{"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/playing-atari-with-deep-reinforcement","title":"Playing Atari with Deep Reinforcement Learning","arxiv_id":"1312.5602","date":"2013-12-19","proceeding":null,"authors":["Volodymyr Mnih","Koray Kavukcuoglu","David Silver","Alex Graves","Ioannis Antonoglou","Daan Wierstra","Martin Riedmiller"],"abstract":"We present the first deep learning model to successfully learn control\npolicies directly from high-dimensional sensory input using reinforcement\nlearning. The model is a convolutional neural network, trained with a variant\nof Q-learning, whose input is raw pixels and whose output is a value function\nestimating future rewards. We apply our method to seven Atari 2600 games from\nthe Arcade Learning Environment, with no adjustment of the architecture or\nlearning algorithm. We find that it outperforms all previous approaches on six\nof the games and surpasses a human expert on three of them.","url_abs":"http://arxiv.org/abs/1312.5602v1","url_pdf":"http://arxiv.org/pdf/1312.5602v1.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":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/2023-MindSpore-1/ms-code-52","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/AndrewJWashington/protodriver","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/Anshu1245/RL-CourseProject","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/BH4/Deep-Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/CankayaUniversity/ceng-407-408-License-Plate-Recognition-Using-Deep-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/FauzaanQureshi/deep-Q-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/Gary-Shi/Tank","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/InSpaceAI/RL-Zoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/Ishan-Kumar2/Reinforcement-Learning-on-2048","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/JackFurby/Breakout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/JonasRSV/DQN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/JonasRSV/DQNTensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/JuliaPOMDP/DeepQLearning.jl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/K-tang-mkv/baseRLAlgorithm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/KatyNTsachi/Hierarchical-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/KavindaKottege/DeepQ-Pong","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/Linging/Traffic-Signal-Control","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/LukasGardberg/cartpole","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/MOVzeroOne/DQN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/MateuszJanda/netris-ai-robot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/MehmetBarutcu/Streaming-Algorithm-for-Monotone-k-Submodular-Maximization-with-Cardinality-Constraints","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/R-Stefano/DQN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/RLeike/connect-four","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/Rabrg/dqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/RandyDeng/gym_connect4","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/RobotMobile/rl-paper-review","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/SayhoKim/tetrisRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/Sheepsody/Batched-Impala-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/ShivamShrirao/deep_Q_learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/ShivamShrirao/deep_Q_learning_from_scratch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/TheFebrin/DeepRL-Pong","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/Wentworth1996/Summer_Intern_Progress","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/alfredvc/paac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/avillemin/Minecraft-AI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/behzaad/Deep_QLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/bjotho/Zelda1AI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/blakeMilner/DeepQLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/borea17/efficient_rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/borhanreo/Obstacle-Avoid-Car","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/daviddcho/supermario","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/drforester/Q-learning-Intersection-Crossing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/dsgiitr/rl_2048","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/eddynelson/dqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/epignatelli/human-level-control-through-deep-reinforcement-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/esmeralday/MARL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/eublefar/dqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/filippogiruzzi/deep_q_learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/geeky-wizard/Atari-Deep-Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/grass123-hub/DQN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/harvitronix/reinforcement-learning-car","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/igoracmorais/inteligencia_artificial","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/invictos/InsacarDQN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/jonaths/dqn-grid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/jonaths/tf-dqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/joshiatul/game_playing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/kmdanielduan/DQN_Family_PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/komejisatori/ReinforcementCar","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/kshitij-ingale/Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/ktkachuk/Atari-with-Q-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/markusdutschke/yahtzee","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/marload/DeepRL-TensorFlow2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/marload/deep-rl-tf2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/mfregeau/DeepLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/nandomp/AICollaboratory","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/nathanin/pad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/natsumeS/analysis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/near32/regym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/niklasschmitz/DeepQLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/ninja18/AtariDQN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/omkarv/pong-from-pixels","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/paintception/Deep-Quality-Value-Family","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/paintception/Deep-Quality-Value-Family-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/parilo/rl-server","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/pavitrakumar78/Playing-custom-games-using-Deep-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/proroklab/popgym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/qiankun214/DQN-FlappyBird-python3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/rikluost/RL_DQN_Pong","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/rishavb123/MineRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/saha0073/Deep-Reinforcement-Learning-to-play-Cartpole","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/sourenaKhanzadeh/snakeAi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/spragunr/deep_q_rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/subhadip-maiti/tinydqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/sunjeet95/Deep-Q-Network-using-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/sygi/deep_q_rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"playing-atari-with-deep-reinforcement","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":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/tlohr/nfsu2-ai","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/ugo-nama-kun/DQN-chainer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/vincentpalma/DQN-for-CaRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/vsquareg/RL_ERA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/xValentim/Steering_Behaviors_with_pygame","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/yaxinchen666/dce_pricingRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/Curt-Park/rainbow-is-all-you-need","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/DLR-RM/stable-baselines3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Playing_Atari_with_Deep_Reinforcement_Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/NervanaSystems/coach","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/anita-hu/TF2-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/bay3s/dqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/chandar-lab/RLHive","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/facebookresearch/rl/blob/main/examples/dqn/dqn.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/gordicaleksa/pytorch-learn-reinforcement-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/han-won/PlayingAtariWithMindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/hill-a/stable-baselines","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","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":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/lvyufeng/DQN-MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/michaelnny/deep_rl_zoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/pytorch/rl/tree/main/examples/dqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/ray-project/ray/tree/master/rllib","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/toni-sm/skrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"playing-atari-with-deep-reinforcement","repo_url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/dqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"multi-goal-reinforcement-learning","task_name":"Multi-Goal Reinforcement Learning"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dqn","method_name":"DQN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"epsilon-greedy-exploration","method_name":"Epsilon Greedy Exploration"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[{"slug":"dqn","name":"DQN","full_name":"Deep Q-Network"}],"results":[{"leaderboard":"/sota/atari-games-on-atari-2600-beam-rider","task":"Atari Games","dataset":"Atari 2600 Beam Rider","model":"DQN Best","rank_in_archive_order":40,"of":49,"metrics":{"Score":"5184"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-breakout","task":"Atari Games","dataset":"Atari 2600 Breakout","model":"DQN Best","rank_in_archive_order":46,"of":58,"metrics":{"Score":"225"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-enduro","task":"Atari Games","dataset":"Atari 2600 Enduro","model":"DQN Best","rank_in_archive_order":33,"of":48,"metrics":{"Score":"661"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-pong","task":"Atari Games","dataset":"Atari 2600 Pong","model":"DQN Best","rank_in_archive_order":7,"of":52,"metrics":{"Score":"21"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-qbert","task":"Atari Games","dataset":"Atari 2600 Q*Bert","model":"DQN Best","rank_in_archive_order":44,"of":57,"metrics":{"Score":"4500"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-seaquest","task":"Atari Games","dataset":"Atari 2600 Seaquest","model":"DQN Best","rank_in_archive_order":42,"of":57,"metrics":{"Score":"1740"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-space-invaders","task":"Atari Games","dataset":"Atari 2600 Space Invaders","model":"DQN Best","rank_in_archive_order":45,"of":55,"metrics":{"Score":"1075"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1312.5602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1312.5602"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/DLR-RM/stable-baselines3","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alfredvc/paac","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/harvitronix/reinforcement-learning-car","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/filippogiruzzi/deep_q_learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/FauzaanQureshi/deep-Q-learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/dqn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/saha0073/Deep-Reinforcement-Learning-to-play-Cartpole","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Rabrg/dqn","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/proroklab/popgym","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rishavb123/MineRL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ray-project/ray/tree/master/rllib","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/toni-sm/skrl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/han-won/PlayingAtariWithMindSpore","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Anshu1245/RL-CourseProject","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marload/deep-rl-tf2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/avillemin/Minecraft-AI","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/daviddcho/supermario","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JackFurby/Breakout","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JuliaPOMDP/DeepQLearning.jl","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/spragunr/deep_q_rl","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/parilo/rl-server","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Playing_Atari_with_Deep_Reinforcement_Learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/joshiatul/game_playing","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BH4/Deep-Reinforcement-Learning","reach":null}],"summary":{"ran":33,"ran_draft_wrong":16,"ran_fixture":2,"ran_honours":5,"unverified":61},"by_repo_kind":{"listed":{"samples":117,"ran":56,"repositories":50}},"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":56,"samples":[{"code_sha256_prefix":"69b2f2e5a6967e4c","entry":"BaseBlock","repo":"Sheepsody/Batched-Impala-PyTorch","repo_kind":"listed","path":"src/networks/ActorCritic.py","file_url":"https://github.com/Sheepsody/Batched-Impala-PyTorch/blob/HEAD/src/networks/ActorCritic.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":"69b2f2e5a6967e4c"}},{"code_sha256_prefix":"8da78c4bfe306c3e","entry":"Brain","repo":"avillemin/Minecraft-AI","repo_kind":"listed","path":"DQN/Agent.py","file_url":"https://github.com/avillemin/Minecraft-AI/blob/HEAD/DQN/Agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8da78c4bfe306c3e"}},{"code_sha256_prefix":"81c2538f25d49bf5","entry":"BrainDQN","repo":"qiankun214/DQN-FlappyBird-python3","repo_kind":"listed","path":"BrainDQN.py","file_url":"https://github.com/qiankun214/DQN-FlappyBird-python3/blob/HEAD/BrainDQN.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":"81c2538f25d49bf5"}},{"code_sha256_prefix":"9c1d06fe674d019d","entry":"DQN","repo":"bay3s/dqn","repo_kind":"listed","path":"src/agents/dqn.py","file_url":"https://github.com/bay3s/dqn/blob/HEAD/src/agents/dqn.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":"9c1d06fe674d019d"}},{"code_sha256_prefix":"a54a3b810f63e7d1","entry":"DQN","repo":"TheFebrin/DeepRL-Pong","repo_kind":"listed","path":"models/dqn_model.py","file_url":"https://github.com/TheFebrin/DeepRL-Pong/blob/HEAD/models/dqn_model.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":"a54a3b810f63e7d1"}},{"code_sha256_prefix":"cc31fb79a4c9cfad","entry":"DQN","repo":"MaximeVandegar/Papers-in-100-Lines-of-Code","repo_kind":"listed","path":"Playing_Atari_with_Deep_Reinforcement_Learning/dqn.py","file_url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/blob/HEAD/Playing_Atari_with_Deep_Reinforcement_Learning/dqn.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":"cc31fb79a4c9cfad"}},{"code_sha256_prefix":"e65d2c13d9aa7641","entry":"DQN","repo":"daviddcho/supermario","repo_kind":"listed","path":"model.py","file_url":"https://github.com/daviddcho/supermario/blob/HEAD/model.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":"e65d2c13d9aa7641"}},{"code_sha256_prefix":"51cf7eff17d1081c","entry":"DQN","repo":"gordicaleksa/pytorch-learn-reinforcement-learning","repo_kind":"listed","path":"models/definitions/DQN.py","file_url":"https://github.com/gordicaleksa/pytorch-learn-reinforcement-learning/blob/HEAD/models/definitions/DQN.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":"51cf7eff17d1081c"}},{"code_sha256_prefix":"7ac5ee56c6e889b6","entry":"DQN","repo":"K-tang-mkv/baseRLAlgorithm","repo_kind":"listed","path":"algorithms/DQN_pytorch_offical/dqn.py","file_url":"https://github.com/K-tang-mkv/baseRLAlgorithm/blob/HEAD/algorithms/DQN_pytorch_offical/dqn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7ac5ee56c6e889b6"}},{"code_sha256_prefix":"c7a2e9b74e4de596","entry":"DQN","repo":"vincentpalma/DQN-for-CaRL","repo_kind":"listed","path":"dqn_training.py","file_url":"https://github.com/vincentpalma/DQN-for-CaRL/blob/HEAD/dqn_training.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c7a2e9b74e4de596"}},{"code_sha256_prefix":"9dc82f090fea3bda","entry":"DQN_Conv","repo":"kmdanielduan/DQN_Family_PyTorch","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/kmdanielduan/DQN_Family_PyTorch/blob/HEAD/networks.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":"9dc82f090fea3bda"}},{"code_sha256_prefix":"73b097a72c5ea2f5","entry":"DqnConvNet","repo":"michaelnny/deep_rl_zoo","repo_kind":"listed","path":"deep_rl_zoo/networks/value.py","file_url":"https://github.com/michaelnny/deep_rl_zoo/blob/HEAD/deep_rl_zoo/networks/value.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":"73b097a72c5ea2f5"}},{"code_sha256_prefix":"f67fec3bfe6045aa","entry":"DropoutNd","repo":"proroklab/popgym","repo_kind":"listed","path":"popgym/baselines/models/s4d.py","file_url":"https://github.com/proroklab/popgym/blob/HEAD/popgym/baselines/models/s4d.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":"f67fec3bfe6045aa"}},{"code_sha256_prefix":"8eceb653c628a651","entry":"DuelingDQN","repo":"SayhoKim/tetrisRL","repo_kind":"listed","path":"lib/models/ddqn.py","file_url":"https://github.com/SayhoKim/tetrisRL/blob/HEAD/lib/models/ddqn.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":"8eceb653c628a651"}},{"code_sha256_prefix":"f9118b06dae7f603","entry":"ExperienceReplay","repo":"BH4/Deep-Reinforcement-Learning","repo_kind":"listed","path":"Training/qlearn.py","file_url":"https://github.com/BH4/Deep-Reinforcement-Learning/blob/HEAD/Training/qlearn.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":"f9118b06dae7f603"}},{"code_sha256_prefix":"96164b4731db1134","entry":"ExperienceReplay","repo":"JonasRSV/DQNTensorflow","repo_kind":"listed","path":"dqn.py","file_url":"https://github.com/JonasRSV/DQNTensorflow/blob/HEAD/dqn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"96164b4731db1134"}},{"code_sha256_prefix":"373f5c8eb72337f4","entry":"IModel","repo":"TheFebrin/DeepRL-Pong","repo_kind":"listed","path":"models/dqn_model.py","file_url":"https://github.com/TheFebrin/DeepRL-Pong/blob/HEAD/models/dqn_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":"373f5c8eb72337f4"}},{"code_sha256_prefix":"ddd25e3de70197a2","entry":"LayerShapeLogger","repo":"tensorpack/tensorpack","repo_kind":"listed","path":"tensorpack/models/conv2d.py","file_url":"https://github.com/tensorpack/tensorpack/blob/HEAD/tensorpack/models/conv2d.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":"ddd25e3de70197a2"}},{"code_sha256_prefix":"400c752a0d8d06f7","entry":"LinearActivation","repo":"proroklab/popgym","repo_kind":"listed","path":"popgym/baselines/models/s4d.py","file_url":"https://github.com/proroklab/popgym/blob/HEAD/popgym/baselines/models/s4d.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":"400c752a0d8d06f7"}},{"code_sha256_prefix":"6734b023c48264d1","entry":"Linear_QNet","repo":"sourenaKhanzadeh/snakeAi","repo_kind":"listed","path":"model.py","file_url":"https://github.com/sourenaKhanzadeh/snakeAi/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6734b023c48264d1"}},{"code_sha256_prefix":"7af2befd6fd71b28","entry":"MLPNetwork","repo":"chandar-lab/RLHive","repo_kind":"listed","path":"hive/agents/qnets/atari/nature_atari_dqn.py","file_url":"https://github.com/chandar-lab/RLHive/blob/HEAD/hive/agents/qnets/atari/nature_atari_dqn.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":"7af2befd6fd71b28"}},{"code_sha256_prefix":"2e7175149cc42e4e","entry":"Model","repo":"TheFebrin/DeepRL-Pong","repo_kind":"listed","path":"models/dqn_model.py","file_url":"https://github.com/TheFebrin/DeepRL-Pong/blob/HEAD/models/dqn_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":"2e7175149cc42e4e"}},{"code_sha256_prefix":"0387692d5cb08179","entry":"Model","repo":"labmlai/annotated_deep_learning_paper_implementations","repo_kind":"listed","path":"labml_nn/rl/dqn/model.py","file_url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/HEAD/labml_nn/rl/dqn/model.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":"0387692d5cb08179"}},{"code_sha256_prefix":"c448520babac98f1","entry":"NatureCnnBackboneNet","repo":"michaelnny/deep_rl_zoo","repo_kind":"listed","path":"deep_rl_zoo/networks/value.py","file_url":"https://github.com/michaelnny/deep_rl_zoo/blob/HEAD/deep_rl_zoo/networks/value.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":"c448520babac98f1"}},{"code_sha256_prefix":"93b98bd6ec8a54eb","entry":"Net","repo":"OscarHuangWind/Preference-Guided-DQN-Atari","repo_kind":"listed","path":"Network.py","file_url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari/blob/HEAD/Network.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":"93b98bd6ec8a54eb"}},{"code_sha256_prefix":"e2d32d93aef8dd96","entry":"NoisyLinear","repo":"chandar-lab/RLHive","repo_kind":"listed","path":"hive/agents/qnets/atari/nature_atari_dqn.py","file_url":"https://github.com/chandar-lab/RLHive/blob/HEAD/hive/agents/qnets/atari/nature_atari_dqn.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":"e2d32d93aef8dd96"}},{"code_sha256_prefix":"391471b2e6f9888c","entry":"QNetwork","repo":"Linging/Traffic-Signal-Control","repo_kind":"listed","path":"Agent/networks.py","file_url":"https://github.com/Linging/Traffic-Signal-Control/blob/HEAD/Agent/networks.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":"391471b2e6f9888c"}},{"code_sha256_prefix":"770e704a180ff720","entry":"RLNetwork","repo":"komejisatori/ReinforcementCar","repo_kind":"listed","path":"model/network.py","file_url":"https://github.com/komejisatori/ReinforcementCar/blob/HEAD/model/network.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":"770e704a180ff720"}},{"code_sha256_prefix":"cb2515fde4e1a0e0","entry":"ResidualBlock","repo":"Sheepsody/Batched-Impala-PyTorch","repo_kind":"listed","path":"src/networks/ActorCritic.py","file_url":"https://github.com/Sheepsody/Batched-Impala-PyTorch/blob/HEAD/src/networks/ActorCritic.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":"cb2515fde4e1a0e0"}},{"code_sha256_prefix":"3298a4358c400287","entry":"ShallowConv","repo":"Sheepsody/Batched-Impala-PyTorch","repo_kind":"listed","path":"src/networks/ActorCritic.py","file_url":"https://github.com/Sheepsody/Batched-Impala-PyTorch/blob/HEAD/src/networks/ActorCritic.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":"3298a4358c400287"}},{"code_sha256_prefix":"54e74edb75cc6f83","entry":"Training","repo":"BH4/Deep-Reinforcement-Learning","repo_kind":"listed","path":"Training/qlearn.py","file_url":"https://github.com/BH4/Deep-Reinforcement-Learning/blob/HEAD/Training/qlearn.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":"54e74edb75cc6f83"}},{"code_sha256_prefix":"a1061c9f352373b7","entry":"VariableHolder","repo":"tensorpack/tensorpack","repo_kind":"listed","path":"tensorpack/models/conv2d.py","file_url":"https://github.com/tensorpack/tensorpack/blob/HEAD/tensorpack/models/conv2d.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":"a1061c9f352373b7"}},{"code_sha256_prefix":"18e2a7b2917f4571","entry":"_output_size_conv2d","repo":"Sheepsody/Batched-Impala-PyTorch","repo_kind":"listed","path":"src/networks/ActorCritic.py","file_url":"https://github.com/Sheepsody/Batched-Impala-PyTorch/blob/HEAD/src/networks/ActorCritic.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"18e2a7b2917f4571"}},{"code_sha256_prefix":"bff3b19f646bee04","entry":"base_name","repo":"parilo/rl-server","repo_kind":"listed","path":"tf_rl/conv_model.py","file_url":"https://github.com/parilo/rl-server/blob/HEAD/tf_rl/conv_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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bff3b19f646bee04"}},{"code_sha256_prefix":"dca827af2639f99d","entry":"base_name2","repo":"parilo/rl-server","repo_kind":"listed","path":"tf_rl/conv_model.py","file_url":"https://github.com/parilo/rl-server/blob/HEAD/tf_rl/conv_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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dca827af2639f99d"}},{"code_sha256_prefix":"d09a6a1f1807cb36","entry":"build_q_network","repo":"eddynelson/dqn","repo_kind":"listed","path":"dqn/networks/dueling_network.py","file_url":"https://github.com/eddynelson/dqn/blob/HEAD/dqn/networks/dueling_network.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d09a6a1f1807cb36"}},{"code_sha256_prefix":"9c004a3c7f80a048","entry":"calc_conv2d_output","repo":"michaelnny/deep_rl_zoo","repo_kind":"listed","path":"deep_rl_zoo/networks/value.py","file_url":"https://github.com/michaelnny/deep_rl_zoo/blob/HEAD/deep_rl_zoo/networks/value.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9c004a3c7f80a048"}},{"code_sha256_prefix":"6ec20a43d727c364","entry":"calculate_output_dim","repo":"chandar-lab/RLHive","repo_kind":"listed","path":"hive/agents/qnets/atari/nature_atari_dqn.py","file_url":"https://github.com/chandar-lab/RLHive/blob/HEAD/hive/agents/qnets/atari/nature_atari_dqn.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ec20a43d727c364"}},{"code_sha256_prefix":"58a16fa9e75bc087","entry":"convert_to_tflayer_args","repo":"tensorpack/tensorpack","repo_kind":"listed","path":"tensorpack/models/conv2d.py","file_url":"https://github.com/tensorpack/tensorpack/blob/HEAD/tensorpack/models/conv2d.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"58a16fa9e75bc087"}},{"code_sha256_prefix":"b93a2d0046d7cf64","entry":"customBoard","repo":"invictos/InsacarDQN","repo_kind":"listed","path":"agent/agent.py","file_url":"https://github.com/invictos/InsacarDQN/blob/HEAD/agent/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b93a2d0046d7cf64"}},{"code_sha256_prefix":"391c3adc43a9fb2d","entry":"dplr","repo":"proroklab/popgym","repo_kind":"listed","path":"popgym/baselines/models/s4d.py","file_url":"https://github.com/proroklab/popgym/blob/HEAD/popgym/baselines/models/s4d.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":"391c3adc43a9fb2d"}},{"code_sha256_prefix":"143311d10e7d046c","entry":"flatten","repo":"alfredvc/paac","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/alfredvc/paac/blob/HEAD/networks.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"143311d10e7d046c"}},{"code_sha256_prefix":"e57b423feb455f31","entry":"get_data_format","repo":"tensorpack/tensorpack","repo_kind":"listed","path":"tensorpack/models/conv2d.py","file_url":"https://github.com/tensorpack/tensorpack/blob/HEAD/tensorpack/models/conv2d.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e57b423feb455f31"}},{"code_sha256_prefix":"436e0ec3f2b87eea","entry":"get_tf_version_tuple","repo":"tensorpack/tensorpack","repo_kind":"listed","path":"tensorpack/models/conv2d.py","file_url":"https://github.com/tensorpack/tensorpack/blob/HEAD/tensorpack/models/conv2d.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"436e0ec3f2b87eea"}},{"code_sha256_prefix":"eaf9a525f0459416","entry":"huber_loss","repo":"KavindaKottege/DeepQ-Pong","repo_kind":"listed","path":"DeepQ-Pong.py","file_url":"https://github.com/KavindaKottege/DeepQ-Pong/blob/HEAD/DeepQ-Pong.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":"eaf9a525f0459416"}},{"code_sha256_prefix":"802a4fa23e5c7036","entry":"layer_register","repo":"tensorpack/tensorpack","repo_kind":"listed","path":"tensorpack/models/conv2d.py","file_url":"https://github.com/tensorpack/tensorpack/blob/HEAD/tensorpack/models/conv2d.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"802a4fa23e5c7036"}},{"code_sha256_prefix":"ac7dc76edd237aa9","entry":"map_common_tfargs","repo":"tensorpack/tensorpack","repo_kind":"listed","path":"tensorpack/models/conv2d.py","file_url":"https://github.com/tensorpack/tensorpack/blob/HEAD/tensorpack/models/conv2d.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ac7dc76edd237aa9"}},{"code_sha256_prefix":"1afb1d67cec9b38b","entry":"map_dqn_var","repo":"eublefar/dqn","repo_kind":"listed","path":"dqn.py","file_url":"https://github.com/eublefar/dqn/blob/HEAD/dqn.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":"1afb1d67cec9b38b"}},{"code_sha256_prefix":"634d6466b3771df7","entry":"neural_net","repo":"vsquareg/RL_ERA","repo_kind":"listed","path":"nn.py","file_url":"https://github.com/vsquareg/RL_ERA/blob/HEAD/nn.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"634d6466b3771df7"}},{"code_sha256_prefix":"08037869b6206d12","entry":"nplr","repo":"proroklab/popgym","repo_kind":"listed","path":"popgym/baselines/models/s4d.py","file_url":"https://github.com/proroklab/popgym/blob/HEAD/popgym/baselines/models/s4d.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":"08037869b6206d12"}},{"code_sha256_prefix":"14bcfdbb8473e4b3","entry":"power","repo":"proroklab/popgym","repo_kind":"listed","path":"popgym/baselines/models/s4d.py","file_url":"https://github.com/proroklab/popgym/blob/HEAD/popgym/baselines/models/s4d.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"14bcfdbb8473e4b3"}},{"code_sha256_prefix":"67e350096b3030fb","entry":"rank_correction","repo":"proroklab/popgym","repo_kind":"listed","path":"popgym/baselines/models/s4d.py","file_url":"https://github.com/proroklab/popgym/blob/HEAD/popgym/baselines/models/s4d.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"67e350096b3030fb"}},{"code_sha256_prefix":"8f8fae04132f94eb","entry":"shape2d","repo":"tensorpack/tensorpack","repo_kind":"listed","path":"tensorpack/models/conv2d.py","file_url":"https://github.com/tensorpack/tensorpack/blob/HEAD/tensorpack/models/conv2d.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8f8fae04132f94eb"}},{"code_sha256_prefix":"e97f3b4aab9510ab","entry":"shape4d","repo":"tensorpack/tensorpack","repo_kind":"listed","path":"tensorpack/models/conv2d.py","file_url":"https://github.com/tensorpack/tensorpack/blob/HEAD/tensorpack/models/conv2d.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e97f3b4aab9510ab"}},{"code_sha256_prefix":"d613b8ca99bc2295","entry":"transition","repo":"proroklab/popgym","repo_kind":"listed","path":"popgym/baselines/models/s4d.py","file_url":"https://github.com/proroklab/popgym/blob/HEAD/popgym/baselines/models/s4d.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":"d613b8ca99bc2295"}},{"code_sha256_prefix":"1f72577dd8ccaa95","entry":"zero_sum_loss","repo":"RLeike/connect-four","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/RLeike/connect-four/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1f72577dd8ccaa95"}},{"code_sha256_prefix":"26d04828131d058e","entry":"AbstractAgent","repo":"RLeike/connect-four","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/RLeike/connect-four/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":"26d04828131d058e"}},{"code_sha256_prefix":"623be0021af9cc32","entry":"ActionStateModel","repo":"marload/DeepRL-TensorFlow2","repo_kind":"listed","path":"DQN/DQN_Discrete.py","file_url":"https://github.com/marload/DeepRL-TensorFlow2/blob/HEAD/DQN/DQN_Discrete.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":"623be0021af9cc32"}},{"code_sha256_prefix":"9097edcc955ed803","entry":"ActorCriticLSTM","repo":"Sheepsody/Batched-Impala-PyTorch","repo_kind":"listed","path":"src/networks/ActorCritic.py","file_url":"https://github.com/Sheepsody/Batched-Impala-PyTorch/blob/HEAD/src/networks/ActorCritic.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":"9097edcc955ed803"}},{"code_sha256_prefix":"d16973e80e747353","entry":"BodyType","repo":"Sheepsody/Batched-Impala-PyTorch","repo_kind":"listed","path":"src/networks/ActorCritic.py","file_url":"https://github.com/Sheepsody/Batched-Impala-PyTorch/blob/HEAD/src/networks/ActorCritic.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":"d16973e80e747353"}},{"code_sha256_prefix":"ed92e17b3aae8048","entry":"CNN","repo":"FauzaanQureshi/deep-Q-learning","repo_kind":"listed","path":"CNN.py","file_url":"https://github.com/FauzaanQureshi/deep-Q-learning/blob/HEAD/CNN.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":"ed92e17b3aae8048"}},{"code_sha256_prefix":"986b511bd19889fc","entry":"CNN","repo":"parilo/rl-server","repo_kind":"listed","path":"tf_rl/conv_model.py","file_url":"https://github.com/parilo/rl-server/blob/HEAD/tf_rl/conv_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":"986b511bd19889fc"}},{"code_sha256_prefix":"39be9974e39c4007","entry":"CachingAgent","repo":"MateuszJanda/netris-ai-robot","repo_kind":"listed","path":"robot/agents/caching_agent.py","file_url":"https://github.com/MateuszJanda/netris-ai-robot/blob/HEAD/robot/agents/caching_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":"39be9974e39c4007"}},{"code_sha256_prefix":"c1adecea275c4a2d","entry":"Conv2D","repo":"tensorpack/tensorpack","repo_kind":"listed","path":"tensorpack/models/conv2d.py","file_url":"https://github.com/tensorpack/tensorpack/blob/HEAD/tensorpack/models/conv2d.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":"c1adecea275c4a2d"}},{"code_sha256_prefix":"c9bddbe2aee30eac","entry":"ConvNetwork","repo":"chandar-lab/RLHive","repo_kind":"listed","path":"hive/agents/qnets/atari/nature_atari_dqn.py","file_url":"https://github.com/chandar-lab/RLHive/blob/HEAD/hive/agents/qnets/atari/nature_atari_dqn.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":"c9bddbe2aee30eac"}},{"code_sha256_prefix":"7a2a672d94b88c2c","entry":"DQN","repo":"anita-hu/TF2-RL","repo_kind":"listed","path":"DQN/TF2_DQN_Basic.py","file_url":"https://github.com/anita-hu/TF2-RL/blob/HEAD/DQN/TF2_DQN_Basic.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":"7a2a672d94b88c2c"}},{"code_sha256_prefix":"5114ef5f140eab1f","entry":"DQN","repo":"eublefar/dqn","repo_kind":"listed","path":"dqn.py","file_url":"https://github.com/eublefar/dqn/blob/HEAD/dqn.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":"5114ef5f140eab1f"}},{"code_sha256_prefix":"01a1660b174e9811","entry":"DQN","repo":"JonasRSV/DQNTensorflow","repo_kind":"listed","path":"dqn.py","file_url":"https://github.com/JonasRSV/DQNTensorflow/blob/HEAD/dqn.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":"01a1660b174e9811"}},{"code_sha256_prefix":"b80d6818598d15d7","entry":"DQNAgent","repo":"yaxinchen666/dce_pricingRL","repo_kind":"listed","path":"dqn_s.py","file_url":"https://github.com/yaxinchen666/dce_pricingRL/blob/HEAD/dqn_s.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":"b80d6818598d15d7"}},{"code_sha256_prefix":"f09be9cc319f8b95","entry":"DQNBase","repo":"bay3s/dqn","repo_kind":"listed","path":"src/agents/dqn.py","file_url":"https://github.com/bay3s/dqn/blob/HEAD/src/agents/dqn.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":"f09be9cc319f8b95"}},{"code_sha256_prefix":"1e1c270d61b7ea4b","entry":"DeepConv","repo":"Sheepsody/Batched-Impala-PyTorch","repo_kind":"listed","path":"src/networks/ActorCritic.py","file_url":"https://github.com/Sheepsody/Batched-Impala-PyTorch/blob/HEAD/src/networks/ActorCritic.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":"1e1c270d61b7ea4b"}},{"code_sha256_prefix":"e7dc84f99d692574","entry":"DqnNetworkOutputs","repo":"michaelnny/deep_rl_zoo","repo_kind":"listed","path":"deep_rl_zoo/networks/value.py","file_url":"https://github.com/michaelnny/deep_rl_zoo/blob/HEAD/deep_rl_zoo/networks/value.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":"e7dc84f99d692574"}},{"code_sha256_prefix":"77ebfb9f870755e5","entry":"DuelingQ","repo":"nathanin/pad","repo_kind":"listed","path":"agent/models/duelingq.py","file_url":"https://github.com/nathanin/pad/blob/HEAD/agent/models/duelingq.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":"77ebfb9f870755e5"}},{"code_sha256_prefix":"82c4ff3ff8f63e05","entry":"FeedforwardAgent","repo":"RLeike/connect-four","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/RLeike/connect-four/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":"82c4ff3ff8f63e05"}},{"code_sha256_prefix":"13f78b113956d77f","entry":"Layer","repo":"parilo/rl-server","repo_kind":"listed","path":"tf_rl/conv_model.py","file_url":"https://github.com/parilo/rl-server/blob/HEAD/tf_rl/conv_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":"13f78b113956d77f"}},{"code_sha256_prefix":"15169eebbda3dcc8","entry":"MLP","repo":"parilo/rl-server","repo_kind":"listed","path":"tf_rl/conv_model.py","file_url":"https://github.com/parilo/rl-server/blob/HEAD/tf_rl/conv_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":"15169eebbda3dcc8"}},{"code_sha256_prefix":"0f47d6422b2c5369","entry":"Model","repo":"InSpaceAI/RL-Zoo","repo_kind":"listed","path":"DQN.py","file_url":"https://github.com/InSpaceAI/RL-Zoo/blob/HEAD/DQN.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":"0f47d6422b2c5369"}},{"code_sha256_prefix":"85acd99c58ce6d0c","entry":"NatureAtariDQNModel","repo":"chandar-lab/RLHive","repo_kind":"listed","path":"hive/agents/qnets/atari/nature_atari_dqn.py","file_url":"https://github.com/chandar-lab/RLHive/blob/HEAD/hive/agents/qnets/atari/nature_atari_dqn.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":"85acd99c58ce6d0c"}},{"code_sha256_prefix":"dc3336e8f1fdf44a","entry":"NatureNetwork","repo":"alfredvc/paac","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/alfredvc/paac/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"dc3336e8f1fdf44a"}},{"code_sha256_prefix":"e53b0eb94184ff85","entry":"Network","repo":"alfredvc/paac","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/alfredvc/paac/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e53b0eb94184ff85"}},{"code_sha256_prefix":"ee0b2a23c9478bfc","entry":"Network","repo":"sunjeet95/Deep-Q-Network-using-Tensorflow","repo_kind":"listed","path":"main_cartpole.py","file_url":"https://github.com/sunjeet95/Deep-Q-Network-using-Tensorflow/blob/HEAD/main_cartpole.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":"ee0b2a23c9478bfc"}},{"code_sha256_prefix":"30e46a646e08a7d8","entry":"OptimModule","repo":"proroklab/popgym","repo_kind":"listed","path":"popgym/baselines/models/s4d.py","file_url":"https://github.com/proroklab/popgym/blob/HEAD/popgym/baselines/models/s4d.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":"30e46a646e08a7d8"}},{"code_sha256_prefix":"0e08e7a4d7c5d8b2","entry":"QAgent","repo":"LukasGardberg/cartpole","repo_kind":"listed","path":"carpole_train.py","file_url":"https://github.com/LukasGardberg/cartpole/blob/HEAD/carpole_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":"0e08e7a4d7c5d8b2"}},{"code_sha256_prefix":"42f3816a2d486c1a","entry":"QEstimator","repo":"filippogiruzzi/deep_q_learning","repo_kind":"listed","path":"dqn/models/estimators.py","file_url":"https://github.com/filippogiruzzi/deep_q_learning/blob/HEAD/dqn/models/estimators.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":"42f3816a2d486c1a"}},{"code_sha256_prefix":"7f1cd947395254b0","entry":"QNetworkNIPS","repo":"Linging/Traffic-Signal-Control","repo_kind":"listed","path":"Agent/networks.py","file_url":"https://github.com/Linging/Traffic-Signal-Control/blob/HEAD/Agent/networks.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":"7f1cd947395254b0"}},{"code_sha256_prefix":"92a00d39074b7d60","entry":"Replay","repo":"bay3s/dqn","repo_kind":"listed","path":"src/agents/dqn.py","file_url":"https://github.com/bay3s/dqn/blob/HEAD/src/agents/dqn.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":"92a00d39074b7d60"}},{"code_sha256_prefix":"58ded9af82892cc0","entry":"S4","repo":"proroklab/popgym","repo_kind":"listed","path":"popgym/baselines/models/s4d.py","file_url":"https://github.com/proroklab/popgym/blob/HEAD/popgym/baselines/models/s4d.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":"58ded9af82892cc0"}},{"code_sha256_prefix":"89b4b37f6d5d8c72","entry":"SSKernel","repo":"proroklab/popgym","repo_kind":"listed","path":"popgym/baselines/models/s4d.py","file_url":"https://github.com/proroklab/popgym/blob/HEAD/popgym/baselines/models/s4d.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":"89b4b37f6d5d8c72"}},{"code_sha256_prefix":"d78e88b5a6d2c2b1","entry":"SSKernelDiag","repo":"proroklab/popgym","repo_kind":"listed","path":"popgym/baselines/models/s4d.py","file_url":"https://github.com/proroklab/popgym/blob/HEAD/popgym/baselines/models/s4d.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":"d78e88b5a6d2c2b1"}},{"code_sha256_prefix":"6f34cfb42a2fac86","entry":"SSKernelNPLR","repo":"proroklab/popgym","repo_kind":"listed","path":"popgym/baselines/models/s4d.py","file_url":"https://github.com/proroklab/popgym/blob/HEAD/popgym/baselines/models/s4d.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":"6f34cfb42a2fac86"}},{"code_sha256_prefix":"7a20c93d8aa9f48b","entry":"_register","repo":"tensorpack/tensorpack","repo_kind":"listed","path":"tensorpack/models/conv2d.py","file_url":"https://github.com/tensorpack/tensorpack/blob/HEAD/tensorpack/models/conv2d.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":"7a20c93d8aa9f48b"}},{"code_sha256_prefix":"d2c233a4e64933cb","entry":"agent","repo":"invictos/InsacarDQN","repo_kind":"listed","path":"agent/agent.py","file_url":"https://github.com/invictos/InsacarDQN/blob/HEAD/agent/agent.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":"d2c233a4e64933cb"}},{"code_sha256_prefix":"e444b6d743c4c506","entry":"atariAgent","repo":"ninja18/AtariDQN","repo_kind":"listed","path":"DQNModel.py","file_url":"https://github.com/ninja18/AtariDQN/blob/HEAD/DQNModel.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":"e444b6d743c4c506"}},{"code_sha256_prefix":"21077a0a5bf80f4e","entry":"atari_model","repo":"KavindaKottege/DeepQ-Pong","repo_kind":"listed","path":"DeepQ-Pong.py","file_url":"https://github.com/KavindaKottege/DeepQ-Pong/blob/HEAD/DeepQ-Pong.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":"21077a0a5bf80f4e"}},{"code_sha256_prefix":"4d830cd514f6cb32","entry":"combination","repo":"proroklab/popgym","repo_kind":"listed","path":"popgym/baselines/models/s4d.py","file_url":"https://github.com/proroklab/popgym/blob/HEAD/popgym/baselines/models/s4d.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":"4d830cd514f6cb32"}},{"code_sha256_prefix":"4577713d4b86ef2b","entry":"conv2d","repo":"alfredvc/paac","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/alfredvc/paac/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4577713d4b86ef2b"}},{"code_sha256_prefix":"8e415301ac3c74a1","entry":"conv_bias_variable","repo":"alfredvc/paac","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/alfredvc/paac/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8e415301ac3c74a1"}},{"code_sha256_prefix":"4f7455bb7e545246","entry":"conv_network","repo":"jonaths/dqn-grid","repo_kind":"listed","path":"networks/qnetworks.py","file_url":"https://github.com/jonaths/dqn-grid/blob/HEAD/networks/qnetworks.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":"4f7455bb7e545246"}},{"code_sha256_prefix":"8d6b5d3084a9d52f","entry":"conv_weight_variable","repo":"alfredvc/paac","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/alfredvc/paac/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8d6b5d3084a9d52f"}},{"code_sha256_prefix":"8852f55a6471cb78","entry":"exp_replay","repo":"Anshu1245/RL-CourseProject","repo_kind":"listed","path":"DQN/dqn.py","file_url":"https://github.com/Anshu1245/RL-CourseProject/blob/HEAD/DQN/dqn.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":"8852f55a6471cb78"}},{"code_sha256_prefix":"11c5727aaabe378a","entry":"fc","repo":"alfredvc/paac","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/alfredvc/paac/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"11c5727aaabe378a"}},{"code_sha256_prefix":"77ef8402d44c461b","entry":"fc_bias_variable","repo":"alfredvc/paac","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/alfredvc/paac/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"77ef8402d44c461b"}},{"code_sha256_prefix":"4519c6fdfa92a307","entry":"fc_weight_variable","repo":"alfredvc/paac","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/alfredvc/paac/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4519c6fdfa92a307"}},{"code_sha256_prefix":"1e29c6e3df986421","entry":"image_number","repo":"tlohr/nfsu2-ai","repo_kind":"listed","path":"CreateDataSet.py","file_url":"https://github.com/tlohr/nfsu2-ai/blob/HEAD/CreateDataSet.py","link_basis":"harvester_set","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":"1e29c6e3df986421"}},{"code_sha256_prefix":"3f487113acd567b9","entry":"initialize_weights","repo":"michaelnny/deep_rl_zoo","repo_kind":"listed","path":"deep_rl_zoo/networks/value.py","file_url":"https://github.com/michaelnny/deep_rl_zoo/blob/HEAD/deep_rl_zoo/networks/value.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":"3f487113acd567b9"}},{"code_sha256_prefix":"eecf538e06851adc","entry":"log_once","repo":"tensorpack/tensorpack","repo_kind":"listed","path":"tensorpack/models/conv2d.py","file_url":"https://github.com/tensorpack/tensorpack/blob/HEAD/tensorpack/models/conv2d.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":"eecf538e06851adc"}},{"code_sha256_prefix":"8f9da127eceb2a1d","entry":"make_model","repo":"rishavb123/MineRL","repo_kind":"listed","path":"model.py","file_url":"https://github.com/rishavb123/MineRL/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":"8f9da127eceb2a1d"}},{"code_sha256_prefix":"a8cd6ded600d9813","entry":"module","repo":"epignatelli/human-level-control-through-deep-reinforcement-learning","repo_kind":"listed","path":"dqn/base.py","file_url":"https://github.com/epignatelli/human-level-control-through-deep-reinforcement-learning/blob/HEAD/dqn/base.py","link_basis":"harvester_set","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":"a8cd6ded600d9813"}},{"code_sha256_prefix":"215e80576955e5a8","entry":"movingaverage","repo":"borhanreo/Obstacle-Avoid-Car","repo_kind":"listed","path":"plotting.py","file_url":"https://github.com/borhanreo/Obstacle-Avoid-Car/blob/HEAD/plotting.py","link_basis":"harvester_set","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":"215e80576955e5a8"}},{"code_sha256_prefix":"3d3d55b5d8bd5963","entry":"params_to_filename","repo":"borhanreo/Obstacle-Avoid-Car","repo_kind":"listed","path":"learning.py","file_url":"https://github.com/borhanreo/Obstacle-Avoid-Car/blob/HEAD/learning.py","link_basis":"harvester_set","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":"3d3d55b5d8bd5963"}},{"code_sha256_prefix":"57c6b35d80e952e1","entry":"process_args","repo":"spragunr/deep_q_rl","repo_kind":"listed","path":"deep_q_rl/launcher.py","file_url":"https://github.com/spragunr/deep_q_rl/blob/HEAD/deep_q_rl/launcher.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"57c6b35d80e952e1"}},{"code_sha256_prefix":"5448b18f64386fdb","entry":"process_minibatch","repo":"borhanreo/Obstacle-Avoid-Car","repo_kind":"listed","path":"learning.py","file_url":"https://github.com/borhanreo/Obstacle-Avoid-Car/blob/HEAD/learning.py","link_basis":"harvester_set","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":"5448b18f64386fdb"}},{"code_sha256_prefix":"316b3c2ef7ed0d5e","entry":"process_minibatch2","repo":"borhanreo/Obstacle-Avoid-Car","repo_kind":"listed","path":"learning.py","file_url":"https://github.com/borhanreo/Obstacle-Avoid-Car/blob/HEAD/learning.py","link_basis":"harvester_set","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":"316b3c2ef7ed0d5e"}},{"code_sha256_prefix":"8987d3556f2dbdbe","entry":"readable_output","repo":"borhanreo/Obstacle-Avoid-Car","repo_kind":"listed","path":"plotting.py","file_url":"https://github.com/borhanreo/Obstacle-Avoid-Car/blob/HEAD/plotting.py","link_basis":"harvester_set","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":"8987d3556f2dbdbe"}},{"code_sha256_prefix":"00500c0bcb8ead09","entry":"rename_get_variable","repo":"tensorpack/tensorpack","repo_kind":"listed","path":"tensorpack/models/conv2d.py","file_url":"https://github.com/tensorpack/tensorpack/blob/HEAD/tensorpack/models/conv2d.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":"00500c0bcb8ead09"}},{"code_sha256_prefix":"df21990110979f81","entry":"sample_memories","repo":"jonaths/tf-dqn","repo_kind":"listed","path":"tiny_dqn.py","file_url":"https://github.com/jonaths/tf-dqn/blob/HEAD/tiny_dqn.py","link_basis":"harvester_set","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":"df21990110979f81"}},{"code_sha256_prefix":"284562b888d37de3","entry":"ssm","repo":"proroklab/popgym","repo_kind":"listed","path":"popgym/baselines/models/s4d.py","file_url":"https://github.com/proroklab/popgym/blob/HEAD/popgym/baselines/models/s4d.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":"284562b888d37de3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}