id=\"1904.09751\")"},{"arxiv_id":"2104.09864","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.09864"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.09864\")"},{"arxiv_id":"2105.14491","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.14491"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.14491\")"},{"arxiv_id":"2106.09685","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.09685"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.09685\")"},{"arxiv_id":"2112.04426","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2112.04426"},"call":"get_harvested_code_for_paper(arxiv_id=\"2112.04426\")"},{"arxiv_id":"2112.10752","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2112.10752"},"call":"get_harvested_code_for_paper(arxiv_id=\"2112.10752\")"},{"arxiv_id":"2305.14342","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.14342"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.14342\")"}]},{"repo":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"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":"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":"00400865900363be","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements the clipped surrogate objective function that is optimized in the PPO algorithm.","centrality":"contribution","entry":"proximal_policy_optimization_loss","entry_sha256":"063d29364d7e4f81","n_bricks":1,"bricks":[{"entry":"proximal_policy_optimization_loss","code_sha256":"063d29364d7e4f81","role":"entry","order":0,"level":1,"status":"ran_draft_wrong"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":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":"5114412eb471","n_siblings":63,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"0b569190b947297b","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper proposes Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent to improve sample efficiency and stability.","centrality":"contribution","entry":"PPO","entry_sha256":"1ebfd098cf241f3c","n_bricks":1,"bricks":[{"entry":"PPO","code_sha256":"1ebfd098cf241f3c","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"109fc2e17a7052a8","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization, which optimizes a clipped surrogate objective function using multiple epochs of minibatch updates.","centrality":"contribution","entry":"PPO_continuous","entry_sha256":"5dc5fc3b8ad0138c","n_bricks":12,"bricks":[{"entry":"PPO_continuous","code_sha256":"5dc5fc3b8ad0138c","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Algorithm","code_sha256":"d5c516ed0fa589e3","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"RolloutBuffer_PPO_lag","code_sha256":"6f986aa2d59a44f8","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"StateFunction","code_sha256":"a78ee4761e8df9d8","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"StateIndependentPolicy","code_sha256":"fbd28096c7f0c30f","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"calculate_gae","code_sha256":"b5a22b5e0dce3796","role":"helper","order":5,"level":1,"status":"ran_draft_wrong"},{"entry":"calculate_gae_cost","code_sha256":"77393baa1a11c24b","role":"helper","order":6,"level":1,"status":"ran_draft_wrong"},{"entry":"build_mlp","code_sha256":"c511268a73d82fc6","role":"helper","order":7,"level":1,"status":"ran_draft_wrong"},{"entry":"evaluate_lop_pi","code_sha256":"fef4ec37a6ea52e7","role":"helper","order":8,"level":1,"status":"ran_honours"},{"entry":"reparameterize","code_sha256":"b1c9c127240c75d8","role":"helper","order":9,"level":1,"status":"ran_draft_wrong"},{"entry":"atanh","code_sha256":"264c9e17d7dfe7eb","role":"helper","order":10,"level":1,"status":"ran_honours"},{"entry":"calculate_log_pi","code_sha256":"476e14ee8b7219ac","role":"helper","order":11,"level":1,"status":"ran_honours"}],"ran_individually":10,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3,"ran_draft_wrong":4,"ran_honours":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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"146971b78d6d66e3","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that alternates between sampling data and optimizing a surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"Agent","entry_sha256":"53db83baee745ffd","n_bricks":3,"bricks":[{"entry":"Agent","code_sha256":"53db83baee745ffd","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"54ccb8ae3f658c83","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"c004c93ba5634851","role":"model","order":2,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"220df86717f32d27","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims that Proximal Policy Optimization (PPO) alternates between sampling data and optimizing a 'surrogate' objective function using stochastic gradient ascent with a clipped objective to ensure stable policy updates.","centrality":"contribution","entry":"clipped_surrogate","entry_sha256":"9c65b36eec7ec92a","n_bricks":2,"bricks":[{"entry":"clipped_surrogate","code_sha256":"9c65b36eec7ec92a","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"states_to_prob","code_sha256":"a7700bf49f384087","role":"model","order":1,"level":1,"status":"ran_draft_wrong"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"2309588005c38e4c","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent while constraining policy updates to avoid large deviations.","centrality":"contribution","entry":"PPO","entry_sha256":"5954e04c0ee7d26e","n_bricks":1,"bricks":[{"entry":"PPO","code_sha256":"5954e04c0ee7d26e","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"2f16ac3e5516d290","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims a new family of policy gradient methods called Proximal Policy Optimization (PPO) that optimizes a surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"Agent","entry_sha256":"b1f30e180cb81a3a","n_bricks":4,"bricks":[{"entry":"Agent","code_sha256":"b1f30e180cb81a3a","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"ActorCritic","code_sha256":"f7a59411ac390f78","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"e9f1207fc08f9fa9","role":"model","order":2,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"b4455ab1f545ae9c","role":"model","order":3,"level":1,"status":"ran"}],"ran_individually":4,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"326783669afd99bb","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims a new family of policy gradient methods (PPO) that optimizes a surrogate objective function using stochastic gradient ascent, implemented here as a reinforcement learning agent with a policy network and an Adam optimizer.","centrality":"contribution","entry":"PongAgent","entry_sha256":"40f05c72bfe4c048","n_bricks":2,"bricks":[{"entry":"PongAgent","code_sha256":"40f05c72bfe4c048","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Policy","code_sha256":"c02c0631708465dc","role":"model","order":1,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"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":"5114412eb471","n_siblings":63,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"3275ac3cdce1720b","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper proposes Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent while interacting with the environment.","centrality":"contribution","entry":"Agent","entry_sha256":"f473685be4b59e7f","n_bricks":2,"bricks":[{"entry":"Agent","code_sha256":"f473685be4b59e7f","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"MemoryPPO","code_sha256":"75bc51af9c0cf574","role":"data_transform","order":1,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"35c17852d7b2f6e3","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"This code implements the Proximal Policy Optimization (PPO) algorithm, which alternates between sampling data from the environment and optimizing a clipped surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"PPO","entry_sha256":"b48c75c1f791937c","n_bricks":4,"bricks":[{"entry":"PPO","code_sha256":"b48c75c1f791937c","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"PolicyUpdate","code_sha256":"2eb0c930a45a7472","role":"update_rule","order":1,"level":1,"status":"ran"},{"entry":"ppo_loss","code_sha256":"2c9a98eedcdea762","role":"loss","order":2,"level":0,"status":"unverified"},{"entry":"ModelUpdate","code_sha256":"7f143a6ee276436b","role":"helper","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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"3ab0156ebf261111","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent while constraining policy updates to avoid destructive large updates.","centrality":"contribution","entry":"PPOalgorithm","entry_sha256":"bce2a8566fa36fda","n_bricks":1,"bricks":[{"entry":"PPOalgorithm","code_sha256":"bce2a8566fa36fda","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"3be003ba3ca03d94","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims a new family of policy gradient methods that optimize a surrogate objective function using stochastic gradient ascent to improve reinforcement learning performance.","centrality":"contribution","entry":"PPOAgent","entry_sha256":"01b7328f523d7756","n_bricks":4,"bricks":[{"entry":"PPOAgent","code_sha256":"01b7328f523d7756","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"bf0c1da602f8a16d","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"708e869097ea91ff","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"gaussian_likelihood","code_sha256":"b46c632bedd3d8af","role":"helper","order":3,"level":1,"status":"ran_honours"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"3d1f2cc06035ea0a","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent with clipped probability ratios to ensure stable updates.","centrality":"contribution","entry":"learn","entry_sha256":"be674cc9da531aa5","n_bricks":7,"bricks":[{"entry":"learn","code_sha256":"be674cc9da531aa5","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Model","code_sha256":"14b4f65f714ccf75","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"Runner","code_sha256":"c80e9a362666d32e","role":"sampler","order":2,"level":1,"status":"ran"},{"entry":"constfn","code_sha256":"8758308dc6c0727f","role":"helper","order":3,"level":1,"status":"ran_draft_wrong"},{"entry":"safemean","code_sha256":"a7b323241cd70612","role":"metric","order":4,"level":1,"status":"ran_honours"},{"entry":"AbstractEnvRunner","code_sha256":"5b125d5154c21cbf","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"sf01","code_sha256":"baf2a28d376d7803","role":"data_transform","order":6,"level":1,"status":"ran_violates"}],"ran_individually":4,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1,"ran_draft_wrong":1,"ran_honours":1,"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"4001252face0416d","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent while constraining policy updates to avoid destructive large updates.","centrality":"contribution","entry":"Model","entry_sha256":"a9432edcc1976925","n_bricks":2,"bricks":[{"entry":"Model","code_sha256":"a9432edcc1976925","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"sample","code_sha256":"6b56455d8ddd9bf1","role":"sampler","order":1,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"44d8b39d2fb476c9","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"This function implements the clipped surrogate objective function central to Proximal Policy Optimization (PPO), which alternates between sampling data and optimizing this objective using stochastic gradient ascent.","centrality":"contribution","entry":"ppo_loss","entry_sha256":"0db440a845c6a4fa","n_bricks":1,"bricks":[{"entry":"ppo_loss","code_sha256":"0db440a845c6a4fa","role":"entry","order":0,"level":1,"status":"ran_honours"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"452ce971591430ce","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a family of policy gradient methods that alternates between sampling data and optimizing a surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"PPO","entry_sha256":"578c10d4e2b66073","n_bricks":3,"bricks":[{"entry":"PPO","code_sha256":"578c10d4e2b66073","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Categorical","code_sha256":"cc0a6d60ba0d615d","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Continous","code_sha256":"1e06bd08fb825800","role":"model","order":2,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"484ddcf0d4356b8c","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"Agent","entry_sha256":"4c40cb5849fd342f","n_bricks":4,"bricks":[{"entry":"Agent","code_sha256":"4c40cb5849fd342f","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"ActorCritic","code_sha256":"607bb439a428fd2a","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Actor","code_sha256":"8fc0ce07edd32744","role":"model","order":2,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"b4455ab1f545ae9c","role":"model","order":3,"level":1,"status":"ran"}],"ran_individually":4,"ran_individually_constructed":4,"ran_individually_by_status":{"ran":4},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"4ce5af77fa6f4833","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements the Proximal Policy Optimization (PPO) surrogate objective function, which alternates between sampling data and optimizing a clipped surrogate objective using stochastic gradient ascent.","centrality":"contribution","entry":"surrogate_loss","entry_sha256":"6647017115e92ee7","n_bricks":1,"bricks":[{"entry":"surrogate_loss","code_sha256":"6647017115e92ee7","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"4dc0f5bbcea8f6cb","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent to improve sample efficiency and stability.","centrality":"contribution","entry":"PPO","entry_sha256":"ded7302e103e8dd7","n_bricks":12,"bricks":[{"entry":"PPO","code_sha256":"ded7302e103e8dd7","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Agent","code_sha256":"c3c2c245443da6e3","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"Env","code_sha256":"f5415970200a24b5","role":"helper","order":2,"level":0,"status":"unverified"},{"entry":"NormalizedMLP","code_sha256":"1271c934496f2b53","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"RolloutBuffer","code_sha256":"049dd1dd7386f7f1","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"StateIndependentPolicy","code_sha256":"4652f7766f254cc1","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"calculate_gae","code_sha256":"7e7afb47f6ebd451","role":"helper","order":6,"level":1,"status":"ran_draft_wrong"},{"entry":"MLP","code_sha256":"f2a4b483cf41dcfd","role":"helper","order":7,"level":1,"status":"ran"},{"entry":"evaluate_log_pi","code_sha256":"c977657d1b1dadef","role":"helper","order":8,"level":1,"status":"ran_draft_wrong"},{"entry":"reparameterize","code_sha256":"6741967893f01eac","role":"helper","order":9,"level":1,"status":"ran_draft_wrong"},{"entry":"init_param","code_sha256":"f2cddb5460e2bc7e","role":"helper","order":10,"level":1,"status":"ran_draft_wrong"},{"entry":"calculate_log_pi","code_sha256":"eb4a6cb62afcb0ec","role":"helper","order":11,"level":1,"status":"ran_draft_wrong"}],"ran_individually":8,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3,"ran_draft_wrong":5},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"4f2cdd5736c5ac05","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements the Proximal Policy Optimization algorithm that alternates between sampling data from environment interaction and optimizing a surrogate objective function.","centrality":"contribution","entry":"PPO","entry_sha256":"cb4776fdb4698c72","n_bricks":4,"bricks":[{"entry":"PPO","code_sha256":"cb4776fdb4698c72","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Actor","code_sha256":"c3cb4b39b7e82812","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Buffer","code_sha256":"5eac27c1ede5a3f1","role":"sampler","order":2,"level":1,"status":"ran"},{"entry":"Critic","code_sha256":"f1685211d6effd06","role":"model","order":3,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"545631e1506660a9","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"PPO","entry_sha256":"f7417c7ed09d5ade","n_bricks":2,"bricks":[{"entry":"PPO","code_sha256":"f7417c7ed09d5ade","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Critic","code_sha256":"f42b9cecada07086","role":"model","order":1,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"56dc80195a79d4ab","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization, a policy gradient method that alternates between sampling data and optimizing a surrogate objective function.","centrality":"contribution","entry":"train","entry_sha256":"f5d2e6057543255c","n_bricks":2,"bricks":[{"entry":"train","code_sha256":"f5d2e6057543255c","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ReplayMemory","code_sha256":"7539f57b4803c98e","role":"sampler","order":1,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"UNCLEAR","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":"5114412eb471","n_siblings":63,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"5c85085383d91168","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization (PPO), a novel policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent with clipped probability ratios to ensure stable updates.","centrality":"contribution","entry":"PPO","entry_sha256":"00bb1a30b070c324","n_bricks":1,"bricks":[{"entry":"PPO","code_sha256":"00bb1a30b070c324","role":"entry","order":0,"level":1,"status":"ran"}],"ran_individually":1,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"5e8e5bc0133684ff","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements the Proximal Policy Optimization (PPO) algorithm, which alternates between sampling data from the environment and optimizing a surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"PPOAlgo","entry_sha256":"dce583aa0f5fb136","n_bricks":7,"bricks":[{"entry":"PPOAlgo","code_sha256":"dce583aa0f5fb136","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"BaseAlgo","code_sha256":"6c7082241ec61d89","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"DictList","code_sha256":"28919ed273c0c995","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"ExtraInfoCollector","code_sha256":"06c62bb9eacfe08c","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"ParallelEnv","code_sha256":"f0b71d0c5374efdf","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"default_preprocess_obss","code_sha256":"1cd2e751ff91ca44","role":"helper","order":5,"level":1,"status":"ran_draft_wrong"},{"entry":"worker","code_sha256":"01571ae37dfefba2","role":"helper","order":6,"level":0,"status":"unverified"}],"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"5f670b9e0bff80cc","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization, a new family of policy gradient methods that optimizes a surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"PPO","entry_sha256":"1c8d1f046ceeaadf","n_bricks":2,"bricks":[{"entry":"PPO","code_sha256":"1c8d1f046ceeaadf","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Parameters","code_sha256":"8764b4ca6ce10aca","role":"helper","order":1,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"65fea45a5fbcf003","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent with clipped probability ratios to ensure stable updates.","centrality":"contribution","entry":"Agent","entry_sha256":"64930ee88e057fb9","n_bricks":3,"bricks":[{"entry":"Agent","code_sha256":"64930ee88e057fb9","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActorNet","code_sha256":"13b852ad71d18604","role":"model","order":1,"level":1,"status":"ran"},{"entry":"CriticNet","code_sha256":"1a18a57c9dbc3655","role":"model","order":2,"level":1,"status":"ran"}],"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"67465e0454ae1502","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization (PPO) with a clipped objective surrogate function to optimize policy gradients.","centrality":"contribution","entry":"PPO_CLIP","entry_sha256":"542d8a7c56874ec9","n_bricks":1,"bricks":[{"entry":"PPO_CLIP","code_sha256":"542d8a7c56874ec9","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"69dcc57ca900f4a9","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent while constraining policy updates to avoid destructive large updates.","centrality":"contribution","entry":"ppo_update","entry_sha256":"f20ab80cf000ba69","n_bricks":2,"bricks":[{"entry":"ppo_update","code_sha256":"f20ab80cf000ba69","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ppo_iter","code_sha256":"df1fd605b67498ef","role":"data_transform","order":1,"level":1,"status":"ran_draft_wrong"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"6c6488eaf07c5cd2","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent, with clipped probability ratios to ensure stable updates.","centrality":"contribution","entry":"PPO","entry_sha256":"cd66a006bca55706","n_bricks":11,"bricks":[{"entry":"PPO","code_sha256":"cd66a006bca55706","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Algorithm","code_sha256":"2bddf6daaed4d669","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"RolloutBuffer","code_sha256":"168b3d776129e246","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"StateFunction","code_sha256":"7f9dae876ba7e00b","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"StateIndependentPolicy","code_sha256":"dea2715df3f6a1e3","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"calculate_gae","code_sha256":"b5a22b5e0dce3796","role":"helper","order":5,"level":1,"status":"ran_draft_wrong"},{"entry":"build_mlp","code_sha256":"c511268a73d82fc6","role":"helper","order":6,"level":1,"status":"ran_draft_wrong"},{"entry":"evaluate_lop_pi","code_sha256":"1cfc11023c8784d6","role":"helper","order":7,"level":1,"status":"ran_draft_wrong"},{"entry":"reparameterize","code_sha256":"7c5e74bc668cf5cc","role":"helper","order":8,"level":1,"status":"ran_draft_wrong"},{"entry":"atanh","code_sha256":"264c9e17d7dfe7eb","role":"helper","order":9,"level":1,"status":"ran_honours"},{"entry":"calculate_log_pi","code_sha256":"b4f2ea8b3db73cea","role":"helper","order":10,"level":1,"status":"ran_draft_wrong"}],"ran_individually":9,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3,"ran_draft_wrong":5,"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"7b781a51dbdb10eb","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"PPO","entry_sha256":"ea96173e68302d60","n_bricks":1,"bricks":[{"entry":"PPO","code_sha256":"ea96173e68302d60","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"820466280dda9c76","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent while constraining policy updates to avoid large deviations.","centrality":"contribution","entry":"PPO","entry_sha256":"bd4134c19ff6f1eb","n_bricks":3,"bricks":[{"entry":"PPO","code_sha256":"bd4134c19ff6f1eb","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"ActorCritic","code_sha256":"bab8cee03856463f","role":"model","order":1,"level":1,"status":"ran"},{"entry":"RolloutBuffer","code_sha256":"22bcf7bc55b864b8","role":"sampler","order":2,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"83b8ef33e9af0b97","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims a new family of policy gradient methods called Proximal Policy Optimization (PPO) that optimizes a surrogate objective function using stochastic gradient ascent to improve sample efficiency and stability in reinforcement learning.","centrality":"contribution","entry":"PPOAlgo","entry_sha256":"108ec8df92e50f23","n_bricks":6,"bricks":[{"entry":"PPOAlgo","code_sha256":"108ec8df92e50f23","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"BaseAlgo","code_sha256":"deafc9726839a93c","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"DictList","code_sha256":"28919ed273c0c995","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"ParallelEnv","code_sha256":"028cd0cc569e4945","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"default_preprocess_obss","code_sha256":"1cd2e751ff91ca44","role":"helper","order":4,"level":1,"status":"ran_draft_wrong"},{"entry":"worker","code_sha256":"0a1d06fc0e7bba39","role":"helper","order":5,"level":0,"status":"unverified"}],"ran_individually":3,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2,"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"8693af6c0b7a4743","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements the Proximal Policy Optimization (PPO) algorithm, specifically the clipped surrogate objective function for policy gradient updates.","centrality":"contribution","entry":"proximal_policy_optimization_loss","entry_sha256":"2492441b222787d6","n_bricks":1,"bricks":[{"entry":"proximal_policy_optimization_loss","code_sha256":"2492441b222787d6","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"86bd407862da2411","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements the clipped surrogate objective function that is optimized using stochastic gradient ascent in PPO.","centrality":"contribution","entry":"clipped_surrogate","entry_sha256":"db1820f47853260b","n_bricks":2,"bricks":[{"entry":"clipped_surrogate","code_sha256":"db1820f47853260b","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"states_to_prob","code_sha256":"f8348c78f9a4c594","role":"helper","order":1,"level":1,"status":"ran_draft_wrong"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":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":"5114412eb471","n_siblings":63,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"8b3d19783f5c610b","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization, a policy gradient method that alternates between sampling data and optimizing a surrogate objective function using stochastic gradient ascent to improve sample efficiency and stability.","centrality":"contribution","entry":"PPO","entry_sha256":"20cf521175a91e97","n_bricks":2,"bricks":[{"entry":"PPO","code_sha256":"20cf521175a91e97","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Base","code_sha256":"9619638a806c794f","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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"8c140ab8c777ee63","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent with clipping to constrain policy updates.","centrality":"contribution","entry":"Policy","entry_sha256":"ec594f35cdf2f00e","n_bricks":3,"bricks":[{"entry":"Policy","code_sha256":"ec594f35cdf2f00e","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"PolicyNN","code_sha256":"06f3c47cdf2dd979","role":"model","order":1,"level":1,"status":"ran"},{"entry":"check_optimality","code_sha256":"54948e8edd9b8bc1","role":"metric","order":2,"level":1,"status":"ran_draft_wrong"}],"ran_individually":3,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2,"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"8d6590892a5b6996","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims a new family of policy gradient methods that optimize a clipped surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"PPO","entry_sha256":"3c7b55685f685987","n_bricks":9,"bricks":[{"entry":"PPO","code_sha256":"3c7b55685f685987","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"PPOConfig","code_sha256":"a247afb083cad9ff","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"PPOModel","code_sha256":"55d94edcf36e1447","role":"model","order":2,"level":0,"status":"unverified"},{"entry":"tonumpy","code_sha256":"ca8d4b1715a4e662","role":"helper","order":3,"level":1,"status":"ran_honours"},{"entry":"totorch","code_sha256":"3ab1bc57b4217bc7","role":"helper","order":4,"level":1,"status":"ran_draft_wrong"},{"entry":"totorch_many","code_sha256":"82f14c9f59ca7edc","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"ModelConfig","code_sha256":"12f3d1927fc20cf0","role":"helper","order":6,"level":1,"status":"ran"},{"entry":"Agent","code_sha256":"449ad938cfccea32","role":"helper","order":7,"level":0,"status":"unverified"},{"entry":"polynomial_sheduler","code_sha256":"a99332a9cc3b7293","role":"helper","order":8,"level":1,"status":"ran_draft_wrong"}],"ran_individually":5,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2,"ran_draft_wrong":2,"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"8d6fee5945f49846","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent while alternating between sampling data and updating the policy.","centrality":"contribution","entry":"PPO","entry_sha256":"7451a2c222e554d4","n_bricks":3,"bricks":[{"entry":"PPO","code_sha256":"7451a2c222e554d4","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ffNetwork","code_sha256":"37c11b4e769d359d","role":"model","order":1,"level":0,"status":"unverified"},{"entry":"valueNetwork","code_sha256":"887a93fefeaff1d2","role":"model","order":2,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"90c9b8afd1f6f185","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent to improve sample efficiency and stability.","centrality":"contribution","entry":"PPOAgent","entry_sha256":"e3bd893b00cce00e","n_bricks":4,"bricks":[{"entry":"PPOAgent","code_sha256":"e3bd893b00cce00e","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"BaseAgent","code_sha256":"38803d98e366da6d","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"Batcher","code_sha256":"6dbcf603fe9c4a6f","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"tensor","code_sha256":"03b48449f3d4d675","role":"helper","order":3,"level":1,"status":"ran_fixture"}],"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"93e3c144f2fcebec","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements the Proximal Policy Optimization (PPO) clipped objective loss function as proposed in the paper.","centrality":"contribution","entry":"ppo_clip_loss","entry_sha256":"942f9baf61103bea","n_bricks":1,"bricks":[{"entry":"ppo_clip_loss","code_sha256":"942f9baf61103bea","role":"entry","order":0,"level":1,"status":"ran_honours"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"95e7acfe51a56ff3","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"This function implements the PPO surrogate objective optimization using clipped probability ratios and multiple epochs of minibatch updates.","centrality":"contribution","entry":"ppo_update","entry_sha256":"76b542040b4e4fcf","n_bricks":3,"bricks":[{"entry":"ppo_update","code_sha256":"76b542040b4e4fcf","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"get_gae_advantage","code_sha256":"62a48793f7edb3af","role":"data_transform","order":1,"level":1,"status":"ran_draft_wrong"},{"entry":"get_reward_to_go","code_sha256":"356537802e7b2bdb","role":"data_transform","order":2,"level":1,"status":"ran_violates"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_draft_wrong":1,"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"963202faa4c5bea5","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization, a policy gradient method that optimizes a clipped surrogate objective function.","centrality":"contribution","entry":"PPOAlgorithm","entry_sha256":"08c8acc6b144eabd","n_bricks":3,"bricks":[{"entry":"PPOAlgorithm","code_sha256":"08c8acc6b144eabd","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Storage","code_sha256":"e626bd567c81f207","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"random_sample","code_sha256":"2439c728712b51ae","role":"helper","order":2,"level":1,"status":"ran_draft_wrong"}],"ran_individually":3,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2,"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"98f7bb203dda6920","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"PPOAgent","entry_sha256":"786ef0f1e1c69fc2","n_bricks":1,"bricks":[{"entry":"PPOAgent","code_sha256":"786ef0f1e1c69fc2","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":"UNCLEAR","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":"5114412eb471","n_siblings":63,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"9d8ce58b69147416","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent to improve sample efficiency and stability.","centrality":"contribution","entry":"PPO","entry_sha256":"6e26f9d72a957989","n_bricks":5,"bricks":[{"entry":"PPO","code_sha256":"6e26f9d72a957989","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"BaseAgent","code_sha256":"2dd687e050a61476","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"TrajectoryBuffer","code_sha256":"58ee12a76b1fd1a1","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"entropy","code_sha256":"1732d17d766f28da","role":"loss","order":3,"level":1,"status":"ran_draft_wrong"},{"entry":"Buffer","code_sha256":"6f2b092fd868a348","role":"helper","order":4,"level":0,"status":"unverified"}],"ran_individually":3,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2,"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"9dc95a3cfa84d169","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"This code implements the Proximal Policy Optimization (PPO) algorithm by constructing a training graph that alternates between sampling data and optimizing a surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"build_train","entry_sha256":"2e9e6b5586603bfb","n_bricks":1,"bricks":[{"entry":"build_train","code_sha256":"2e9e6b5586603bfb","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"aa2577adcf955e3d","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent while constraining policy updates to avoid large deviations.","centrality":"contribution","entry":"update","entry_sha256":"7271dace2360dd93","n_bricks":2,"bricks":[{"entry":"update","code_sha256":"7271dace2360dd93","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"_pick_batch","code_sha256":"a5b8d69558cb1833","role":"helper","order":1,"level":1,"status":"ran_draft_wrong"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ae803636ac0600a8","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims a new family of policy gradient methods that optimize a surrogate objective function using stochastic gradient ascent, specifically Proximal Policy Optimization (PPO).","centrality":"contribution","entry":"update","entry_sha256":"3e7bdf63d50d132e","n_bricks":2,"bricks":[{"entry":"update","code_sha256":"3e7bdf63d50d132e","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"_pick_batch","code_sha256":"a5b8d69558cb1833","role":"helper","order":1,"level":1,"status":"ran_draft_wrong"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"afcac13d8faac401","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"Implements the Proximal Policy Optimization (PPO) algorithm for reinforcement learning, using a surrogate objective function optimized via stochastic gradient ascent.","centrality":"contribution","entry":"PPO","entry_sha256":"e33afa03c0df2bff","n_bricks":2,"bricks":[{"entry":"PPO","code_sha256":"e33afa03c0df2bff","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"parallel_trajectory_collection","code_sha256":"f1449fb45454e326","role":"helper","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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"bb25dd31a314de78","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"This code implements the Proximal Policy Optimization (PPO) algorithm, which alternates between sampling data from the environment and optimizing a surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"PPO","entry_sha256":"86201a6180de4a09","n_bricks":12,"bricks":[{"entry":"PPO","code_sha256":"86201a6180de4a09","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Algorithm","code_sha256":"527acc6b195e3ec9","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"RolloutBuffer","code_sha256":"c169652ebc3cb1c4","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"StateFunction","code_sha256":"ab47bdba4f875268","role":"helper","order":3,"level":1,"status":"ran"},{"entry":"StateIndependentPolicy","code_sha256":"181b4202198be200","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"calculate_gae","code_sha256":"b5a22b5e0dce3796","role":"helper","order":5,"level":1,"status":"ran_draft_wrong"},{"entry":"build_mlp","code_sha256":"373bf1b3269456e9","role":"helper","order":6,"level":1,"status":"ran_draft_wrong"},{"entry":"evaluate_lop_pi","code_sha256":"1cfc11023c8784d6","role":"helper","order":7,"level":1,"status":"ran_draft_wrong"},{"entry":"evaluate_lop_pi_inf","code_sha256":"92227b56b34a423b","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":"atanh","code_sha256":"264c9e17d7dfe7eb","role":"helper","order":10,"level":1,"status":"ran_honours"},{"entry":"calculate_log_pi","code_sha256":"b4f2ea8b3db73cea","role":"helper","order":11,"level":1,"status":"ran_draft_wrong"}],"ran_individually":10,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3,"ran_draft_wrong":6,"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"be99ff2dc064352d","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper proposes a new family of policy gradient methods called Proximal Policy Optimization (PPO), which optimizes a surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"PPONetwork","entry_sha256":"7dbfda361c907b1e","n_bricks":1,"bricks":[{"entry":"PPONetwork","code_sha256":"7dbfda361c907b1e","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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"bf7a5807bc6decbb","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements a loss function for Proximal Policy Optimization (PPO) for continuous action spaces, which is a key component of the PPO algorithm proposed in the paper.","centrality":"contribution","entry":"proximal_policy_optimization_loss_continuous","entry_sha256":"a690a9a71794bce7","n_bricks":1,"bricks":[{"entry":"proximal_policy_optimization_loss_continuous","code_sha256":"a690a9a71794bce7","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"c31a1b29be6dccc4","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization (PPO), a novel policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent while alternating between sampling data and updating the policy.","centrality":"contribution","entry":"PPO","entry_sha256":"7af85bd3eff93a8f","n_bricks":1,"bricks":[{"entry":"PPO","code_sha256":"7af85bd3eff93a8f","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"c62f861f771b9563","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that alternates between sampling data from the environment and optimizing a surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"Agent","entry_sha256":"d196dcee4a5b1061","n_bricks":2,"bricks":[{"entry":"Agent","code_sha256":"d196dcee4a5b1061","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"init_weights","code_sha256":"c2f17acc73ce8ca9","role":"helper","order":1,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"c8b3266a6c71954e","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization (PPO), a new family of policy gradient methods that optimizes a surrogate objective function using stochastic gradient ascent with clipped probability ratios to ensure stable updates.","centrality":"contribution","entry":"PPO","entry_sha256":"ef96810753b59244","n_bricks":3,"bricks":[{"entry":"PPO","code_sha256":"ef96810753b59244","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActorCritic","code_sha256":"6ff581679958bf77","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Buffer","code_sha256":"d0735a6f70135e3f","role":"helper","order":2,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"c9442e5f1a3f07c0","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements the Proximal Policy Optimization (PPO) algorithm by updating the policy and value networks using clipped surrogate objectives and advantage estimation.","centrality":"contribution","entry":"ppo_step","entry_sha256":"f423e91c2339c824","n_bricks":1,"bricks":[{"entry":"ppo_step","code_sha256":"f423e91c2339c824","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ca966194ac6bde41","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements Proximal Policy Optimization (PPO), a family of policy gradient methods that optimizes a surrogate objective function using stochastic gradient ascent while alternating between sampling data and updating the policy.","centrality":"contribution","entry":"PPO","entry_sha256":"24ed6c73c85ddcca","n_bricks":1,"bricks":[{"entry":"PPO","code_sha256":"24ed6c73c85ddcca","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ce5631d908c867ec","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims a new family of policy gradient methods that optimize a surrogate objective function using stochastic gradient ascent to improve sample efficiency and stability in reinforcement learning.","centrality":"contribution","entry":"update","entry_sha256":"0b170016a5f01a6e","n_bricks":2,"bricks":[{"entry":"update","code_sha256":"0b170016a5f01a6e","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"_pick_batch","code_sha256":"a5b8d69558cb1833","role":"helper","order":1,"level":1,"status":"ran_draft_wrong"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"cf9f22ce8d9df0b1","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent with clipped probability ratios to ensure stable updates.","centrality":"contribution","entry":"PPO","entry_sha256":"6073c0994e65bae3","n_bricks":3,"bricks":[{"entry":"PPO","code_sha256":"6073c0994e65bae3","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActorCritic","code_sha256":"2f383d9f3f2f7b4f","role":"model","order":1,"level":1,"status":"ran"},{"entry":"Memory","code_sha256":"121aee63a1a24691","role":"sampler","order":2,"level":0,"status":"unverified"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d10b94a897b575c0","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims that Proximal Policy Optimization (PPO) implements a new family of policy gradient methods that optimize a surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"Policy","entry_sha256":"be3a23c2176d855c","n_bricks":3,"bricks":[{"entry":"Policy","code_sha256":"be3a23c2176d855c","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Mlp","code_sha256":"088783306dda80fe","role":"model","order":1,"level":1,"status":"ran"},{"entry":"init_layer","code_sha256":"375f0073f16726f9","role":"helper","order":2,"level":1,"status":"ran_draft_wrong"}],"ran_individually":3,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":2,"ran_draft_wrong":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":"5114412eb471","n_siblings":63,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"d2c6885423d4aecf","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"This code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent while constraining policy updates to avoid large deviations.","centrality":"contribution","entry":"PPO","entry_sha256":"df9fd7d088621b72","n_bricks":3,"bricks":[{"entry":"PPO","code_sha256":"df9fd7d088621b72","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Config","code_sha256":"593f887d35295a28","role":"helper","order":1,"level":0,"status":"unverified"},{"entry":"Tools","code_sha256":"63380712f9af778d","role":"helper","order":2,"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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"e1139e085618d3a6","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The paper claims this code implements a new family of policy gradient methods called Proximal Policy Optimization (PPO), which optimizes a surrogate objective function using stochastic gradient ascent.","centrality":"contribution","entry":"MyPPO","entry_sha256":"bb56e14071f60cba","n_bricks":1,"bricks":[{"entry":"MyPPO","code_sha256":"bb56e14071f60cba","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":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"e4bbf4ae4dbdaceb","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent while alternating between sampling data and updating the policy.","centrality":"contribution","entry":"PPOAgent","entry_sha256":"a01bf852d6ef518a","n_bricks":4,"bricks":[{"entry":"PPOAgent","code_sha256":"a01bf852d6ef518a","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"BaseAgent","code_sha256":"38803d98e366da6d","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"Batcher","code_sha256":"6dbcf603fe9c4a6f","role":"helper","order":2,"level":1,"status":"ran"},{"entry":"tensor","code_sha256":"8e103b8cabd1203c","role":"helper","order":3,"level":0,"status":"unverified"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"ea8574b6125d04b0","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent with clipped probability ratios to ensure stable updates.","centrality":"contribution","entry":"PPO","entry_sha256":"f51a9f6b2ca368d9","n_bricks":2,"bricks":[{"entry":"PPO","code_sha256":"f51a9f6b2ca368d9","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ActorCritic","code_sha256":"d068adb7cb463c20","role":"model","order":1,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"f2c646ce0523c173","source_kind":"harvested","method_name":"Proximal Policy Optimization (PPO)","realizes_method":"Proximal Policy Optimization (PPO)","graph_method":"Proximal Policy Optimization (PPO)","realizes_severed":false,"claim":"The code implements Proximal Policy Optimization (PPO), a policy gradient method that optimizes a surrogate objective function using stochastic gradient ascent while interacting with the environment.","centrality":"contribution","entry":"PPO_lunarlander","entry_sha256":"48d2039b794ca629","n_bricks":1,"bricks":[{"entry":"PPO_lunarlander","code_sha256":"48d2039b794ca629","role":"entry","order":0,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"5114412eb471","n_siblings":63,"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":"5114412eb471","realizes_method":"Proximal Policy Optimization (PPO)","source_kind":"harvested","batch_at":"2026-09-09T22:44:46+00:00","members":["00400865900363be","0b569190b947297b","109fc2e17a7052a8","146971b78d6d66e3","220df86717f32d27","2309588005c38e4c","2f16ac3e5516d290","326783669afd99bb","3275ac3cdce1720b","35c17852d7b2f6e3","3ab0156ebf261111","3be003ba3ca03d94","3d1f2cc06035ea0a","4001252face0416d","44d8b39d2fb476c9","452ce971591430ce","484ddcf0d4356b8c","4ce5af77fa6f4833","4dc0f5bbcea8f6cb","4f2cdd5736c5ac05","545631e1506660a9","56dc80195a79d4ab","5c85085383d91168","5e8e5bc0133684ff","5f670b9e0bff80cc","65fea45a5fbcf003","67465e0454ae1502","69dcc57ca900f4a9","6c6488eaf07c5cd2","7b781a51dbdb10eb","820466280dda9c76","83b8ef33e9af0b97","8693af6c0b7a4743","86bd407862da2411","8b3d19783f5c610b","8c140ab8c777ee63","8d6590892a5b6996","8d6fee5945f49846","90c9b8afd1f6f185","93e3c144f2fcebec","95e7acfe51a56ff3","963202faa4c5bea5","98f7bb203dda6920","9d8ce58b69147416","9dc95a3cfa84d169","aa2577adcf955e3d","ae803636ac0600a8","afcac13d8faac401","bb25dd31a314de78","be99ff2dc064352d","bf7a5807bc6decbb","c31a1b29be6dccc4","c62f861f771b9563","c8b3266a6c71954e","c9442e5f1a3f07c0","ca966194ac6bde41","ce5631d908c867ec","cf9f22ce8d9df0b1","d10b94a897b575c0","d2c6885423d4aecf","e1139e085618d3a6","e4bbf4ae4dbdaceb","ea8574b6125d04b0","f2c646ce0523c173"]}],"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":"1707.06347"},"call":"assembly(arxiv_id=\"1707.06347\")"},"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/1707.06347.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/1707.06347.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/lcswillems/torch-ac","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DLR-RM/stable-baselines3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Khrylx/PyTorch-RL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jfpettit/flare","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sc2crazy/StarCrackRL","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/intellisys-lab/stellaris-sc24","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gaetanserre/l2rpn-2022_ppo-baseline","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/Horizon","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/benevolentAI/guacamol_baselines","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/clwainwright/proximal_policy_optimization","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LuEE-C/PPO-Keras","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jsztompka/MultiAgent-PPO","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nikhilbarhate99/PPO","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Proximal_Policy_Optimization_Algorithms","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/170928/-Review-Proximal-Policy-Optimization-Algorithms","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JL321/Proximal-Policy-Optimization","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexbaumi/PPO-Algorithms","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nvlabs/gbrl_sb3","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/s-sd/task-amenability","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shuishida/soaprl","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zjlab-ammi/llm4rl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tobiasemrich/SchafkopfRL","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guofeng201507/ISA-IPA-2020-05-05-IS1PT-GRP-High5-StockTrading","reach":{"status":"unanswered"}}],"summary":{"ran":62,"ran_draft_wrong":27,"ran_honours":7,"ran_violates":2,"ran_fixture":1,"unverified":77},"n_samples":176,"n_ran":99,"n_constructed":53,"n_ran_checked":71,"n_instrument":28,"n_unverified":77,"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":173,"ran":96,"n_ran_checked":69,"n_instrument":27,"repositories":64},"unlocated":{"samples":3,"ran":3,"n_ran_checked":2,"n_instrument":1,"repositories":0,"is":"identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded"}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":94,"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":97,"n_ran_without_level_date":2,"n_ran_signature_not_shown":13,"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","census_is":"Syntology's function-name census ran implementations with this entry name on one shared input per bucket (the positional rank, kind and dtype of each array argument) and counted the distinct output digests (sha256 of the output rounded to 6 decimals). implementations and papers count the compared samples; distinct_outputs counts digests across all buckets; n_buckets is how many shared inputs were used. It is not a statement that any two samples compute one thing, and the name is a string, not an identity.","samples":[{"code_sha256":"e9f1207fc08f9fa9","code_sha256_prefix":"e9f1207fc08f9fa9","entry":"Actor","repo":"bonniesjli/PPO-Reacher_UnityML","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/bonniesjli/PPO-Reacher_UnityML/blob/HEAD/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":"e9f1207fc08f9fa9"},"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, bonniesjli/PPO-Reacher_UnityML when it was checked","mcp_get_code":{"code_sha256":"e9f1207fc08f9fa9"}},{"code_sha256":"8fc0ce07edd32744","code_sha256_prefix":"8fc0ce07edd32744","entry":"Actor","repo":"bonniesjli/PPO_Reacher","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/bonniesjli/PPO_Reacher/blob/HEAD/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":"8fc0ce07edd32744"},"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, bonniesjli/PPO_Reacher when it was checked","mcp_get_code":{"code_sha256":"8fc0ce07edd32744"}},{"code_sha256":"c3cb4b39b7e82812","code_sha256_prefix":"c3cb4b39b7e82812","entry":"Actor","repo":"Gregory-Eales/proximal-policy-optimization","repo_kind":"listed","path":"ppo/modules/ppo.py","file_url":"https://github.com/Gregory-Eales/proximal-policy-optimization/blob/HEAD/ppo/modules/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"Actor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/actor","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c3cb4b39b7e82812"}},{"code_sha256":"f7a59411ac390f78","code_sha256_prefix":"f7a59411ac390f78","entry":"ActorCritic","repo":"bonniesjli/PPO-Reacher_UnityML","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/bonniesjli/PPO-Reacher_UnityML/blob/HEAD/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":"ActorCritic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"f7a59411ac390f78"},"code_page":"/code/actorcritic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, bonniesjli/PPO-Reacher_UnityML when it was checked","mcp_get_code":{"code_sha256":"f7a59411ac390f78"}},{"code_sha256":"607bb439a428fd2a","code_sha256_prefix":"607bb439a428fd2a","entry":"ActorCritic","repo":"bonniesjli/PPO_Reacher","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/bonniesjli/PPO_Reacher/blob/HEAD/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":"ActorCritic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"607bb439a428fd2a"},"code_page":"/code/actorcritic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, bonniesjli/PPO_Reacher when it was checked","mcp_get_code":{"code_sha256":"607bb439a428fd2a"}},{"code_sha256":"bab8cee03856463f","code_sha256_prefix":"bab8cee03856463f","entry":"ActorCritic","repo":"nikhilbarhate99/PPO-PyTorch","repo_kind":"listed","path":"PPO.py","file_url":"https://github.com/nikhilbarhate99/PPO-PyTorch/blob/HEAD/PPO.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":"ActorCritic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/actorcritic","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"bab8cee03856463f"}},{"code_sha256":"6ff581679958bf77","code_sha256_prefix":"6ff581679958bf77","entry":"ActorCritic","repo":"bay3s/ppo-rl","repo_kind":"listed","path":"src/ppo/ppo.py","file_url":"https://github.com/bay3s/ppo-rl/blob/HEAD/src/ppo/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"state:Tensor/2/float, action:Tensor/1/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"6ff581679958bf77"},"code_page":"/code/actorcritic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, bay3s/ppo-rl when it was checked","mcp_get_code":{"code_sha256":"6ff581679958bf77"}},{"code_sha256":"2f383d9f3f2f7b4f","code_sha256_prefix":"2f383d9f3f2f7b4f","entry":"ActorCritic","repo":"liuyuezhang/pyrl","repo_kind":"listed","path":"ppo/agent.py","file_url":"https://github.com/liuyuezhang/pyrl/blob/HEAD/ppo/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"x:Tensor/2/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"2f383d9f3f2f7b4f"},"code_page":"/code/actorcritic","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2f383d9f3f2f7b4f"}},{"code_sha256":"13b852ad71d18604","code_sha256_prefix":"13b852ad71d18604","entry":"ActorNet","repo":"xtma/simple-pytorch-rl","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/xtma/simple-pytorch-rl/blob/HEAD/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"x:Tensor/2/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"13b852ad71d18604"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xtma/simple-pytorch-rl when it was checked","mcp_get_code":{"code_sha256":"13b852ad71d18604"}},{"code_sha256":"b1f30e180cb81a3a","code_sha256_prefix":"b1f30e180cb81a3a","entry":"Agent","repo":"bonniesjli/PPO-Reacher_UnityML","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/bonniesjli/PPO-Reacher_UnityML/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Agent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, bonniesjli/PPO-Reacher_UnityML when it was checked","mcp_get_code":{"code_sha256":"b1f30e180cb81a3a"}},{"code_sha256":"4c40cb5849fd342f","code_sha256_prefix":"4c40cb5849fd342f","entry":"Agent","repo":"bonniesjli/PPO_Reacher","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/bonniesjli/PPO_Reacher/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Agent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, bonniesjli/PPO_Reacher when it was checked","mcp_get_code":{"code_sha256":"4c40cb5849fd342f"}},{"code_sha256":"38803d98e366da6d","code_sha256_prefix":"38803d98e366da6d","entry":"BaseAgent","repo":"dmiu-shell/deeprl-shell","repo_kind":"listed","path":"deep_rl/agent/PPO_agent.py","file_url":"https://github.com/dmiu-shell/deeprl-shell/blob/HEAD/deep_rl/agent/PPO_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":"BaseAgent","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/baseagent","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"38803d98e366da6d"}},{"code_sha256":"6dbcf603fe9c4a6f","code_sha256_prefix":"6dbcf603fe9c4a6f","entry":"Batcher","repo":"dmiu-shell/deeprl-shell","repo_kind":"listed","path":"deep_rl/agent/PPO_agent.py","file_url":"https://github.com/dmiu-shell/deeprl-shell/blob/HEAD/deep_rl/agent/PPO_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":"Batcher","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":"6dbcf603fe9c4a6f"}},{"code_sha256":"5eac27c1ede5a3f1","code_sha256_prefix":"5eac27c1ede5a3f1","entry":"Buffer","repo":"Gregory-Eales/proximal-policy-optimization","repo_kind":"listed","path":"ppo/modules/ppo.py","file_url":"https://github.com/Gregory-Eales/proximal-policy-optimization/blob/HEAD/ppo/modules/ppo.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":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5eac27c1ede5a3f1"}},{"code_sha256":"d0735a6f70135e3f","code_sha256_prefix":"d0735a6f70135e3f","entry":"Buffer","repo":"bay3s/ppo-rl","repo_kind":"listed","path":"src/ppo/ppo.py","file_url":"https://github.com/bay3s/ppo-rl/blob/HEAD/src/ppo/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"transition:Transition/1/Tensor","fixture_out_type":"Transition","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, bay3s/ppo-rl when it was checked","mcp_get_code":{"code_sha256":"d0735a6f70135e3f"}},{"code_sha256":"cc0a6d60ba0d615d","code_sha256_prefix":"cc0a6d60ba0d615d","entry":"Categorical","repo":"JonasRSV/PPO","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/JonasRSV/PPO/blob/HEAD/ppo.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":"Categorical","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/categorical","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, JonasRSV/PPO when it was checked","mcp_get_code":{"code_sha256":"cc0a6d60ba0d615d"}},{"code_sha256":"1e06bd08fb825800","code_sha256_prefix":"1e06bd08fb825800","entry":"Continous","repo":"JonasRSV/PPO","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/JonasRSV/PPO/blob/HEAD/ppo.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":"Continous","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, JonasRSV/PPO when it was checked","mcp_get_code":{"code_sha256":"1e06bd08fb825800"}},{"code_sha256":"b4455ab1f545ae9c","code_sha256_prefix":"b4455ab1f545ae9c","entry":"Critic","repo":"bonniesjli/PPO-Reacher_UnityML","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/bonniesjli/PPO-Reacher_UnityML/blob/HEAD/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":"Critic","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"b4455ab1f545ae9c"},"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, bonniesjli/PPO-Reacher_UnityML when it was checked","mcp_get_code":{"code_sha256":"b4455ab1f545ae9c"}},{"code_sha256":"f1685211d6effd06","code_sha256_prefix":"f1685211d6effd06","entry":"Critic","repo":"Gregory-Eales/proximal-policy-optimization","repo_kind":"listed","path":"ppo/modules/ppo.py","file_url":"https://github.com/Gregory-Eales/proximal-policy-optimization/blob/HEAD/ppo/modules/ppo.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":"f1685211d6effd06"}},{"code_sha256":"1a18a57c9dbc3655","code_sha256_prefix":"1a18a57c9dbc3655","entry":"CriticNet","repo":"xtma/simple-pytorch-rl","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/xtma/simple-pytorch-rl/blob/HEAD/ppo.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":"CriticNet","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xtma/simple-pytorch-rl when it was checked","mcp_get_code":{"code_sha256":"1a18a57c9dbc3655"}},{"code_sha256":"28919ed273c0c995","code_sha256_prefix":"28919ed273c0c995","entry":"DictList","repo":"GiadaSimionato/Reasoning_Agents_2020","repo_kind":"listed","path":"babyai_rb/babyai/rl/algos/ppo.py","file_url":"https://github.com/GiadaSimionato/Reasoning_Agents_2020/blob/HEAD/babyai_rb/babyai/rl/algos/ppo.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":"DictList","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, GiadaSimionato/Reasoning_Agents_2020 when it was checked","mcp_get_code":{"code_sha256":"28919ed273c0c995"}},{"code_sha256":"06c62bb9eacfe08c","code_sha256_prefix":"06c62bb9eacfe08c","entry":"ExtraInfoCollector","repo":"GiadaSimionato/Reasoning_Agents_2020","repo_kind":"listed","path":"babyai_rb/babyai/rl/algos/ppo.py","file_url":"https://github.com/GiadaSimionato/Reasoning_Agents_2020/blob/HEAD/babyai_rb/babyai/rl/algos/ppo.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":"ExtraInfoCollector","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, GiadaSimionato/Reasoning_Agents_2020 when it was checked","mcp_get_code":{"code_sha256":"06c62bb9eacfe08c"}},{"code_sha256":"f2a4b483cf41dcfd","code_sha256_prefix":"f2a4b483cf41dcfd","entry":"MLP","repo":"mit-realm/neuriss","repo_kind":"listed","path":"neuriss/rl/ppo.py","file_url":"https://github.com/mit-realm/neuriss/blob/HEAD/neuriss/rl/ppo.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":"MLP","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/mlp","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f2a4b483cf41dcfd"}},{"code_sha256":"75bc51af9c0cf574","code_sha256_prefix":"75bc51af9c0cf574","entry":"MemoryPPO","repo":"nric/ProximalPolicyOptimizationContinuousKeras","repo_kind":"listed","path":"ppo_keras_continuous.py","file_url":"https://github.com/nric/ProximalPolicyOptimizationContinuousKeras/blob/HEAD/ppo_keras_continuous.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"MemoryPPO","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, nric/ProximalPolicyOptimizationContinuousKeras when it was checked","mcp_get_code":{"code_sha256":"75bc51af9c0cf574"}},{"code_sha256":"088783306dda80fe","code_sha256_prefix":"088783306dda80fe","entry":"Mlp","repo":"ASzot/ppo-pytorch","repo_kind":"listed","path":"model.py","file_url":"https://github.com/ASzot/ppo-pytorch/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"inputs: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":"088783306dda80fe"},"code_page":"/code/mlp-3","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"088783306dda80fe"}},{"code_sha256":"7f143a6ee276436b","code_sha256_prefix":"7f143a6ee276436b","entry":"ModelUpdate","repo":"Narsil/rl-baselines","repo_kind":"listed","path":"rl_baselines/ppo.py","file_url":"https://github.com/Narsil/rl-baselines/blob/HEAD/rl_baselines/ppo.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":"ModelUpdate","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, Narsil/rl-baselines when it was checked","mcp_get_code":{"code_sha256":"7f143a6ee276436b"}},{"code_sha256":"bb56e14071f60cba","code_sha256_prefix":"bb56e14071f60cba","entry":"MyPPO","repo":"BrianPulfer/PapersReimplementations","repo_kind":"listed","path":"src/rl/ppo/ppo.py","file_url":"https://github.com/BrianPulfer/PapersReimplementations/blob/HEAD/src/rl/ppo/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"x:Tensor/3/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"bb56e14071f60cba"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"bb56e14071f60cba"}},{"code_sha256":"1271c934496f2b53","code_sha256_prefix":"1271c934496f2b53","entry":"NormalizedMLP","repo":"mit-realm/neuriss","repo_kind":"listed","path":"neuriss/rl/ppo.py","file_url":"https://github.com/mit-realm/neuriss/blob/HEAD/neuriss/rl/ppo.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":"NormalizedMLP","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"1271c934496f2b53"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1271c934496f2b53"}},{"code_sha256":"1ebfd098cf241f3c","code_sha256_prefix":"1ebfd098cf241f3c","entry":"PPO","repo":"uvipen/super-mario-bros-ppo-pytorch","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/uvipen/super-mario-bros-ppo-pytorch/blob/HEAD/src/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":"PPO","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":"1ebfd098cf241f3c"}},{"code_sha256":"b48c75c1f791937c","code_sha256_prefix":"b48c75c1f791937c","entry":"PPO","repo":"Narsil/rl-baselines","repo_kind":"listed","path":"rl_baselines/ppo.py","file_url":"https://github.com/Narsil/rl-baselines/blob/HEAD/rl_baselines/ppo.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":"PPO","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, Narsil/rl-baselines when it was checked","mcp_get_code":{"code_sha256":"b48c75c1f791937c"}},{"code_sha256":"00bb1a30b070c324","code_sha256_prefix":"00bb1a30b070c324","entry":"PPO","repo":"dyabel/handson_rl","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/dyabel/handson_rl/blob/HEAD/ppo.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":"PPO","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, dyabel/handson_rl when it was checked","mcp_get_code":{"code_sha256":"00bb1a30b070c324"}},{"code_sha256":"bd4134c19ff6f1eb","code_sha256_prefix":"bd4134c19ff6f1eb","entry":"PPO","repo":"nikhilbarhate99/PPO-PyTorch","repo_kind":"listed","path":"PPO.py","file_url":"https://github.com/nikhilbarhate99/PPO-PyTorch/blob/HEAD/PPO.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":"PPO","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":"bd4134c19ff6f1eb"}},{"code_sha256":"20cf521175a91e97","code_sha256_prefix":"20cf521175a91e97","entry":"PPO","repo":"zjlab-ammi/llm4rl","repo_kind":"listed","path":"algos/ppo.py","file_url":"https://github.com/zjlab-ammi/llm4rl/blob/HEAD/algos/ppo.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":"PPO","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, zjlab-ammi/llm4rl when it was checked","mcp_get_code":{"code_sha256":"20cf521175a91e97"}},{"code_sha256":"6e26f9d72a957989","code_sha256_prefix":"6e26f9d72a957989","entry":"PPO","repo":"hamishs/JAX-RL","repo_kind":"listed","path":"src/jax_rl/algorithms/ppo.py","file_url":"https://github.com/hamishs/JAX-RL/blob/HEAD/src/jax_rl/algorithms/ppo.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":"PPO","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":"6e26f9d72a957989"}},{"code_sha256":"e33afa03c0df2bff","code_sha256_prefix":"e33afa03c0df2bff","entry":"PPO","repo":"tilkb/thermoai","repo_kind":"listed","path":"controller/RL/PPO.py","file_url":"https://github.com/tilkb/thermoai/blob/HEAD/controller/RL/PPO.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":"PPO","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, tilkb/thermoai when it was checked","mcp_get_code":{"code_sha256":"e33afa03c0df2bff"}},{"code_sha256":"e3bd893b00cce00e","code_sha256_prefix":"e3bd893b00cce00e","entry":"PPOAgent","repo":"dmiu-shell/deeprl-shell","repo_kind":"listed","path":"deep_rl/agent/PPO_agent.py","file_url":"https://github.com/dmiu-shell/deeprl-shell/blob/HEAD/deep_rl/agent/PPO_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":"PPOAgent","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":"e3bd893b00cce00e"}},{"code_sha256":"786ef0f1e1c69fc2","code_sha256_prefix":"786ef0f1e1c69fc2","entry":"PPOAgent","repo":"ifestus/rl","repo_kind":"listed","path":"policy_agents.py","file_url":"https://github.com/ifestus/rl/blob/HEAD/policy_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":"PPOAgent","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, ifestus/rl when it was checked","mcp_get_code":{"code_sha256":"786ef0f1e1c69fc2"}},{"code_sha256":"08c8acc6b144eabd","code_sha256_prefix":"08c8acc6b144eabd","entry":"PPOAlgorithm","repo":"near32/regym","repo_kind":"listed","path":"regym/rl_algorithms/algorithms/PPO/ppo.py","file_url":"https://github.com/near32/regym/blob/HEAD/regym/rl_algorithms/algorithms/PPO/ppo.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":"PPOAlgorithm","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":"08c8acc6b144eabd"}},{"code_sha256":"7dbfda361c907b1e","code_sha256_prefix":"7dbfda361c907b1e","entry":"PPONetwork","repo":"jsztompka/PPO-demo","repo_kind":"listed","path":"model.py","file_url":"https://github.com/jsztompka/PPO-demo/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"state:Tensor/2/float, action:NoneType/0/?","fixture_out_type":"dict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"7dbfda361c907b1e"},"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, jsztompka/PPO-demo when it was checked","mcp_get_code":{"code_sha256":"7dbfda361c907b1e"}},{"code_sha256":"f0b71d0c5374efdf","code_sha256_prefix":"f0b71d0c5374efdf","entry":"ParallelEnv","repo":"GiadaSimionato/Reasoning_Agents_2020","repo_kind":"listed","path":"babyai_rb/babyai/rl/algos/ppo.py","file_url":"https://github.com/GiadaSimionato/Reasoning_Agents_2020/blob/HEAD/babyai_rb/babyai/rl/algos/ppo.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":"ParallelEnv","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, GiadaSimionato/Reasoning_Agents_2020 when it was checked","mcp_get_code":{"code_sha256":"f0b71d0c5374efdf"}},{"code_sha256":"028cd0cc569e4945","code_sha256_prefix":"028cd0cc569e4945","entry":"ParallelEnv","repo":"lcswillems/torch-ac","repo_kind":"listed","path":"torch_ac/algos/ppo.py","file_url":"https://github.com/lcswillems/torch-ac/blob/HEAD/torch_ac/algos/ppo.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":"ParallelEnv","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":"028cd0cc569e4945"}},{"code_sha256":"c02c0631708465dc","code_sha256_prefix":"c02c0631708465dc","entry":"Policy","repo":"tuanpnm99/RLPongAgent","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/tuanpnm99/RLPongAgent/blob/HEAD/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":"Policy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/policy","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, tuanpnm99/RLPongAgent when it was checked","mcp_get_code":{"code_sha256":"c02c0631708465dc"}},{"code_sha256":"ec594f35cdf2f00e","code_sha256_prefix":"ec594f35cdf2f00e","entry":"Policy","repo":"mark-gluzman/NmodelPPO","repo_kind":"listed","path":"actor_utils.py","file_url":"https://github.com/mark-gluzman/NmodelPPO/blob/HEAD/actor_utils.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":"Policy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/policy","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, mark-gluzman/NmodelPPO when it was checked","mcp_get_code":{"code_sha256":"ec594f35cdf2f00e"}},{"code_sha256":"be3a23c2176d855c","code_sha256_prefix":"be3a23c2176d855c","entry":"Policy","repo":"ASzot/ppo-pytorch","repo_kind":"listed","path":"model.py","file_url":"https://github.com/ASzot/ppo-pytorch/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"inputs:Tensor/2/float, deterministic:bool/0/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"be3a23c2176d855c"},"code_page":"/code/policy","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"be3a23c2176d855c"}},{"code_sha256":"06f3c47cdf2dd979","code_sha256_prefix":"06f3c47cdf2dd979","entry":"PolicyNN","repo":"mark-gluzman/NmodelPPO","repo_kind":"listed","path":"actor_utils.py","file_url":"https://github.com/mark-gluzman/NmodelPPO/blob/HEAD/actor_utils.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":"PolicyNN","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, mark-gluzman/NmodelPPO when it was checked","mcp_get_code":{"code_sha256":"06f3c47cdf2dd979"}},{"code_sha256":"2eb0c930a45a7472","code_sha256_prefix":"2eb0c930a45a7472","entry":"PolicyUpdate","repo":"Narsil/rl-baselines","repo_kind":"listed","path":"rl_baselines/ppo.py","file_url":"https://github.com/Narsil/rl-baselines/blob/HEAD/rl_baselines/ppo.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":"PolicyUpdate","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, Narsil/rl-baselines when it was checked","mcp_get_code":{"code_sha256":"2eb0c930a45a7472"}},{"code_sha256":"7539f57b4803c98e","code_sha256_prefix":"7539f57b4803c98e","entry":"ReplayMemory","repo":"llSourcell/OpenAI_Five_vs_Dota2_Explained","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/llSourcell/OpenAI_Five_vs_Dota2_Explained/blob/HEAD/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"ReplayMemory","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/replaymemory","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7539f57b4803c98e"}},{"code_sha256":"049dd1dd7386f7f1","code_sha256_prefix":"049dd1dd7386f7f1","entry":"RolloutBuffer","repo":"mit-realm/neuriss","repo_kind":"listed","path":"neuriss/rl/ppo.py","file_url":"https://github.com/mit-realm/neuriss/blob/HEAD/neuriss/rl/ppo.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":"RolloutBuffer","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":"049dd1dd7386f7f1"}},{"code_sha256":"168b3d776129e246","code_sha256_prefix":"168b3d776129e246","entry":"RolloutBuffer","repo":"ku2482/gail-airl-ppo.pytorch","repo_kind":"listed","path":"gail_airl_ppo/algo/ppo.py","file_url":"https://github.com/ku2482/gail-airl-ppo.pytorch/blob/HEAD/gail_airl_ppo/algo/ppo.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":"RolloutBuffer","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":"168b3d776129e246"}},{"code_sha256":"22bcf7bc55b864b8","code_sha256_prefix":"22bcf7bc55b864b8","entry":"RolloutBuffer","repo":"nikhilbarhate99/PPO-PyTorch","repo_kind":"listed","path":"PPO.py","file_url":"https://github.com/nikhilbarhate99/PPO-PyTorch/blob/HEAD/PPO.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":"RolloutBuffer","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":"22bcf7bc55b864b8"}},{"code_sha256":"c169652ebc3cb1c4","code_sha256_prefix":"c169652ebc3cb1c4","entry":"RolloutBuffer","repo":"evieq01/oodil","repo_kind":"listed","path":"simulated_robot/gail_airl_ppo/algo/ppo.py","file_url":"https://github.com/evieq01/oodil/blob/HEAD/simulated_robot/gail_airl_ppo/algo/ppo.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":"RolloutBuffer","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":"c169652ebc3cb1c4"}},{"code_sha256":"6f986aa2d59a44f8","code_sha256_prefix":"6f986aa2d59a44f8","entry":"RolloutBuffer_PPO_lag","repo":"hmhuy0/SIM-RL","repo_kind":"listed","path":"Sources/algo/ppo.py","file_url":"https://github.com/hmhuy0/SIM-RL/blob/HEAD/Sources/algo/ppo.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":"RolloutBuffer_PPO_lag","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, hmhuy0/SIM-RL when it was checked","mcp_get_code":{"code_sha256":"6f986aa2d59a44f8"}},{"code_sha256":"c80e9a362666d32e","code_sha256_prefix":"c80e9a362666d32e","entry":"Runner","repo":"wangzhengfei0730/NIPS2018-AIforProsthetics","repo_kind":"listed","path":"baselines/ppo2/ppo2.py","file_url":"https://github.com/wangzhengfei0730/NIPS2018-AIforProsthetics/blob/HEAD/baselines/ppo2/ppo2.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":"Runner","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, wangzhengfei0730/NIPS2018-AIforProsthetics when it was checked","mcp_get_code":{"code_sha256":"c80e9a362666d32e"}},{"code_sha256":"a78ee4761e8df9d8","code_sha256_prefix":"a78ee4761e8df9d8","entry":"StateFunction","repo":"hmhuy0/SIM-RL","repo_kind":"listed","path":"Sources/algo/ppo.py","file_url":"https://github.com/hmhuy0/SIM-RL/blob/HEAD/Sources/algo/ppo.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":"StateFunction","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"a78ee4761e8df9d8"},"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, hmhuy0/SIM-RL when it was checked","mcp_get_code":{"code_sha256":"a78ee4761e8df9d8"}},{"code_sha256":"7f9dae876ba7e00b","code_sha256_prefix":"7f9dae876ba7e00b","entry":"StateFunction","repo":"ku2482/gail-airl-ppo.pytorch","repo_kind":"listed","path":"gail_airl_ppo/algo/ppo.py","file_url":"https://github.com/ku2482/gail-airl-ppo.pytorch/blob/HEAD/gail_airl_ppo/algo/ppo.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":"StateFunction","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"7f9dae876ba7e00b"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7f9dae876ba7e00b"}},{"code_sha256":"ab47bdba4f875268","code_sha256_prefix":"ab47bdba4f875268","entry":"StateFunction","repo":"evieq01/oodil","repo_kind":"listed","path":"simulated_robot/gail_airl_ppo/algo/ppo.py","file_url":"https://github.com/evieq01/oodil/blob/HEAD/simulated_robot/gail_airl_ppo/algo/ppo.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":"StateFunction","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"ab47bdba4f875268"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ab47bdba4f875268"}},{"code_sha256":"fbd28096c7f0c30f","code_sha256_prefix":"fbd28096c7f0c30f","entry":"StateIndependentPolicy","repo":"hmhuy0/SIM-RL","repo_kind":"listed","path":"Sources/algo/ppo.py","file_url":"https://github.com/hmhuy0/SIM-RL/blob/HEAD/Sources/algo/ppo.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":"StateIndependentPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"fbd28096c7f0c30f"},"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, hmhuy0/SIM-RL when it was checked","mcp_get_code":{"code_sha256":"fbd28096c7f0c30f"}},{"code_sha256":"dea2715df3f6a1e3","code_sha256_prefix":"dea2715df3f6a1e3","entry":"StateIndependentPolicy","repo":"ku2482/gail-airl-ppo.pytorch","repo_kind":"listed","path":"gail_airl_ppo/algo/ppo.py","file_url":"https://github.com/ku2482/gail-airl-ppo.pytorch/blob/HEAD/gail_airl_ppo/algo/ppo.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":"StateIndependentPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"dea2715df3f6a1e3"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"dea2715df3f6a1e3"}},{"code_sha256":"181b4202198be200","code_sha256_prefix":"181b4202198be200","entry":"StateIndependentPolicy","repo":"evieq01/oodil","repo_kind":"listed","path":"simulated_robot/gail_airl_ppo/algo/ppo.py","file_url":"https://github.com/evieq01/oodil/blob/HEAD/simulated_robot/gail_airl_ppo/algo/ppo.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":"StateIndependentPolicy","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"181b4202198be200"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"181b4202198be200"}},{"code_sha256":"e626bd567c81f207","code_sha256_prefix":"e626bd567c81f207","entry":"Storage","repo":"near32/regym","repo_kind":"listed","path":"regym/rl_algorithms/algorithms/PPO/ppo.py","file_url":"https://github.com/near32/regym/blob/HEAD/regym/rl_algorithms/algorithms/PPO/ppo.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":"Storage","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":"e626bd567c81f207"}},{"code_sha256":"63380712f9af778d","code_sha256_prefix":"63380712f9af778d","entry":"Tools","repo":"OctopusMind/RLHF_PPO","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/OctopusMind/RLHF_PPO/blob/HEAD/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"logits:Tensor/3/float, labels:Tensor/2/int","fixture_out_type":"Tensor","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":"63380712f9af778d"}},{"code_sha256":"58ee12a76b1fd1a1","code_sha256_prefix":"58ee12a76b1fd1a1","entry":"TrajectoryBuffer","repo":"hamishs/JAX-RL","repo_kind":"listed","path":"src/jax_rl/algorithms/ppo.py","file_url":"https://github.com/hamishs/JAX-RL/blob/HEAD/src/jax_rl/algorithms/ppo.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":"TrajectoryBuffer","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":"58ee12a76b1fd1a1"}},{"code_sha256":"a5b8d69558cb1833","code_sha256_prefix":"a5b8d69558cb1833","entry":"_pick_batch","repo":"Gouet/Acrobot-PPO","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/Gouet/Acrobot-PPO/blob/HEAD/ppo.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":"mini_batch_size:int/0/int, data:ndarray/2/float, batch_index:int/0/int, flat:bool/0/bool, shape:NoneType/0/?","fixture_out_type":"ndarray","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"a5b8d69558cb1833"},"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, Gouet/Acrobot-PPO when it was checked","mcp_get_code":{"code_sha256":"a5b8d69558cb1833"}},{"code_sha256":"264c9e17d7dfe7eb","code_sha256_prefix":"264c9e17d7dfe7eb","entry":"atanh","repo":"hmhuy0/SIM-RL","repo_kind":"listed","path":"Sources/algo/ppo.py","file_url":"https://github.com/hmhuy0/SIM-RL/blob/HEAD/Sources/algo/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/atanh","census":{"url":"/census/atanh","implementations":3,"papers":5,"distinct_outputs":2,"n_buckets":1,"bucket_key":[[2,"float","float32"]],"bucket_index":1,"bucket_label":"arg 1: rank 2, kind float, dtype float32"},"census_bucket_fragment":"bucket-1","licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hmhuy0/SIM-RL when it was checked","mcp_get_code":{"code_sha256":"264c9e17d7dfe7eb"}},{"code_sha256":"c511268a73d82fc6","code_sha256_prefix":"c511268a73d82fc6","entry":"build_mlp","repo":"hmhuy0/SIM-RL","repo_kind":"listed","path":"Sources/algo/ppo.py","file_url":"https://github.com/hmhuy0/SIM-RL/blob/HEAD/Sources/algo/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"Sequential","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/build-mlp","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hmhuy0/SIM-RL when it was checked","mcp_get_code":{"code_sha256":"c511268a73d82fc6"}},{"code_sha256":"373bf1b3269456e9","code_sha256_prefix":"373bf1b3269456e9","entry":"build_mlp","repo":"evieq01/oodil","repo_kind":"listed","path":"simulated_robot/gail_airl_ppo/algo/ppo.py","file_url":"https://github.com/evieq01/oodil/blob/HEAD/simulated_robot/gail_airl_ppo/algo/ppo.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":"input_dim:int/0/int, output_dim:int/0/int, hidden_units:list/1/int, hidden_activation:callable/0/?, output_activation:callable/0/?, dropout:float/0/float","fixture_out_type":"Sequential","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/build-mlp","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"373bf1b3269456e9"}},{"code_sha256":"b5a22b5e0dce3796","code_sha256_prefix":"b5a22b5e0dce3796","entry":"calculate_gae","repo":"hmhuy0/SIM-RL","repo_kind":"listed","path":"Sources/algo/ppo.py","file_url":"https://github.com/hmhuy0/SIM-RL/blob/HEAD/Sources/algo/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"values:Tensor/1/float, rewards:Tensor/1/float, dones:Tensor/1/float, next_values:Tensor/1/float, gamma:float/0/float, lambd:float/0/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"b5a22b5e0dce3796"},"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, hmhuy0/SIM-RL when it was checked","mcp_get_code":{"code_sha256":"b5a22b5e0dce3796"}},{"code_sha256":"7e7afb47f6ebd451","code_sha256_prefix":"7e7afb47f6ebd451","entry":"calculate_gae","repo":"mit-realm/neuriss","repo_kind":"listed","path":"neuriss/rl/ppo.py","file_url":"https://github.com/mit-realm/neuriss/blob/HEAD/neuriss/rl/ppo.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":"values:Tensor/1/float, rewards:Tensor/1/float, dones:Tensor/1/float, next_values:Tensor/1/float, gamma:float/0/float, lambd:float/0/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"7e7afb47f6ebd451"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7e7afb47f6ebd451"}},{"code_sha256":"77393baa1a11c24b","code_sha256_prefix":"77393baa1a11c24b","entry":"calculate_gae_cost","repo":"hmhuy0/SIM-RL","repo_kind":"listed","path":"Sources/algo/ppo.py","file_url":"https://github.com/hmhuy0/SIM-RL/blob/HEAD/Sources/algo/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"values:Tensor/1/float, rewards:Tensor/1/float, dones:Tensor/1/float, next_values:Tensor/1/float, gamma:float/0/float, lambd:float/0/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"77393baa1a11c24b"},"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, hmhuy0/SIM-RL when it was checked","mcp_get_code":{"code_sha256":"77393baa1a11c24b"}},{"code_sha256":"476e14ee8b7219ac","code_sha256_prefix":"476e14ee8b7219ac","entry":"calculate_log_pi","repo":"hmhuy0/SIM-RL","repo_kind":"listed","path":"Sources/algo/ppo.py","file_url":"https://github.com/hmhuy0/SIM-RL/blob/HEAD/Sources/algo/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"log_stds:Tensor/2/float, noises:Tensor/2/float, actions: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":"476e14ee8b7219ac"},"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, hmhuy0/SIM-RL when it was checked","mcp_get_code":{"code_sha256":"476e14ee8b7219ac"}},{"code_sha256":"eb4a6cb62afcb0ec","code_sha256_prefix":"eb4a6cb62afcb0ec","entry":"calculate_log_pi","repo":"mit-realm/neuriss","repo_kind":"listed","path":"neuriss/rl/ppo.py","file_url":"https://github.com/mit-realm/neuriss/blob/HEAD/neuriss/rl/ppo.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":"log_stds:Tensor/2/float, noises:Tensor/2/float, actions: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":"eb4a6cb62afcb0ec"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"eb4a6cb62afcb0ec"}},{"code_sha256":"b4f2ea8b3db73cea","code_sha256_prefix":"b4f2ea8b3db73cea","entry":"calculate_log_pi","repo":"ku2482/gail-airl-ppo.pytorch","repo_kind":"listed","path":"gail_airl_ppo/algo/ppo.py","file_url":"https://github.com/ku2482/gail-airl-ppo.pytorch/blob/HEAD/gail_airl_ppo/algo/ppo.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":"log_stds:Tensor/2/float, noises:Tensor/2/float, actions: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":"b4f2ea8b3db73cea"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b4f2ea8b3db73cea"}},{"code_sha256":"54948e8edd9b8bc1","code_sha256_prefix":"54948e8edd9b8bc1","entry":"check_optimality","repo":null,"repo_kind":"listed","path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"signature":"unscaled_obs:list/1/ndarray, actions:list/1/ndarray, file_name:str/0/str","fixture_out_type":"int","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"placed_by_identical_code":{"repo":"mark-gluzman/NmodelPPO","path":"actor_utils.py","file_url":"https://github.com/mark-gluzman/NmodelPPO/blob/HEAD/actor_utils.py","papers":["2008.01644"],"is":"identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own"},"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"54948e8edd9b8bc1"}},{"code_sha256":"8758308dc6c0727f","code_sha256_prefix":"8758308dc6c0727f","entry":"constfn","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"val:int/0/int","fixture_out_type":"function","code_page":"/code/constfn","census":null,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"8758308dc6c0727f"}},{"code_sha256":"1cd2e751ff91ca44","code_sha256_prefix":"1cd2e751ff91ca44","entry":"default_preprocess_obss","repo":"GiadaSimionato/Reasoning_Agents_2020","repo_kind":"listed","path":"babyai_rb/babyai/rl/algos/ppo.py","file_url":"https://github.com/GiadaSimionato/Reasoning_Agents_2020/blob/HEAD/babyai_rb/babyai/rl/algos/ppo.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":"obss:list/1/list, device:NoneType/0/?","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"1cd2e751ff91ca44"},"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, GiadaSimionato/Reasoning_Agents_2020 when it was checked","mcp_get_code":{"code_sha256":"1cd2e751ff91ca44"}},{"code_sha256":"1732d17d766f28da","code_sha256_prefix":"1732d17d766f28da","entry":"entropy","repo":"hamishs/JAX-RL","repo_kind":"listed","path":"src/jax_rl/algorithms/ppo.py","file_url":"https://github.com/hamishs/JAX-RL/blob/HEAD/src/jax_rl/algorithms/ppo.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":"dist:ArrayImpl/2/float, axis:int/0/int","fixture_out_type":"ArrayImpl","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"1732d17d766f28da"},"code_page":"/code/entropy","census":{"url":"/census/entropy","implementations":22,"papers":25,"distinct_outputs":16,"n_buckets":4,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1732d17d766f28da"}},{"code_sha256":"c977657d1b1dadef","code_sha256_prefix":"c977657d1b1dadef","entry":"evaluate_log_pi","repo":"mit-realm/neuriss","repo_kind":"listed","path":"neuriss/rl/ppo.py","file_url":"https://github.com/mit-realm/neuriss/blob/HEAD/neuriss/rl/ppo.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":"means:Tensor/2/float, log_stds:Tensor/2/float, actions: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":"c977657d1b1dadef"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c977657d1b1dadef"}},{"code_sha256":"fef4ec37a6ea52e7","code_sha256_prefix":"fef4ec37a6ea52e7","entry":"evaluate_lop_pi","repo":"hmhuy0/SIM-RL","repo_kind":"listed","path":"Sources/algo/ppo.py","file_url":"https://github.com/hmhuy0/SIM-RL/blob/HEAD/Sources/algo/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"means:Tensor/2/float, log_stds:Tensor/2/float, actions: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":"fef4ec37a6ea52e7"},"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, hmhuy0/SIM-RL when it was checked","mcp_get_code":{"code_sha256":"fef4ec37a6ea52e7"}},{"code_sha256":"1cfc11023c8784d6","code_sha256_prefix":"1cfc11023c8784d6","entry":"evaluate_lop_pi","repo":"ku2482/gail-airl-ppo.pytorch","repo_kind":"listed","path":"gail_airl_ppo/algo/ppo.py","file_url":"https://github.com/ku2482/gail-airl-ppo.pytorch/blob/HEAD/gail_airl_ppo/algo/ppo.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":"means:Tensor/2/float, log_stds:Tensor/2/float, actions: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":"1cfc11023c8784d6"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1cfc11023c8784d6"}},{"code_sha256":"92227b56b34a423b","code_sha256_prefix":"92227b56b34a423b","entry":"evaluate_lop_pi_inf","repo":"evieq01/oodil","repo_kind":"listed","path":"simulated_robot/gail_airl_ppo/algo/ppo.py","file_url":"https://github.com/evieq01/oodil/blob/HEAD/simulated_robot/gail_airl_ppo/algo/ppo.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":"means:Tensor/2/float, log_stds:Tensor/2/float, actions: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":"92227b56b34a423b"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"92227b56b34a423b"}},{"code_sha256":"b46c632bedd3d8af","code_sha256_prefix":"b46c632bedd3d8af","entry":"gaussian_likelihood","repo":"InSpaceAI/RL-Zoo","repo_kind":"listed","path":"PPO.py","file_url":"https://github.com/InSpaceAI/RL-Zoo/blob/HEAD/PPO.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"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","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, InSpaceAI/RL-Zoo when it was checked","mcp_get_code":{"code_sha256":"b46c632bedd3d8af"}},{"code_sha256":"62a48793f7edb3af","code_sha256_prefix":"62a48793f7edb3af","entry":"get_gae_advantage","repo":"silvialuu/DRL-2018","repo_kind":"listed","path":"es-ppo/ppo.py","file_url":"https://github.com/silvialuu/DRL-2018/blob/HEAD/es-ppo/ppo.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":"rewards:Tensor/2/float, values:Tensor/2/float, mask_n:Tensor/2/float, gamma:float/0/float, lam:float/0/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"62a48793f7edb3af"},"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, silvialuu/DRL-2018 when it was checked","mcp_get_code":{"code_sha256":"62a48793f7edb3af"}},{"code_sha256":"356537802e7b2bdb","code_sha256_prefix":"356537802e7b2bdb","entry":"get_reward_to_go","repo":"silvialuu/DRL-2018","repo_kind":"listed","path":"es-ppo/ppo.py","file_url":"https://github.com/silvialuu/DRL-2018/blob/HEAD/es-ppo/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"rewards:list/1/float, mask_n:list/1/float, gamma:float/0/float","fixture_out_type":"list","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"356537802e7b2bdb"},"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, silvialuu/DRL-2018 when it was checked","mcp_get_code":{"code_sha256":"356537802e7b2bdb"}},{"code_sha256":"375f0073f16726f9","code_sha256_prefix":"375f0073f16726f9","entry":"init_layer","repo":"ASzot/ppo-pytorch","repo_kind":"listed","path":"model.py","file_url":"https://github.com/ASzot/ppo-pytorch/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"m:callable/0/?","fixture_out_type":"Linear","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/init-layer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"375f0073f16726f9"}},{"code_sha256":"f2cddb5460e2bc7e","code_sha256_prefix":"f2cddb5460e2bc7e","entry":"init_param","repo":"mit-realm/neuriss","repo_kind":"listed","path":"neuriss/rl/ppo.py","file_url":"https://github.com/mit-realm/neuriss/blob/HEAD/neuriss/rl/ppo.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":"module:callable/0/?, gain:float/0/float","fixture_out_type":"SimpleModule","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":"f2cddb5460e2bc7e"}},{"code_sha256":"f1449fb45454e326","code_sha256_prefix":"f1449fb45454e326","entry":"parallel_trajectory_collection","repo":"tilkb/thermoai","repo_kind":"listed","path":"controller/RL/PPO.py","file_url":"https://github.com/tilkb/thermoai/blob/HEAD/controller/RL/PPO.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":"simulator:SimpleSimulator/0/?, actor_model:callable/0/?, count:int/0/int, min_value:float/0/float, max_value:float/0/float, sigma:float/0/float, init_step:int/0/int, gamma:float/0/float","fixture_out_type":"list","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, tilkb/thermoai when it was checked","mcp_get_code":{"code_sha256":"f1449fb45454e326"}},{"code_sha256":"942f9baf61103bea","code_sha256_prefix":"942f9baf61103bea","entry":"ppo_clip_loss","repo":"siddharthverma314/proximalpolicyoptimization","repo_kind":"listed","path":"src/ppo.py","file_url":"https://github.com/siddharthverma314/proximalpolicyoptimization/blob/HEAD/src/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"signature":"policy:callable/0/?, arc:MinimalArc/0/?, epsilon:float/0/float","fixture_out_type":"Tensor","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, siddharthverma314/proximalpolicyoptimization when it was checked","mcp_get_code":{"code_sha256":"942f9baf61103bea"}},{"code_sha256":"df1fd605b67498ef","code_sha256_prefix":"df1fd605b67498ef","entry":"ppo_iter","repo":"Ostyk/walk-bot","repo_kind":"listed","path":"v_pytorch/ppo_train.py","file_url":"https://github.com/Ostyk/walk-bot/blob/HEAD/v_pytorch/ppo_train.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":"states:Tensor/2/float, actions:Tensor/2/float, log_probs:Tensor/2/float, returns:Tensor/2/float, advantage:Tensor/2/float","fixture_out_type":"generator","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, Ostyk/walk-bot when it was checked","mcp_get_code":{"code_sha256":"df1fd605b67498ef"}},{"code_sha256":"0db440a845c6a4fa","code_sha256_prefix":"0db440a845c6a4fa","entry":"ppo_loss","repo":"arnomoonens/yarll","repo_kind":"listed","path":"yarll/agents/tf2/ppo/ppo.py","file_url":"https://github.com/arnomoonens/yarll/blob/HEAD/yarll/agents/tf2/ppo/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"old_logprob:EagerTensor/2/float, new_logprob:EagerTensor/2/float, epsilon:EagerTensor/0/float, advantage: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":"0db440a845c6a4fa"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0db440a845c6a4fa"}},{"code_sha256":"063d29364d7e4f81","code_sha256_prefix":"063d29364d7e4f81","entry":"proximal_policy_optimization_loss","repo":"CSautier/PongBot","repo_kind":"listed","path":"PongBot.py","file_url":"https://github.com/CSautier/PongBot/blob/HEAD/PongBot.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":"advantage:EagerTensor/2/float, old_prediction:EagerTensor/2/float","fixture_out_type":"function","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, CSautier/PongBot when it was checked","mcp_get_code":{"code_sha256":"063d29364d7e4f81"}},{"code_sha256":"2439c728712b51ae","code_sha256_prefix":"2439c728712b51ae","entry":"random_sample","repo":"near32/regym","repo_kind":"listed","path":"regym/rl_algorithms/algorithms/PPO/ppo.py","file_url":"https://github.com/near32/regym/blob/HEAD/regym/rl_algorithms/algorithms/PPO/ppo.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":"indices:ndarray/1/int, batch_size:int/0/int","fixture_out_type":"generator","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/random-sample","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2439c728712b51ae"}},{"code_sha256":"b1c9c127240c75d8","code_sha256_prefix":"b1c9c127240c75d8","entry":"reparameterize","repo":"hmhuy0/SIM-RL","repo_kind":"listed","path":"Sources/algo/ppo.py","file_url":"https://github.com/hmhuy0/SIM-RL/blob/HEAD/Sources/algo/ppo.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"means:Tensor/2/float, log_stds: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":"b1c9c127240c75d8"},"code_page":"/code/reparameterize","census":{"url":"/census/reparameterize","implementations":12,"papers":17,"distinct_outputs":5,"n_buckets":4,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hmhuy0/SIM-RL when it was checked","mcp_get_code":{"code_sha256":"b1c9c127240c75d8"}},{"code_sha256":"6741967893f01eac","code_sha256_prefix":"6741967893f01eac","entry":"reparameterize","repo":"mit-realm/neuriss","repo_kind":"listed","path":"neuriss/rl/ppo.py","file_url":"https://github.com/mit-realm/neuriss/blob/HEAD/neuriss/rl/ppo.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":"means:Tensor/2/float, log_stds: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":"6741967893f01eac"},"code_page":"/code/reparameterize","census":{"url":"/census/reparameterize","implementations":12,"papers":17,"distinct_outputs":5,"n_buckets":4,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6741967893f01eac"}},{"code_sha256":"7c5e74bc668cf5cc","code_sha256_prefix":"7c5e74bc668cf5cc","entry":"reparameterize","repo":"ku2482/gail-airl-ppo.pytorch","repo_kind":"listed","path":"gail_airl_ppo/algo/ppo.py","file_url":"https://github.com/ku2482/gail-airl-ppo.pytorch/blob/HEAD/gail_airl_ppo/algo/ppo.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":"means:Tensor/2/float, log_stds: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":"7c5e74bc668cf5cc"},"code_page":"/code/reparameterize","census":{"url":"/census/reparameterize","implementations":12,"papers":17,"distinct_outputs":5,"n_buckets":4,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7c5e74bc668cf5cc"}},{"code_sha256":"a7b323241cd70612","code_sha256_prefix":"a7b323241cd70612","entry":"safemean","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"xs:list/1/float","fixture_out_type":"float64","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"a7b323241cd70612"},"code_page":"/code/safemean","census":null,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"a7b323241cd70612"}},{"code_sha256":"baf2a28d376d7803","code_sha256_prefix":"baf2a28d376d7803","entry":"sf01","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"arr:ndarray/4/float","fixture_out_type":"ndarray","code_page":"/code/sf01","census":null,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"baf2a28d376d7803"}},{"code_sha256":"a7700bf49f384087","code_sha256_prefix":"a7700bf49f384087","entry":"states_to_prob","repo":"deconlabs/TradingZoo-Dynamic-fee-simulation","repo_kind":"listed","path":"agent/PPO/utils.py","file_url":"https://github.com/deconlabs/TradingZoo-Dynamic-fee-simulation/blob/HEAD/agent/PPO/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"signature":"model:callable/0/?, states:list/1/Tensor","fixture_out_type":"Tensor","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":"a7700bf49f384087"}},{"code_sha256":"f8348c78f9a4c594","code_sha256_prefix":"f8348c78f9a4c594","entry":"states_to_prob","repo":"Rafael1s/Deep-Reinforcement-Learning-Udacity","repo_kind":"listed","path":"Pong-Policy-Gradient-PPO/pong_utils.py","file_url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity/blob/HEAD/Pong-Policy-Gradient-PPO/pong_utils.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":"policy:callable/0/?, states:list/1/Tensor","fixture_out_type":"Tensor","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":"f8348c78f9a4c594"}},{"code_sha256":"03b48449f3d4d675","code_sha256_prefix":"03b48449f3d4d675","entry":"tensor","repo":"dmiu-shell/deeprl-shell","repo_kind":"listed","path":"deep_rl/agent/PPO_agent.py","file_url":"https://github.com/dmiu-shell/deeprl-shell/blob/HEAD/deep_rl/agent/PPO_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"x:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"03b48449f3d4d675"},"code_page":"/code/tensor","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"03b48449f3d4d675"}},{"code_sha256":"5b125d5154c21cbf","code_sha256_prefix":"5b125d5154c21cbf","entry":"AbstractEnvRunner","repo":"wangzhengfei0730/NIPS2018-AIforProsthetics","repo_kind":"listed","path":"baselines/ppo2/ppo2.py","file_url":"https://github.com/wangzhengfei0730/NIPS2018-AIforProsthetics/blob/HEAD/baselines/ppo2/ppo2.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, wangzhengfei0730/NIPS2018-AIforProsthetics when it was checked","mcp_get_code":{"code_sha256":"5b125d5154c21cbf"}},{"code_sha256":"54ccb8ae3f658c83","code_sha256_prefix":"54ccb8ae3f658c83","entry":"Actor","repo":"marload/DeepRL-TensorFlow2","repo_kind":"listed","path":"PPO/PPO_Continuous.py","file_url":"https://github.com/marload/DeepRL-TensorFlow2/blob/HEAD/PPO/PPO_Continuous.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"54ccb8ae3f658c83"}},{"code_sha256":"bf0c1da602f8a16d","code_sha256_prefix":"bf0c1da602f8a16d","entry":"Actor","repo":"InSpaceAI/RL-Zoo","repo_kind":"listed","path":"PPO.py","file_url":"https://github.com/InSpaceAI/RL-Zoo/blob/HEAD/PPO.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actor","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, InSpaceAI/RL-Zoo when it was checked","mcp_get_code":{"code_sha256":"bf0c1da602f8a16d"}},{"code_sha256":"d068adb7cb463c20","code_sha256_prefix":"d068adb7cb463c20","entry":"ActorCritic","repo":"tommyvsfu1/RL-NTU","repo_kind":"listed","path":"RL_mlds_hw4/hw4/agent_dir/agent_pg.py","file_url":"https://github.com/tommyvsfu1/RL-NTU/blob/HEAD/RL_mlds_hw4/hw4/agent_dir/agent_pg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/actorcritic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, tommyvsfu1/RL-NTU when it was checked","mcp_get_code":{"code_sha256":"d068adb7cb463c20"}},{"code_sha256":"53db83baee745ffd","code_sha256_prefix":"53db83baee745ffd","entry":"Agent","repo":"marload/DeepRL-TensorFlow2","repo_kind":"listed","path":"PPO/PPO_Continuous.py","file_url":"https://github.com/marload/DeepRL-TensorFlow2/blob/HEAD/PPO/PPO_Continuous.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"53db83baee745ffd"}},{"code_sha256":"f473685be4b59e7f","code_sha256_prefix":"f473685be4b59e7f","entry":"Agent","repo":"nric/ProximalPolicyOptimizationContinuousKeras","repo_kind":"listed","path":"ppo_keras_continuous.py","file_url":"https://github.com/nric/ProximalPolicyOptimizationContinuousKeras/blob/HEAD/ppo_keras_continuous.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, nric/ProximalPolicyOptimizationContinuousKeras when it was checked","mcp_get_code":{"code_sha256":"f473685be4b59e7f"}},{"code_sha256":"c3c2c245443da6e3","code_sha256_prefix":"c3c2c245443da6e3","entry":"Agent","repo":"mit-realm/neuriss","repo_kind":"listed","path":"neuriss/rl/ppo.py","file_url":"https://github.com/mit-realm/neuriss/blob/HEAD/neuriss/rl/ppo.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":"c3c2c245443da6e3"}},{"code_sha256":"64930ee88e057fb9","code_sha256_prefix":"64930ee88e057fb9","entry":"Agent","repo":"xtma/simple-pytorch-rl","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/xtma/simple-pytorch-rl/blob/HEAD/ppo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xtma/simple-pytorch-rl when it was checked","mcp_get_code":{"code_sha256":"64930ee88e057fb9"}},{"code_sha256":"449ad938cfccea32","code_sha256_prefix":"449ad938cfccea32","entry":"Agent","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/PPO/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/PPO/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"449ad938cfccea32"}},{"code_sha256":"d196dcee4a5b1061","code_sha256_prefix":"d196dcee4a5b1061","entry":"Agent","repo":"alexbaumi/PPO-Algorithm","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/alexbaumi/PPO-Algorithm/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/agent","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, alexbaumi/PPO-Algorithm when it was checked","mcp_get_code":{"code_sha256":"d196dcee4a5b1061"}},{"code_sha256":"d5c516ed0fa589e3","code_sha256_prefix":"d5c516ed0fa589e3","entry":"Algorithm","repo":"hmhuy0/SIM-RL","repo_kind":"listed","path":"Sources/algo/ppo.py","file_url":"https://github.com/hmhuy0/SIM-RL/blob/HEAD/Sources/algo/ppo.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, hmhuy0/SIM-RL when it was checked","mcp_get_code":{"code_sha256":"d5c516ed0fa589e3"}},{"code_sha256":"2bddf6daaed4d669","code_sha256_prefix":"2bddf6daaed4d669","entry":"Algorithm","repo":"ku2482/gail-airl-ppo.pytorch","repo_kind":"listed","path":"gail_airl_ppo/algo/ppo.py","file_url":"https://github.com/ku2482/gail-airl-ppo.pytorch/blob/HEAD/gail_airl_ppo/algo/ppo.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":"2bddf6daaed4d669"}},{"code_sha256":"527acc6b195e3ec9","code_sha256_prefix":"527acc6b195e3ec9","entry":"Algorithm","repo":"evieq01/oodil","repo_kind":"listed","path":"simulated_robot/gail_airl_ppo/algo/ppo.py","file_url":"https://github.com/evieq01/oodil/blob/HEAD/simulated_robot/gail_airl_ppo/algo/ppo.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":"527acc6b195e3ec9"}},{"code_sha256":"9619638a806c794f","code_sha256_prefix":"9619638a806c794f","entry":"Base","repo":"zjlab-ammi/llm4rl","repo_kind":"listed","path":"algos/ppo.py","file_url":"https://github.com/zjlab-ammi/llm4rl/blob/HEAD/algos/ppo.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/base","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zjlab-ammi/llm4rl when it was checked","mcp_get_code":{"code_sha256":"9619638a806c794f"}},{"code_sha256":"2dd687e050a61476","code_sha256_prefix":"2dd687e050a61476","entry":"BaseAgent","repo":"hamishs/JAX-RL","repo_kind":"listed","path":"src/jax_rl/algorithms/ppo.py","file_url":"https://github.com/hamishs/JAX-RL/blob/HEAD/src/jax_rl/algorithms/ppo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/baseagent","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2dd687e050a61476"}},{"code_sha256":"6c7082241ec61d89","code_sha256_prefix":"6c7082241ec61d89","entry":"BaseAlgo","repo":"GiadaSimionato/Reasoning_Agents_2020","repo_kind":"listed","path":"babyai_rb/babyai/rl/algos/ppo.py","file_url":"https://github.com/GiadaSimionato/Reasoning_Agents_2020/blob/HEAD/babyai_rb/babyai/rl/algos/ppo.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, GiadaSimionato/Reasoning_Agents_2020 when it was checked","mcp_get_code":{"code_sha256":"6c7082241ec61d89"}},{"code_sha256":"deafc9726839a93c","code_sha256_prefix":"deafc9726839a93c","entry":"BaseAlgo","repo":"lcswillems/torch-ac","repo_kind":"listed","path":"torch_ac/algos/ppo.py","file_url":"https://github.com/lcswillems/torch-ac/blob/HEAD/torch_ac/algos/ppo.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":"deafc9726839a93c"}},{"code_sha256":"6f2b092fd868a348","code_sha256_prefix":"6f2b092fd868a348","entry":"Buffer","repo":"hamishs/JAX-RL","repo_kind":"listed","path":"src/jax_rl/algorithms/ppo.py","file_url":"https://github.com/hamishs/JAX-RL/blob/HEAD/src/jax_rl/algorithms/ppo.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":"6f2b092fd868a348"}},{"code_sha256":"593f887d35295a28","code_sha256_prefix":"593f887d35295a28","entry":"Config","repo":"OctopusMind/RLHF_PPO","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/OctopusMind/RLHF_PPO/blob/HEAD/ppo.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/config","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"593f887d35295a28"}},{"code_sha256":"c004c93ba5634851","code_sha256_prefix":"c004c93ba5634851","entry":"Critic","repo":"marload/DeepRL-TensorFlow2","repo_kind":"listed","path":"PPO/PPO_Continuous.py","file_url":"https://github.com/marload/DeepRL-TensorFlow2/blob/HEAD/PPO/PPO_Continuous.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/critic","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c004c93ba5634851"}},{"code_sha256":"708e869097ea91ff","code_sha256_prefix":"708e869097ea91ff","entry":"Critic","repo":"InSpaceAI/RL-Zoo","repo_kind":"listed","path":"PPO.py","file_url":"https://github.com/InSpaceAI/RL-Zoo/blob/HEAD/PPO.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/critic","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, InSpaceAI/RL-Zoo when it was checked","mcp_get_code":{"code_sha256":"708e869097ea91ff"}},{"code_sha256":"f42b9cecada07086","code_sha256_prefix":"f42b9cecada07086","entry":"Critic","repo":"yoavalon/Quadcopter-env","repo_kind":"listed","path":"kdev/ppo.py","file_url":"https://github.com/yoavalon/Quadcopter-env/blob/HEAD/kdev/ppo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/critic","census":null,"licence":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, yoavalon/Quadcopter-env, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"f42b9cecada07086"}},{"code_sha256":"f5415970200a24b5","code_sha256_prefix":"f5415970200a24b5","entry":"Env","repo":"mit-realm/neuriss","repo_kind":"listed","path":"neuriss/rl/ppo.py","file_url":"https://github.com/mit-realm/neuriss/blob/HEAD/neuriss/rl/ppo.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/env","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f5415970200a24b5"}},{"code_sha256":"121aee63a1a24691","code_sha256_prefix":"121aee63a1a24691","entry":"Memory","repo":"liuyuezhang/pyrl","repo_kind":"listed","path":"ppo/agent.py","file_url":"https://github.com/liuyuezhang/pyrl/blob/HEAD/ppo/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/memory","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"121aee63a1a24691"}},{"code_sha256":"14b4f65f714ccf75","code_sha256_prefix":"14b4f65f714ccf75","entry":"Model","repo":"wangzhengfei0730/NIPS2018-AIforProsthetics","repo_kind":"listed","path":"baselines/ppo2/ppo2.py","file_url":"https://github.com/wangzhengfei0730/NIPS2018-AIforProsthetics/blob/HEAD/baselines/ppo2/ppo2.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":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, wangzhengfei0730/NIPS2018-AIforProsthetics when it was checked","mcp_get_code":{"code_sha256":"14b4f65f714ccf75"}},{"code_sha256":"a9432edcc1976925","code_sha256_prefix":"a9432edcc1976925","entry":"Model","repo":"saschaschramm/Pong","repo_kind":"listed","path":"models/ppo/model.py","file_url":"https://github.com/saschaschramm/Pong/blob/HEAD/models/ppo/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/model","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, saschaschramm/Pong when it was checked","mcp_get_code":{"code_sha256":"a9432edcc1976925"}},{"code_sha256":"5954e04c0ee7d26e","code_sha256_prefix":"5954e04c0ee7d26e","entry":"PPO","repo":"MaximeVandegar/Papers-in-100-Lines-of-Code","repo_kind":"listed","path":"Proximal_Policy_Optimization_Algorithms/ppo.py","file_url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/blob/HEAD/Proximal_Policy_Optimization_Algorithms/ppo.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":"5954e04c0ee7d26e"}},{"code_sha256":"578c10d4e2b66073","code_sha256_prefix":"578c10d4e2b66073","entry":"PPO","repo":"JonasRSV/PPO","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/JonasRSV/PPO/blob/HEAD/ppo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, JonasRSV/PPO when it was checked","mcp_get_code":{"code_sha256":"578c10d4e2b66073"}},{"code_sha256":"ded7302e103e8dd7","code_sha256_prefix":"ded7302e103e8dd7","entry":"PPO","repo":"mit-realm/neuriss","repo_kind":"listed","path":"neuriss/rl/ppo.py","file_url":"https://github.com/mit-realm/neuriss/blob/HEAD/neuriss/rl/ppo.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":"ded7302e103e8dd7"}},{"code_sha256":"cb4776fdb4698c72","code_sha256_prefix":"cb4776fdb4698c72","entry":"PPO","repo":"Gregory-Eales/proximal-policy-optimization","repo_kind":"listed","path":"ppo/modules/ppo.py","file_url":"https://github.com/Gregory-Eales/proximal-policy-optimization/blob/HEAD/ppo/modules/ppo.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":"cb4776fdb4698c72"}},{"code_sha256":"f7417c7ed09d5ade","code_sha256_prefix":"f7417c7ed09d5ade","entry":"PPO","repo":"yoavalon/Quadcopter-env","repo_kind":"listed","path":"kdev/ppo.py","file_url":"https://github.com/yoavalon/Quadcopter-env/blob/HEAD/kdev/ppo.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":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, yoavalon/Quadcopter-env, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"f7417c7ed09d5ade"}},{"code_sha256":"1c8d1f046ceeaadf","code_sha256_prefix":"1c8d1f046ceeaadf","entry":"PPO","repo":"CSautier/Breakout","repo_kind":"listed","path":"model.py","file_url":"https://github.com/CSautier/Breakout/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, CSautier/Breakout when it was checked","mcp_get_code":{"code_sha256":"1c8d1f046ceeaadf"}},{"code_sha256":"cd66a006bca55706","code_sha256_prefix":"cd66a006bca55706","entry":"PPO","repo":"ku2482/gail-airl-ppo.pytorch","repo_kind":"listed","path":"gail_airl_ppo/algo/ppo.py","file_url":"https://github.com/ku2482/gail-airl-ppo.pytorch/blob/HEAD/gail_airl_ppo/algo/ppo.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":"cd66a006bca55706"}},{"code_sha256":"ea96173e68302d60","code_sha256_prefix":"ea96173e68302d60","entry":"PPO","repo":"goncharom/PPOv1","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/goncharom/PPOv1/blob/HEAD/ppo.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, goncharom/PPOv1 when it was checked","mcp_get_code":{"code_sha256":"ea96173e68302d60"}},{"code_sha256":"3c7b55685f685987","code_sha256_prefix":"3c7b55685f685987","entry":"PPO","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/PPO/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/PPO/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":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3c7b55685f685987"}},{"code_sha256":"7451a2c222e554d4","code_sha256_prefix":"7451a2c222e554d4","entry":"PPO","repo":"JL321/Proximal-Policy-Optimization","repo_kind":"listed","path":"PPO.py","file_url":"https://github.com/JL321/Proximal-Policy-Optimization/blob/HEAD/PPO.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, JL321/Proximal-Policy-Optimization when it was checked","mcp_get_code":{"code_sha256":"7451a2c222e554d4"}},{"code_sha256":"86201a6180de4a09","code_sha256_prefix":"86201a6180de4a09","entry":"PPO","repo":"evieq01/oodil","repo_kind":"listed","path":"simulated_robot/gail_airl_ppo/algo/ppo.py","file_url":"https://github.com/evieq01/oodil/blob/HEAD/simulated_robot/gail_airl_ppo/algo/ppo.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":"86201a6180de4a09"}},{"code_sha256":"7af85bd3eff93a8f","code_sha256_prefix":"7af85bd3eff93a8f","entry":"PPO","repo":"morikatron/GAIL_PPO","repo_kind":"listed","path":"algo/ppo.py","file_url":"https://github.com/morikatron/GAIL_PPO/blob/HEAD/algo/ppo.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":"7af85bd3eff93a8f"}},{"code_sha256":"ef96810753b59244","code_sha256_prefix":"ef96810753b59244","entry":"PPO","repo":"bay3s/ppo-rl","repo_kind":"listed","path":"src/ppo/ppo.py","file_url":"https://github.com/bay3s/ppo-rl/blob/HEAD/src/ppo/ppo.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, bay3s/ppo-rl when it was checked","mcp_get_code":{"code_sha256":"ef96810753b59244"}},{"code_sha256":"24ed6c73c85ddcca","code_sha256_prefix":"24ed6c73c85ddcca","entry":"PPO","repo":"morikatron/PPO","repo_kind":"listed","path":"algo/ppo.py","file_url":"https://github.com/morikatron/PPO/blob/HEAD/algo/ppo.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":"24ed6c73c85ddcca"}},{"code_sha256":"6073c0994e65bae3","code_sha256_prefix":"6073c0994e65bae3","entry":"PPO","repo":"liuyuezhang/pyrl","repo_kind":"listed","path":"ppo/agent.py","file_url":"https://github.com/liuyuezhang/pyrl/blob/HEAD/ppo/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":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6073c0994e65bae3"}},{"code_sha256":"df9fd7d088621b72","code_sha256_prefix":"df9fd7d088621b72","entry":"PPO","repo":"OctopusMind/RLHF_PPO","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/OctopusMind/RLHF_PPO/blob/HEAD/ppo.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":"df9fd7d088621b72"}},{"code_sha256":"f51a9f6b2ca368d9","code_sha256_prefix":"f51a9f6b2ca368d9","entry":"PPO","repo":"tommyvsfu1/RL-NTU","repo_kind":"listed","path":"RL_mlds_hw4/hw4/agent_dir/agent_pg.py","file_url":"https://github.com/tommyvsfu1/RL-NTU/blob/HEAD/RL_mlds_hw4/hw4/agent_dir/agent_pg.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, tommyvsfu1/RL-NTU when it was checked","mcp_get_code":{"code_sha256":"f51a9f6b2ca368d9"}},{"code_sha256":"01b7328f523d7756","code_sha256_prefix":"01b7328f523d7756","entry":"PPOAgent","repo":"InSpaceAI/RL-Zoo","repo_kind":"listed","path":"PPO.py","file_url":"https://github.com/InSpaceAI/RL-Zoo/blob/HEAD/PPO.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, InSpaceAI/RL-Zoo when it was checked","mcp_get_code":{"code_sha256":"01b7328f523d7756"}},{"code_sha256":"a01bf852d6ef518a","code_sha256_prefix":"a01bf852d6ef518a","entry":"PPOAgent","repo":"DMIU-ShELL/MOSAIC","repo_kind":"listed","path":"deep_rl/agent/PPO_agent.py","file_url":"https://github.com/DMIU-ShELL/MOSAIC/blob/HEAD/deep_rl/agent/PPO_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":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a01bf852d6ef518a"}},{"code_sha256":"dce583aa0f5fb136","code_sha256_prefix":"dce583aa0f5fb136","entry":"PPOAlgo","repo":"GiadaSimionato/Reasoning_Agents_2020","repo_kind":"listed","path":"babyai_rb/babyai/rl/algos/ppo.py","file_url":"https://github.com/GiadaSimionato/Reasoning_Agents_2020/blob/HEAD/babyai_rb/babyai/rl/algos/ppo.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, GiadaSimionato/Reasoning_Agents_2020 when it was checked","mcp_get_code":{"code_sha256":"dce583aa0f5fb136"}},{"code_sha256":"108ec8df92e50f23","code_sha256_prefix":"108ec8df92e50f23","entry":"PPOAlgo","repo":"lcswillems/torch-ac","repo_kind":"listed","path":"torch_ac/algos/ppo.py","file_url":"https://github.com/lcswillems/torch-ac/blob/HEAD/torch_ac/algos/ppo.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":"108ec8df92e50f23"}},{"code_sha256":"55d94edcf36e1447","code_sha256_prefix":"55d94edcf36e1447","entry":"PPOModel","repo":"jhare96/reinforcement-learning","repo_kind":"listed","path":"rlib/PPO/model.py","file_url":"https://github.com/jhare96/reinforcement-learning/blob/HEAD/rlib/PPO/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":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"55d94edcf36e1447"}},{"code_sha256":"542d8a7c56874ec9","code_sha256_prefix":"542d8a7c56874ec9","entry":"PPO_CLIP","repo":"tensorlayer/RLzoo","repo_kind":"listed","path":"rlzoo/algorithms/ppo_clip/ppo_clip.py","file_url":"https://github.com/tensorlayer/RLzoo/blob/HEAD/rlzoo/algorithms/ppo_clip/ppo_clip.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":"542d8a7c56874ec9"}},{"code_sha256":"5dc5fc3b8ad0138c","code_sha256_prefix":"5dc5fc3b8ad0138c","entry":"PPO_continuous","repo":"hmhuy0/SIM-RL","repo_kind":"listed","path":"Sources/algo/ppo.py","file_url":"https://github.com/hmhuy0/SIM-RL/blob/HEAD/Sources/algo/ppo.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, hmhuy0/SIM-RL when it was checked","mcp_get_code":{"code_sha256":"5dc5fc3b8ad0138c"}},{"code_sha256":"48d2039b794ca629","code_sha256_prefix":"48d2039b794ca629","entry":"PPO_lunarlander","repo":"shreyesss/PPO-implementation-keras-tensorflow","repo_kind":"listed","path":"PPO_lunarlader.py","file_url":"https://github.com/shreyesss/PPO-implementation-keras-tensorflow/blob/HEAD/PPO_lunarlader.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":"GPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GPL-3.0, as GitHub detects it on this paper's repository, shreyesss/PPO-implementation-keras-tensorflow, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"48d2039b794ca629"}},{"code_sha256":"bce2a8566fa36fda","code_sha256_prefix":"bce2a8566fa36fda","entry":"PPOalgorithm","repo":"170928/-Review-Generative-Adversarial-Imitation-Learning","repo_kind":"listed","path":"PPO.py","file_url":"https://github.com/170928/-Review-Generative-Adversarial-Imitation-Learning/blob/HEAD/PPO.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, 170928/-Review-Generative-Adversarial-Imitation-Learning when it was checked","mcp_get_code":{"code_sha256":"bce2a8566fa36fda"}},{"code_sha256":"8764b4ca6ce10aca","code_sha256_prefix":"8764b4ca6ce10aca","entry":"Parameters","repo":"CSautier/Breakout","repo_kind":"listed","path":"model.py","file_url":"https://github.com/CSautier/Breakout/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, CSautier/Breakout when it was checked","mcp_get_code":{"code_sha256":"8764b4ca6ce10aca"}},{"code_sha256":"40f05c72bfe4c048","code_sha256_prefix":"40f05c72bfe4c048","entry":"PongAgent","repo":"tuanpnm99/RLPongAgent","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/tuanpnm99/RLPongAgent/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, tuanpnm99/RLPongAgent when it was checked","mcp_get_code":{"code_sha256":"40f05c72bfe4c048"}},{"code_sha256":"4652f7766f254cc1","code_sha256_prefix":"4652f7766f254cc1","entry":"StateIndependentPolicy","repo":"mit-realm/neuriss","repo_kind":"listed","path":"neuriss/rl/ppo.py","file_url":"https://github.com/mit-realm/neuriss/blob/HEAD/neuriss/rl/ppo.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":"4652f7766f254cc1"}},{"code_sha256":"2e9e6b5586603bfb","code_sha256_prefix":"2e9e6b5586603bfb","entry":"build_train","repo":"benpetit/cs379c","repo_kind":"listed","path":"build_graph.py","file_url":"https://github.com/benpetit/cs379c/blob/HEAD/build_graph.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":"2e9e6b5586603bfb"}},{"code_sha256":"9c65b36eec7ec92a","code_sha256_prefix":"9c65b36eec7ec92a","entry":"clipped_surrogate","repo":"deconlabs/TradingZoo-Dynamic-fee-simulation","repo_kind":"listed","path":"agent/PPO/utils.py","file_url":"https://github.com/deconlabs/TradingZoo-Dynamic-fee-simulation/blob/HEAD/agent/PPO/utils.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":"9c65b36eec7ec92a"}},{"code_sha256":"db1820f47853260b","code_sha256_prefix":"db1820f47853260b","entry":"clipped_surrogate","repo":"Rafael1s/Deep-Reinforcement-Learning-Udacity","repo_kind":"listed","path":"Pong-Policy-Gradient-PPO/pong_utils.py","file_url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity/blob/HEAD/Pong-Policy-Gradient-PPO/pong_utils.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":"db1820f47853260b"}},{"code_sha256":"37c11b4e769d359d","code_sha256_prefix":"37c11b4e769d359d","entry":"ffNetwork","repo":"JL321/Proximal-Policy-Optimization","repo_kind":"listed","path":"PPO.py","file_url":"https://github.com/JL321/Proximal-Policy-Optimization/blob/HEAD/PPO.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, JL321/Proximal-Policy-Optimization when it was checked","mcp_get_code":{"code_sha256":"37c11b4e769d359d"}},{"code_sha256":"c2f17acc73ce8ca9","code_sha256_prefix":"c2f17acc73ce8ca9","entry":"init_weights","repo":"alexbaumi/PPO-Algorithm","repo_kind":"listed","path":"Agent.py","file_url":"https://github.com/alexbaumi/PPO-Algorithm/blob/HEAD/Agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/init-weights","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, alexbaumi/PPO-Algorithm when it was checked","mcp_get_code":{"code_sha256":"c2f17acc73ce8ca9"}},{"code_sha256":"be674cc9da531aa5","code_sha256_prefix":"be674cc9da531aa5","entry":"learn","repo":"wangzhengfei0730/NIPS2018-AIforProsthetics","repo_kind":"listed","path":"baselines/ppo2/ppo2.py","file_url":"https://github.com/wangzhengfei0730/NIPS2018-AIforProsthetics/blob/HEAD/baselines/ppo2/ppo2.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/learn","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, wangzhengfei0730/NIPS2018-AIforProsthetics when it was checked","mcp_get_code":{"code_sha256":"be674cc9da531aa5"}},{"code_sha256":"2c9a98eedcdea762","code_sha256_prefix":"2c9a98eedcdea762","entry":"ppo_loss","repo":"Narsil/rl-baselines","repo_kind":"listed","path":"rl_baselines/ppo.py","file_url":"https://github.com/Narsil/rl-baselines/blob/HEAD/rl_baselines/ppo.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, Narsil/rl-baselines when it was checked","mcp_get_code":{"code_sha256":"2c9a98eedcdea762"}},{"code_sha256":"f423e91c2339c824","code_sha256_prefix":"f423e91c2339c824","entry":"ppo_step","repo":"Khrylx/PyTorch-RL","repo_kind":"listed","path":"core/ppo.py","file_url":"https://github.com/Khrylx/PyTorch-RL/blob/HEAD/core/ppo.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":"f423e91c2339c824"}},{"code_sha256":"f20ab80cf000ba69","code_sha256_prefix":"f20ab80cf000ba69","entry":"ppo_update","repo":"Ostyk/walk-bot","repo_kind":"listed","path":"v_pytorch/ppo_train.py","file_url":"https://github.com/Ostyk/walk-bot/blob/HEAD/v_pytorch/ppo_train.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, Ostyk/walk-bot when it was checked","mcp_get_code":{"code_sha256":"f20ab80cf000ba69"}},{"code_sha256":"76b542040b4e4fcf","code_sha256_prefix":"76b542040b4e4fcf","entry":"ppo_update","repo":"silvialuu/DRL-2018","repo_kind":"listed","path":"es-ppo/ppo.py","file_url":"https://github.com/silvialuu/DRL-2018/blob/HEAD/es-ppo/ppo.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, silvialuu/DRL-2018 when it was checked","mcp_get_code":{"code_sha256":"76b542040b4e4fcf"}},{"code_sha256":"2492441b222787d6","code_sha256_prefix":"2492441b222787d6","entry":"proximal_policy_optimization_loss","repo":"MatteoBrentegani/PPO","repo_kind":"listed","path":"PPO_CentralizedNN/ppo_lossFunctionC.py","file_url":"https://github.com/MatteoBrentegani/PPO/blob/HEAD/PPO_CentralizedNN/ppo_lossFunctionC.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, MatteoBrentegani/PPO when it was checked","mcp_get_code":{"code_sha256":"2492441b222787d6"}},{"code_sha256":"a690a9a71794bce7","code_sha256_prefix":"a690a9a71794bce7","entry":"proximal_policy_optimization_loss_continuous","repo":"downingbots/RLDonkeycar","repo_kind":"listed","path":"donkeycar/donkeycar/parts/RLKeras.py","file_url":"https://github.com/downingbots/RLDonkeycar/blob/HEAD/donkeycar/donkeycar/parts/RLKeras.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":"a690a9a71794bce7"}},{"code_sha256":"6b56455d8ddd9bf1","code_sha256_prefix":"6b56455d8ddd9bf1","entry":"sample","repo":"saschaschramm/Pong","repo_kind":"listed","path":"models/ppo/model.py","file_url":"https://github.com/saschaschramm/Pong/blob/HEAD/models/ppo/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/sample","census":{"url":"/census/sample","implementations":8,"papers":9,"distinct_outputs":7,"n_buckets":5,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, saschaschramm/Pong when it was checked","mcp_get_code":{"code_sha256":"6b56455d8ddd9bf1"}},{"code_sha256":"6647017115e92ee7","code_sha256_prefix":"6647017115e92ee7","entry":"surrogate_loss","repo":"reinforcement-learning-kr/pg_travel","repo_kind":"listed","path":"mujoco/agent/ppo_gae.py","file_url":"https://github.com/reinforcement-learning-kr/pg_travel/blob/HEAD/mujoco/agent/ppo_gae.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/surrogate-loss","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6647017115e92ee7"}},{"code_sha256":"8e103b8cabd1203c","code_sha256_prefix":"8e103b8cabd1203c","entry":"tensor","repo":"DMIU-ShELL/MOSAIC","repo_kind":"listed","path":"deep_rl/agent/PPO_agent.py","file_url":"https://github.com/DMIU-ShELL/MOSAIC/blob/HEAD/deep_rl/agent/PPO_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/tensor","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8e103b8cabd1203c"}},{"code_sha256":"f5d2e6057543255c","code_sha256_prefix":"f5d2e6057543255c","entry":"train","repo":"llSourcell/OpenAI_Five_vs_Dota2_Explained","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/llSourcell/OpenAI_Five_vs_Dota2_Explained/blob/HEAD/ppo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/train","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f5d2e6057543255c"}},{"code_sha256":"7271dace2360dd93","code_sha256_prefix":"7271dace2360dd93","entry":"update","repo":"Gouet/Acrobot-PPO","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/Gouet/Acrobot-PPO/blob/HEAD/ppo.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/update","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Gouet/Acrobot-PPO when it was checked","mcp_get_code":{"code_sha256":"7271dace2360dd93"}},{"code_sha256":"3e7bdf63d50d132e","code_sha256_prefix":"3e7bdf63d50d132e","entry":"update","repo":"Gouet/PPO-pytorch","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/Gouet/PPO-pytorch/blob/HEAD/ppo.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/update","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Gouet/PPO-pytorch when it was checked","mcp_get_code":{"code_sha256":"3e7bdf63d50d132e"}},{"code_sha256":"0b170016a5f01a6e","code_sha256_prefix":"0b170016a5f01a6e","entry":"update","repo":"Gouet/PPO-gym","repo_kind":"listed","path":"ppo.py","file_url":"https://github.com/Gouet/PPO-gym/blob/HEAD/ppo.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/update","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Gouet/PPO-gym when it was checked","mcp_get_code":{"code_sha256":"0b170016a5f01a6e"}},{"code_sha256":"887a93fefeaff1d2","code_sha256_prefix":"887a93fefeaff1d2","entry":"valueNetwork","repo":"JL321/Proximal-Policy-Optimization","repo_kind":"listed","path":"PPO.py","file_url":"https://github.com/JL321/Proximal-Policy-Optimization/blob/HEAD/PPO.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, JL321/Proximal-Policy-Optimization when it was checked","mcp_get_code":{"code_sha256":"887a93fefeaff1d2"}},{"code_sha256":"01571ae37dfefba2","code_sha256_prefix":"01571ae37dfefba2","entry":"worker","repo":"GiadaSimionato/Reasoning_Agents_2020","repo_kind":"listed","path":"babyai_rb/babyai/rl/algos/ppo.py","file_url":"https://github.com/GiadaSimionato/Reasoning_Agents_2020/blob/HEAD/babyai_rb/babyai/rl/algos/ppo.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/worker","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, GiadaSimionato/Reasoning_Agents_2020 when it was checked","mcp_get_code":{"code_sha256":"01571ae37dfefba2"}},{"code_sha256":"0a1d06fc0e7bba39","code_sha256_prefix":"0a1d06fc0e7bba39","entry":"worker","repo":"lcswillems/torch-ac","repo_kind":"listed","path":"torch_ac/algos/ppo.py","file_url":"https://github.com/lcswillems/torch-ac/blob/HEAD/torch_ac/algos/ppo.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/worker","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0a1d06fc0e7bba39"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"dc8ba1a6446e950ded370e678f6003d09c78c9348f3ec2c723765e492b3a77d8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}