{"about":{"site":"https://codewithpapers.app","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.","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"},"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"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","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},"by_repo_kind":{"listed":{"samples":172,"ran":95,"repositories":64}},"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,"samples":[{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e9f1207fc08f9fa9"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8fc0ce07edd32744"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c3cb4b39b7e82812"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f7a59411ac390f78"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"607bb439a428fd2a"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bab8cee03856463f"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ff581679958bf77"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2f383d9f3f2f7b4f"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"13b852ad71d18604"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b1f30e180cb81a3a"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4c40cb5849fd342f"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"38803d98e366da6d"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6dbcf603fe9c4a6f"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5eac27c1ede5a3f1"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d0735a6f70135e3f"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cc0a6d60ba0d615d"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1e06bd08fb825800"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b4455ab1f545ae9c"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f1685211d6effd06"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a18a57c9dbc3655"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"28919ed273c0c995"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"06c62bb9eacfe08c"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f2a4b483cf41dcfd"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"75bc51af9c0cf574"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"088783306dda80fe"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7f143a6ee276436b"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb56e14071f60cba"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1271c934496f2b53"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ebfd098cf241f3c"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b48c75c1f791937c"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"00bb1a30b070c324"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd4134c19ff6f1eb"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"20cf521175a91e97"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e26f9d72a957989"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e33afa03c0df2bff"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e3bd893b00cce00e"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"786ef0f1e1c69fc2"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"08c8acc6b144eabd"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7dbfda361c907b1e"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f0b71d0c5374efdf"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"028cd0cc569e4945"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c02c0631708465dc"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ec594f35cdf2f00e"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be3a23c2176d855c"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"06f3c47cdf2dd979"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2eb0c930a45a7472"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7539f57b4803c98e"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"049dd1dd7386f7f1"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"168b3d776129e246"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22bcf7bc55b864b8"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c169652ebc3cb1c4"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6f986aa2d59a44f8"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c80e9a362666d32e"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a78ee4761e8df9d8"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f9dae876ba7e00b"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ab47bdba4f875268"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fbd28096c7f0c30f"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dea2715df3f6a1e3"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"181b4202198be200"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e626bd567c81f207"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"63380712f9af778d"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58ee12a76b1fd1a1"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a5b8d69558cb1833"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"264c9e17d7dfe7eb"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c511268a73d82fc6"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"373bf1b3269456e9"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b5a22b5e0dce3796"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e7afb47f6ebd451"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"77393baa1a11c24b"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"476e14ee8b7219ac"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eb4a6cb62afcb0ec"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b4f2ea8b3db73cea"}},{"code_sha256_prefix":"54948e8edd9b8bc1","entry":"check_optimality","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":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"54948e8edd9b8bc1"}},{"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,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"8758308dc6c0727f"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1cd2e751ff91ca44"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1732d17d766f28da"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c977657d1b1dadef"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fef4ec37a6ea52e7"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1cfc11023c8784d6"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"92227b56b34a423b"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b46c632bedd3d8af"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"62a48793f7edb3af"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"356537802e7b2bdb"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"375f0073f16726f9"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f2cddb5460e2bc7e"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f1449fb45454e326"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"942f9baf61103bea"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"df1fd605b67498ef"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0db440a845c6a4fa"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"063d29364d7e4f81"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2439c728712b51ae"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b1c9c127240c75d8"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6741967893f01eac"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7c5e74bc668cf5cc"}},{"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,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a7b323241cd70612"}},{"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,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"baf2a28d376d7803"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a7700bf49f384087"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f8348c78f9a4c594"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"03b48449f3d4d675"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5b125d5154c21cbf"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"54ccb8ae3f658c83"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bf0c1da602f8a16d"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d068adb7cb463c20"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"53db83baee745ffd"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f473685be4b59e7f"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c3c2c245443da6e3"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"64930ee88e057fb9"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"449ad938cfccea32"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d196dcee4a5b1061"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d5c516ed0fa589e3"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2bddf6daaed4d669"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"527acc6b195e3ec9"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9619638a806c794f"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2dd687e050a61476"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6c7082241ec61d89"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"deafc9726839a93c"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f2b092fd868a348"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"593f887d35295a28"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c004c93ba5634851"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"708e869097ea91ff"}},{"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,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f42b9cecada07086"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f5415970200a24b5"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"121aee63a1a24691"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"14b4f65f714ccf75"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a9432edcc1976925"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5954e04c0ee7d26e"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"578c10d4e2b66073"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ded7302e103e8dd7"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb4776fdb4698c72"}},{"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,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f7417c7ed09d5ade"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1c8d1f046ceeaadf"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cd66a006bca55706"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea96173e68302d60"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3c7b55685f685987"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7451a2c222e554d4"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"86201a6180de4a09"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7af85bd3eff93a8f"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ef96810753b59244"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"24ed6c73c85ddcca"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6073c0994e65bae3"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"df9fd7d088621b72"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f51a9f6b2ca368d9"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"01b7328f523d7756"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a01bf852d6ef518a"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dce583aa0f5fb136"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"108ec8df92e50f23"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"55d94edcf36e1447"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"542d8a7c56874ec9"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5dc5fc3b8ad0138c"}},{"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,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"48d2039b794ca629"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bce2a8566fa36fda"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8764b4ca6ce10aca"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"40f05c72bfe4c048"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4652f7766f254cc1"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e9e6b5586603bfb"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9c65b36eec7ec92a"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"db1820f47853260b"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"37c11b4e769d359d"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c2f17acc73ce8ca9"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"be674cc9da531aa5"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2c9a98eedcdea762"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f423e91c2339c824"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f20ab80cf000ba69"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"76b542040b4e4fcf"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2492441b222787d6"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a690a9a71794bce7"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6b56455d8ddd9bf1"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6647017115e92ee7"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8e103b8cabd1203c"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f5d2e6057543255c"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7271dace2360dd93"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3e7bdf63d50d132e"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0b170016a5f01a6e"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"887a93fefeaff1d2"}},{"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,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"01571ae37dfefba2"}},{"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,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a1d06fc0e7bba39"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}