{"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/deep-reinforcement-learning-with-double-q","title":"Deep Reinforcement Learning with Double Q-learning","arxiv_id":"1509.06461","date":"2015-09-22","proceeding":null,"authors":["Hado van Hasselt","Arthur Guez","David Silver"],"abstract":"The popular Q-learning algorithm is known to overestimate action values under\ncertain conditions. It was not previously known whether, in practice, such\noverestimations are common, whether they harm performance, and whether they can\ngenerally be prevented. In this paper, we answer all these questions\naffirmatively. In particular, we first show that the recent DQN algorithm,\nwhich combines Q-learning with a deep neural network, suffers from substantial\noverestimations in some games in the Atari 2600 domain. We then show that the\nidea behind the Double Q-learning algorithm, which was introduced in a tabular\nsetting, can be generalized to work with large-scale function approximation. We\npropose a specific adaptation to the DQN algorithm and show that the resulting\nalgorithm not only reduces the observed overestimations, as hypothesized, but\nthat this also leads to much better performance on several games.","url_abs":"http://arxiv.org/abs/1509.06461v3","url_pdf":"http://arxiv.org/pdf/1509.06461v3.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":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/1jsingh/rl_navigation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/Adrelf/DRL-navigation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/Codernauti/Exploration-of-DQN-in-CartPole-Environment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/Curt-Park/rainbow-is-all-you-need","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/Denbergvanthijs/imbDRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/FaboNo/DRLND","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/HussonnoisMaxence/RL_Algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/JonasRSV/DQNTensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/JustinStitt/acrobotDDQN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/KelvinYang0320/deepbots-panda","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/MOVzeroOne/DQN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/NikolausBerl/Udacity_DRLN_Navigation_Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/PeterJochem/Deep_RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/PeterJochem/Double_Deep_QLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/Roman-Kozachek/TradeBot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/SayhoKim/tetrisRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/YuansongFeng/MadMario","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/ZainRaza14/deepRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/aman-khurana/deep-q-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/amirmirzaei79/CartPole-DQN-And-DDQN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/anh-nn01/Lunar-Lander-Double-Deep-Q-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/atavakol/action-branching-agents","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/austinsilveria/Banana-Collection-DQN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/botforge/simplementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/chainer/chainerrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/cove9988/TradingGym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/daviddcho/supermario","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/dxyang/DQN_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/fengsterooni/dql","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/guillaumeboniface/bananaland","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/gznyyb/deep_reinforcement_learning_Pong","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/ianlimle/ItsMeMario","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/ifestus/rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/jadag/DDQN_mario","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/jeffery1236/Atari_DoubleDeepQNetwork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/jezzarax/drlnd_p1_navigation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/jvoynow/DQN-analysis-with-2048","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/kochlisGit/autonomous-vehicles-agent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/matthewsparr/Deep-Zork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/microsoft/med-deadend","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/mightypirate1/DRL-Tetris","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/mindspore-courses/Rainbow-MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/moduIo/Deep-Q-network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/mohit8935/Deep-Q-Learning-Paper","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/molomono/CartPole_Optimized_DDQN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/nbopardi/smb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/near32/regym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/pathway/alphaxos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/puppetect/TradingBot-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/rybread1/DeepRlTrex","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/rybread1/deep-rl-trex","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/seacevedo/ReinforcementLearningProjects","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/shashwatsaxena571/DRL-navigation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/shehrum/RL_Navigation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/ssainz/reinforcement_learning_algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/tensorlayer/RLzoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/tkcoding/DeepRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/tkcoding/Stock_DRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/utarumo/RL_implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/wmol4/Pytorch_DDQN_Unity_Navigation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/wtingda/DeepRLBreakout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/xgfelicia/Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/yukezhu/tensorflow-reinforce","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/yzheng51/rl-dino-run","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/zhengant/dqn_reversi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Deep_Reinforcement_Learning_with_Double_Q_learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/deepmind/rlax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","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":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/opendilab/DI-engine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-with-double-q","repo_url":"https://github.com/toni-sm/skrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep 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":null,"method_name":null},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"ddql","method_name":"DDQL"},{"method_slug":"dqn","method_name":"DQN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"double-dqn","method_name":"Double DQN"},{"method_slug":"double-q-learning","method_name":"Double Q-learning"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"q-learning","method_name":"Q-Learning"},{"method_slug":null,"method_name":"Your Ultimate Guide to JFK International Airport Arrivals at Terminal 7"}],"datasets_introduced":[],"methods_introduced":[{"slug":"ddql","name":"DDQL","full_name":"Double Deep Q-Learning"}],"results":[{"leaderboard":"/sota/atari-games-on-atari-2600-alien","task":"Atari Games","dataset":"Atari 2600 Alien","model":"DQN noop","rank_in_archive_order":31,"of":49,"metrics":{"Score":"1620.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-alien","task":"Atari Games","dataset":"Atari 2600 Alien","model":"DDQN (tuned) hs","rank_in_archive_order":38,"of":49,"metrics":{"Score":"1033.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-alien","task":"Atari Games","dataset":"Atari 2600 Alien","model":"Prior+Duel hs","rank_in_archive_order":42,"of":49,"metrics":{"Score":"823.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-alien","task":"Atari Games","dataset":"Atari 2600 Alien","model":"DQN hs","rank_in_archive_order":45,"of":49,"metrics":{"Score":"634.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-amidar","task":"Atari Games","dataset":"Atari 2600 Amidar","model":"DQN noop","rank_in_archive_order":26,"of":48,"metrics":{"Score":"978.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-amidar","task":"Atari Games","dataset":"Atari 2600 Amidar","model":"Prior+Duel hs","rank_in_archive_order":34,"of":48,"metrics":{"Score":"238.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-amidar","task":"Atari Games","dataset":"Atari 2600 Amidar","model":"DQN hs","rank_in_archive_order":41,"of":48,"metrics":{"Score":"178.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-amidar","task":"Atari Games","dataset":"Atari 2600 Amidar","model":"DDQN (tuned) hs","rank_in_archive_order":44,"of":48,"metrics":{"Score":"169.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-assault","task":"Atari Games","dataset":"Atari 2600 Assault","model":"Prior+Duel hs","rank_in_archive_order":17,"of":45,"metrics":{"Score":"10950.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-assault","task":"Atari Games","dataset":"Atari 2600 Assault","model":"DDQN (tuned) hs","rank_in_archive_order":25,"of":45,"metrics":{"Score":"6060.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-assault","task":"Atari Games","dataset":"Atari 2600 Assault","model":"DQN noop","rank_in_archive_order":30,"of":45,"metrics":{"Score":"4280.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-assault","task":"Atari Games","dataset":"Atari 2600 Assault","model":"DQN hs","rank_in_archive_order":34,"of":45,"metrics":{"Score":"3489.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asterix","task":"Atari Games","dataset":"Atari 2600 Asterix","model":"Prior+Duel hs","rank_in_archive_order":11,"of":49,"metrics":{"Score":"364200.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asterix","task":"Atari Games","dataset":"Atari 2600 Asterix","model":"DDQN (tuned) hs","rank_in_archive_order":34,"of":49,"metrics":{"Score":"16837.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asterix","task":"Atari Games","dataset":"Atari 2600 Asterix","model":"DQN noop","rank_in_archive_order":40,"of":49,"metrics":{"Score":"4359.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asterix","task":"Atari Games","dataset":"Atari 2600 Asterix","model":"DQN hs","rank_in_archive_order":43,"of":49,"metrics":{"Score":"3170.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asteroids","task":"Atari Games","dataset":"Atari 2600 Asteroids","model":"DQN hs","rank_in_archive_order":34,"of":43,"metrics":{"Score":"1458.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asteroids","task":"Atari Games","dataset":"Atari 2600 Asteroids","model":"DQN noop","rank_in_archive_order":35,"of":43,"metrics":{"Score":"1364.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asteroids","task":"Atari Games","dataset":"Atari 2600 Asteroids","model":"DDQN (tuned) hs","rank_in_archive_order":36,"of":43,"metrics":{"Score":"1193.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asteroids","task":"Atari Games","dataset":"Atari 2600 Asteroids","model":"Prior+Duel hs","rank_in_archive_order":39,"of":43,"metrics":{"Score":"1021.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-atlantis","task":"Atari Games","dataset":"Atari 2600 Atlantis","model":"Prior+Duel hs","rank_in_archive_order":27,"of":42,"metrics":{"Score":"423252.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-atlantis","task":"Atari Games","dataset":"Atari 2600 Atlantis","model":"DDQN (tuned) hs","rank_in_archive_order":33,"of":42,"metrics":{"Score":"319688.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-atlantis","task":"Atari Games","dataset":"Atari 2600 Atlantis","model":"DQN hs","rank_in_archive_order":35,"of":42,"metrics":{"Score":"292491.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-atlantis","task":"Atari Games","dataset":"Atari 2600 Atlantis","model":"DQN noop","rank_in_archive_order":36,"of":42,"metrics":{"Score":"279987.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bank-heist","task":"Atari Games","dataset":"Atari 2600 Bank Heist","model":"Prior+Duel hs","rank_in_archive_order":25,"of":45,"metrics":{"Score":"1004.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bank-heist","task":"Atari Games","dataset":"Atari 2600 Bank Heist","model":"DDQN (tuned) hs","rank_in_archive_order":30,"of":45,"metrics":{"Score":"886.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bank-heist","task":"Atari Games","dataset":"Atari 2600 Bank Heist","model":"DQN noop","rank_in_archive_order":35,"of":45,"metrics":{"Score":"455.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bank-heist","task":"Atari Games","dataset":"Atari 2600 Bank Heist","model":"DQN hs","rank_in_archive_order":38,"of":45,"metrics":{"Score":"312.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-battle-zone","task":"Atari Games","dataset":"Atari 2600 Battle Zone","model":"Prior+Duel hs","rank_in_archive_order":25,"of":47,"metrics":{"Score":"30650.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-battle-zone","task":"Atari Games","dataset":"Atari 2600 Battle Zone","model":"DQN noop","rank_in_archive_order":26,"of":47,"metrics":{"Score":"29900.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-battle-zone","task":"Atari Games","dataset":"Atari 2600 Battle Zone","model":"DDQN (tuned) hs","rank_in_archive_order":33,"of":47,"metrics":{"Score":"24740.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-battle-zone","task":"Atari Games","dataset":"Atari 2600 Battle Zone","model":"DQN hs","rank_in_archive_order":34,"of":47,"metrics":{"Score":"23750.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-beam-rider","task":"Atari Games","dataset":"Atari 2600 Beam Rider","model":"Prior+Duel hs","rank_in_archive_order":10,"of":49,"metrics":{"Score":"37412.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-beam-rider","task":"Atari Games","dataset":"Atari 2600 Beam Rider","model":"DDQN (tuned) hs","rank_in_archive_order":23,"of":49,"metrics":{"Score":"17417.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-beam-rider","task":"Atari Games","dataset":"Atari 2600 Beam Rider","model":"DQN hs","rank_in_archive_order":33,"of":49,"metrics":{"Score":"9743.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-beam-rider","task":"Atari Games","dataset":"Atari 2600 Beam Rider","model":"DQN noop","rank_in_archive_order":34,"of":49,"metrics":{"Score":"8627.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-berzerk","task":"Atari Games","dataset":"Atari 2600 Berzerk","model":"Prior+Duel hs","rank_in_archive_order":16,"of":39,"metrics":{"Score":"2178.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-berzerk","task":"Atari Games","dataset":"Atari 2600 Berzerk","model":"DDQN (tuned) hs","rank_in_archive_order":28,"of":39,"metrics":{"Score":"1011.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-berzerk","task":"Atari Games","dataset":"Atari 2600 Berzerk","model":"DQN noop","rank_in_archive_order":37,"of":39,"metrics":{"Score":"585.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-berzerk","task":"Atari Games","dataset":"Atari 2600 Berzerk","model":"DQN hs","rank_in_archive_order":39,"of":39,"metrics":{"Score":"493.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bowling","task":"Atari Games","dataset":"Atari 2600 Bowling","model":"DDQN (tuned) hs","rank_in_archive_order":19,"of":44,"metrics":{"Score":"69.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bowling","task":"Atari Games","dataset":"Atari 2600 Bowling","model":"DQN hs","rank_in_archive_order":27,"of":44,"metrics":{"Score":"56.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bowling","task":"Atari Games","dataset":"Atari 2600 Bowling","model":"DQN noop","rank_in_archive_order":30,"of":44,"metrics":{"Score":"50.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bowling","task":"Atari Games","dataset":"Atari 2600 Bowling","model":"Prior+Duel hs","rank_in_archive_order":31,"of":44,"metrics":{"Score":"50.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-boxing","task":"Atari Games","dataset":"Atari 2600 Boxing","model":"DQN noop","rank_in_archive_order":30,"of":45,"metrics":{"Score":"88.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-boxing","task":"Atari Games","dataset":"Atari 2600 Boxing","model":"Prior+Duel hs","rank_in_archive_order":31,"of":45,"metrics":{"Score":"79.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-boxing","task":"Atari Games","dataset":"Atari 2600 Boxing","model":"DDQN (tuned) hs","rank_in_archive_order":34,"of":45,"metrics":{"Score":"73.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-boxing","task":"Atari Games","dataset":"Atari 2600 Boxing","model":"DQN hs","rank_in_archive_order":37,"of":45,"metrics":{"Score":"70.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-breakout","task":"Atari Games","dataset":"Atari 2600 Breakout","model":"DQN noop","rank_in_archive_order":28,"of":58,"metrics":{"Score":"385.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-breakout","task":"Atari Games","dataset":"Atari 2600 Breakout","model":"DDQN (tuned) hs","rank_in_archive_order":31,"of":58,"metrics":{"Score":"368.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-breakout","task":"Atari Games","dataset":"Atari 2600 Breakout","model":"Prior+Duel hs","rank_in_archive_order":34,"of":58,"metrics":{"Score":"354.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-breakout","task":"Atari Games","dataset":"Atari 2600 Breakout","model":"DQN hs","rank_in_archive_order":35,"of":58,"metrics":{"Score":"354.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-centipede","task":"Atari Games","dataset":"Atari 2600 Centipede","model":"Prior+Duel hs","rank_in_archive_order":28,"of":45,"metrics":{"Score":"5570.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-centipede","task":"Atari Games","dataset":"Atari 2600 Centipede","model":"DQN noop","rank_in_archive_order":31,"of":45,"metrics":{"Score":"4657.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-centipede","task":"Atari Games","dataset":"Atari 2600 Centipede","model":"DQN hs","rank_in_archive_order":37,"of":45,"metrics":{"Score":"3973.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-centipede","task":"Atari Games","dataset":"Atari 2600 Centipede","model":"DDQN (tuned) hs","rank_in_archive_order":39,"of":45,"metrics":{"Score":"3853.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-chopper-command","task":"Atari Games","dataset":"Atari 2600 Chopper Command","model":"Prior+Duel hs","rank_in_archive_order":22,"of":45,"metrics":{"Score":"8058.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-chopper-command","task":"Atari Games","dataset":"Atari 2600 Chopper Command","model":"DQN noop","rank_in_archive_order":27,"of":45,"metrics":{"Score":"6126.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-chopper-command","task":"Atari Games","dataset":"Atari 2600 Chopper Command","model":"DQN hs","rank_in_archive_order":32,"of":45,"metrics":{"Score":"5017.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-chopper-command","task":"Atari Games","dataset":"Atari 2600 Chopper Command","model":"DDQN (tuned) hs","rank_in_archive_order":39,"of":45,"metrics":{"Score":"3495.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-crazy-climber","task":"Atari Games","dataset":"Atari 2600 Crazy Climber","model":"Prior+Duel hs","rank_in_archive_order":26,"of":49,"metrics":{"Score":"127853.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-crazy-climber","task":"Atari Games","dataset":"Atari 2600 Crazy Climber","model":"DDQN (tuned) hs","rank_in_archive_order":34,"of":49,"metrics":{"Score":"113782.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-crazy-climber","task":"Atari Games","dataset":"Atari 2600 Crazy Climber","model":"DQN noop","rank_in_archive_order":36,"of":49,"metrics":{"Score":"110763.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-crazy-climber","task":"Atari Games","dataset":"Atari 2600 Crazy Climber","model":"DQN hs","rank_in_archive_order":39,"of":49,"metrics":{"Score":"98128.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-demon-attack","task":"Atari Games","dataset":"Atari 2600 Demon Attack","model":"Prior+Duel hs","rank_in_archive_order":22,"of":46,"metrics":{"Score":"73371.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-demon-attack","task":"Atari Games","dataset":"Atari 2600 Demon Attack","model":"DDQN (tuned) hs","rank_in_archive_order":26,"of":46,"metrics":{"Score":"69803.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-demon-attack","task":"Atari Games","dataset":"Atari 2600 Demon Attack","model":"DQN hs","rank_in_archive_order":37,"of":46,"metrics":{"Score":"12550.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-demon-attack","task":"Atari Games","dataset":"Atari 2600 Demon Attack","model":"DQN noop","rank_in_archive_order":38,"of":46,"metrics":{"Score":"12149.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-double-dunk","task":"Atari Games","dataset":"Atari 2600 Double Dunk","model":"DQN hs","rank_in_archive_order":29,"of":43,"metrics":{"Score":"-6.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-double-dunk","task":"Atari Games","dataset":"Atari 2600 Double Dunk","model":"DQN noop","rank_in_archive_order":30,"of":43,"metrics":{"Score":"-6.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-double-dunk","task":"Atari Games","dataset":"Atari 2600 Double Dunk","model":"DDQN (tuned) hs","rank_in_archive_order":33,"of":43,"metrics":{"Score":"-0.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-double-dunk","task":"Atari Games","dataset":"Atari 2600 Double Dunk","model":"Prior+Duel hs","rank_in_archive_order":34,"of":43,"metrics":{"Score":"-10.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-enduro","task":"Atari Games","dataset":"Atari 2600 Enduro","model":"Prior+Duel hs","rank_in_archive_order":14,"of":48,"metrics":{"Score":"2223.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-enduro","task":"Atari Games","dataset":"Atari 2600 Enduro","model":"DDQN (tuned) hs","rank_in_archive_order":27,"of":48,"metrics":{"Score":"1216.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-enduro","task":"Atari Games","dataset":"Atari 2600 Enduro","model":"DQN noop","rank_in_archive_order":32,"of":48,"metrics":{"Score":"729.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-enduro","task":"Atari Games","dataset":"Atari 2600 Enduro","model":"DQN hs","rank_in_archive_order":34,"of":48,"metrics":{"Score":"626.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-fishing-derby","task":"Atari Games","dataset":"Atari 2600 Fishing Derby","model":"Prior+Duel hs","rank_in_archive_order":29,"of":44,"metrics":{"Score":"17.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-fishing-derby","task":"Atari Games","dataset":"Atari 2600 Fishing Derby","model":"DDQN (tuned) hs","rank_in_archive_order":35,"of":44,"metrics":{"Score":"3.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-fishing-derby","task":"Atari Games","dataset":"Atari 2600 Fishing Derby","model":"DQN hs","rank_in_archive_order":38,"of":44,"metrics":{"Score":"-1.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-fishing-derby","task":"Atari Games","dataset":"Atari 2600 Fishing Derby","model":"DQN noop","rank_in_archive_order":39,"of":44,"metrics":{"Score":"-4.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-freeway","task":"Atari Games","dataset":"Atari 2600 Freeway","model":"DQN noop","rank_in_archive_order":31,"of":59,"metrics":{"Score":"30.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-freeway","task":"Atari Games","dataset":"Atari 2600 Freeway","model":"DDQN (tuned) hs","rank_in_archive_order":38,"of":59,"metrics":{"Score":"28.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-freeway","task":"Atari Games","dataset":"Atari 2600 Freeway","model":"Prior+Duel hs","rank_in_archive_order":39,"of":59,"metrics":{"Score":"28.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-freeway","task":"Atari Games","dataset":"Atari 2600 Freeway","model":"DQN hs","rank_in_archive_order":43,"of":59,"metrics":{"Score":"26.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-frostbite","task":"Atari Games","dataset":"Atari 2600 Frostbite","model":"Prior+Duel hs","rank_in_archive_order":20,"of":53,"metrics":{"Score":"4038.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-frostbite","task":"Atari Games","dataset":"Atari 2600 Frostbite","model":"DDQN (tuned) hs","rank_in_archive_order":33,"of":53,"metrics":{"Score":"1448.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-frostbite","task":"Atari Games","dataset":"Atari 2600 Frostbite","model":"DQN noop","rank_in_archive_order":36,"of":53,"metrics":{"Score":"797.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-frostbite","task":"Atari Games","dataset":"Atari 2600 Frostbite","model":"DQN hs","rank_in_archive_order":39,"of":53,"metrics":{"Score":"496.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gopher","task":"Atari Games","dataset":"Atari 2600 Gopher","model":"Prior+Duel hs","rank_in_archive_order":10,"of":43,"metrics":{"Score":"105148.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gopher","task":"Atari Games","dataset":"Atari 2600 Gopher","model":"DDQN (tuned) hs","rank_in_archive_order":27,"of":43,"metrics":{"Score":"15253.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gopher","task":"Atari Games","dataset":"Atari 2600 Gopher","model":"DQN noop","rank_in_archive_order":32,"of":43,"metrics":{"Score":"8777.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gopher","task":"Atari Games","dataset":"Atari 2600 Gopher","model":"DQN hs","rank_in_archive_order":35,"of":43,"metrics":{"Score":"8190.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gravitar","task":"Atari Games","dataset":"Atari 2600 Gravitar","model":"DQN noop","rank_in_archive_order":33,"of":53,"metrics":{"Score":"473.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gravitar","task":"Atari Games","dataset":"Atari 2600 Gravitar","model":"DQN hs","rank_in_archive_order":44,"of":53,"metrics":{"Score":"298.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gravitar","task":"Atari Games","dataset":"Atari 2600 Gravitar","model":"DDQN (tuned) hs","rank_in_archive_order":52,"of":53,"metrics":{"Score":"200.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gravitar","task":"Atari Games","dataset":"Atari 2600 Gravitar","model":"Prior+Duel hs","rank_in_archive_order":53,"of":53,"metrics":{"Score":"167.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-hero","task":"Atari Games","dataset":"Atari 2600 HERO","model":"DQN noop","rank_in_archive_order":29,"of":44,"metrics":{"Score":"20437.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-hero","task":"Atari Games","dataset":"Atari 2600 HERO","model":"Prior+Duel hs","rank_in_archive_order":32,"of":44,"metrics":{"Score":"15459.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-hero","task":"Atari Games","dataset":"Atari 2600 HERO","model":"DQN hs","rank_in_archive_order":34,"of":44,"metrics":{"Score":"14992.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-hero","task":"Atari Games","dataset":"Atari 2600 HERO","model":"DDQN (tuned) hs","rank_in_archive_order":35,"of":44,"metrics":{"Score":"14892.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ice-hockey","task":"Atari Games","dataset":"Atari 2600 Ice Hockey","model":"Prior+Duel hs","rank_in_archive_order":18,"of":43,"metrics":{"Score":"0.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ice-hockey","task":"Atari Games","dataset":"Atari 2600 Ice Hockey","model":"DQN hs","rank_in_archive_order":23,"of":43,"metrics":{"Score":"-1.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ice-hockey","task":"Atari Games","dataset":"Atari 2600 Ice Hockey","model":"DQN noop","rank_in_archive_order":24,"of":43,"metrics":{"Score":"-1.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ice-hockey","task":"Atari Games","dataset":"Atari 2600 Ice Hockey","model":"DDQN (tuned) hs","rank_in_archive_order":27,"of":43,"metrics":{"Score":"-2.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-james-bond","task":"Atari Games","dataset":"Atari 2600 James Bond","model":"DQN noop","rank_in_archive_order":28,"of":45,"metrics":{"Score":"768.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-james-bond","task":"Atari Games","dataset":"Atari 2600 James Bond","model":"DQN hs","rank_in_archive_order":29,"of":45,"metrics":{"Score":"697.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-james-bond","task":"Atari Games","dataset":"Atari 2600 James Bond","model":"Prior+Duel hs","rank_in_archive_order":32,"of":45,"metrics":{"Score":"585.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-james-bond","task":"Atari Games","dataset":"Atari 2600 James Bond","model":"DDQN (tuned) hs","rank_in_archive_order":34,"of":45,"metrics":{"Score":"573.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kangaroo","task":"Atari Games","dataset":"Atari 2600 Kangaroo","model":"DDQN (tuned) hs","rank_in_archive_order":22,"of":47,"metrics":{"Score":"11204.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kangaroo","task":"Atari Games","dataset":"Atari 2600 Kangaroo","model":"DQN noop","rank_in_archive_order":26,"of":47,"metrics":{"Score":"7259.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kangaroo","task":"Atari Games","dataset":"Atari 2600 Kangaroo","model":"DQN hs","rank_in_archive_order":29,"of":47,"metrics":{"Score":"4496.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kangaroo","task":"Atari Games","dataset":"Atari 2600 Kangaroo","model":"Prior+Duel hs","rank_in_archive_order":41,"of":47,"metrics":{"Score":"861.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-krull","task":"Atari Games","dataset":"Atari 2600 Krull","model":"DQN noop","rank_in_archive_order":27,"of":45,"metrics":{"Score":"8422.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-krull","task":"Atari Games","dataset":"Atari 2600 Krull","model":"Prior+Duel hs","rank_in_archive_order":33,"of":45,"metrics":{"Score":"7658.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-krull","task":"Atari Games","dataset":"Atari 2600 Krull","model":"DDQN (tuned) hs","rank_in_archive_order":35,"of":45,"metrics":{"Score":"6796.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-krull","task":"Atari Games","dataset":"Atari 2600 Krull","model":"DQN hs","rank_in_archive_order":37,"of":45,"metrics":{"Score":"6206.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kung-fu-master","task":"Atari Games","dataset":"Atari 2600 Kung-Fu Master","model":"Prior+Duel hs","rank_in_archive_order":23,"of":43,"metrics":{"Score":"37484.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kung-fu-master","task":"Atari Games","dataset":"Atari 2600 Kung-Fu Master","model":"DDQN (tuned) hs","rank_in_archive_order":32,"of":43,"metrics":{"Score":"30207.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kung-fu-master","task":"Atari Games","dataset":"Atari 2600 Kung-Fu Master","model":"DQN noop","rank_in_archive_order":36,"of":43,"metrics":{"Score":"26059.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kung-fu-master","task":"Atari Games","dataset":"Atari 2600 Kung-Fu Master","model":"DQN hs","rank_in_archive_order":39,"of":43,"metrics":{"Score":"20882.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-montezumas-revenge","task":"Atari Games","dataset":"Atari 2600 Montezuma's Revenge","model":"DQN hs","rank_in_archive_order":34,"of":50,"metrics":{"Score":"47.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-montezumas-revenge","task":"Atari Games","dataset":"Atari 2600 Montezuma's Revenge","model":"DDQN (tuned) hs","rank_in_archive_order":35,"of":50,"metrics":{"Score":"42.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-montezumas-revenge","task":"Atari Games","dataset":"Atari 2600 Montezuma's Revenge","model":"Prior+Duel hs","rank_in_archive_order":37,"of":50,"metrics":{"Score":"24.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ms-pacman","task":"Atari Games","dataset":"Atari 2600 Ms. Pacman","model":"DQN noop","rank_in_archive_order":27,"of":47,"metrics":{"Score":"3085.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ms-pacman","task":"Atari Games","dataset":"Atari 2600 Ms. Pacman","model":"DDQN (tuned) hs","rank_in_archive_order":40,"of":47,"metrics":{"Score":"1241.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ms-pacman","task":"Atari Games","dataset":"Atari 2600 Ms. Pacman","model":"DQN hs","rank_in_archive_order":42,"of":47,"metrics":{"Score":"1092.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ms-pacman","task":"Atari Games","dataset":"Atari 2600 Ms. Pacman","model":"Prior+Duel hs","rank_in_archive_order":43,"of":47,"metrics":{"Score":"1007.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-name-this-game","task":"Atari Games","dataset":"Atari 2600 Name This Game","model":"Prior+Duel hs","rank_in_archive_order":19,"of":43,"metrics":{"Score":"13637.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-name-this-game","task":"Atari Games","dataset":"Atari 2600 Name This Game","model":"DDQN (tuned) hs","rank_in_archive_order":33,"of":43,"metrics":{"Score":"8960.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-name-this-game","task":"Atari Games","dataset":"Atari 2600 Name This Game","model":"DQN noop","rank_in_archive_order":34,"of":43,"metrics":{"Score":"8207.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-name-this-game","task":"Atari Games","dataset":"Atari 2600 Name This Game","model":"DQN hs","rank_in_archive_order":36,"of":43,"metrics":{"Score":"6738.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-pong","task":"Atari Games","dataset":"Atari 2600 Pong","model":"DQN noop","rank_in_archive_order":34,"of":52,"metrics":{"Score":"19.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-pong","task":"Atari Games","dataset":"Atari 2600 Pong","model":"DDQN (tuned) hs","rank_in_archive_order":35,"of":52,"metrics":{"Score":"19.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-pong","task":"Atari Games","dataset":"Atari 2600 Pong","model":"Prior+Duel hs","rank_in_archive_order":39,"of":52,"metrics":{"Score":"18.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-pong","task":"Atari Games","dataset":"Atari 2600 Pong","model":"DQN hs","rank_in_archive_order":42,"of":52,"metrics":{"Score":"18.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-private-eye","task":"Atari Games","dataset":"Atari 2600 Private Eye","model":"Prior+Duel hs","rank_in_archive_order":22,"of":52,"metrics":{"Score":"1277.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-private-eye","task":"Atari Games","dataset":"Atari 2600 Private Eye","model":"DQN hs","rank_in_archive_order":32,"of":52,"metrics":{"Score":"207.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-private-eye","task":"Atari Games","dataset":"Atari 2600 Private Eye","model":"DQN noop","rank_in_archive_order":39,"of":52,"metrics":{"Score":"146.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-private-eye","task":"Atari Games","dataset":"Atari 2600 Private Eye","model":"DDQN (tuned) hs","rank_in_archive_order":52,"of":52,"metrics":{"Score":"-575.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-qbert","task":"Atari Games","dataset":"Atari 2600 Q*Bert","model":"Prior+Duel hs","rank_in_archive_order":35,"of":57,"metrics":{"Score":"14063.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-qbert","task":"Atari Games","dataset":"Atari 2600 Q*Bert","model":"DQN noop","rank_in_archive_order":37,"of":57,"metrics":{"Score":"13117.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-qbert","task":"Atari Games","dataset":"Atari 2600 Q*Bert","model":"DDQN (tuned) hs","rank_in_archive_order":38,"of":57,"metrics":{"Score":"11020.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-qbert","task":"Atari Games","dataset":"Atari 2600 Q*Bert","model":"DQN hs","rank_in_archive_order":41,"of":57,"metrics":{"Score":"9271.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-river-raid","task":"Atari Games","dataset":"Atari 2600 River Raid","model":"Prior+Duel hs","rank_in_archive_order":18,"of":41,"metrics":{"Score":"16496.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-river-raid","task":"Atari Games","dataset":"Atari 2600 River Raid","model":"DDQN (tuned) hs","rank_in_archive_order":27,"of":41,"metrics":{"Score":"10838.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-river-raid","task":"Atari Games","dataset":"Atari 2600 River Raid","model":"DQN noop","rank_in_archive_order":32,"of":41,"metrics":{"Score":"7377.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-river-raid","task":"Atari Games","dataset":"Atari 2600 River Raid","model":"DQN hs","rank_in_archive_order":36,"of":41,"metrics":{"Score":"4748.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-road-runner","task":"Atari Games","dataset":"Atari 2600 Road Runner","model":"Prior+Duel hs","rank_in_archive_order":23,"of":44,"metrics":{"Score":"54630.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-road-runner","task":"Atari Games","dataset":"Atari 2600 Road Runner","model":"DDQN (tuned) hs","rank_in_archive_order":30,"of":44,"metrics":{"Score":"43156.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-road-runner","task":"Atari Games","dataset":"Atari 2600 Road Runner","model":"DQN noop","rank_in_archive_order":32,"of":44,"metrics":{"Score":"39544.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-road-runner","task":"Atari Games","dataset":"Atari 2600 Road Runner","model":"DQN hs","rank_in_archive_order":34,"of":44,"metrics":{"Score":"35215.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-robotank","task":"Atari Games","dataset":"Atari 2600 Robotank","model":"DQN noop","rank_in_archive_order":19,"of":42,"metrics":{"Score":"63.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-robotank","task":"Atari Games","dataset":"Atari 2600 Robotank","model":"DDQN (tuned) hs","rank_in_archive_order":25,"of":42,"metrics":{"Score":"59.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-robotank","task":"Atari Games","dataset":"Atari 2600 Robotank","model":"DQN hs","rank_in_archive_order":26,"of":42,"metrics":{"Score":"58.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-robotank","task":"Atari Games","dataset":"Atari 2600 Robotank","model":"Prior+Duel hs","rank_in_archive_order":34,"of":42,"metrics":{"Score":"24.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-seaquest","task":"Atari Games","dataset":"Atari 2600 Seaquest","model":"DDQN (tuned) hs","rank_in_archive_order":19,"of":57,"metrics":{"Score":"14498.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-seaquest","task":"Atari Games","dataset":"Atari 2600 Seaquest","model":"DQN noop","rank_in_archive_order":30,"of":57,"metrics":{"Score":"5860.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-seaquest","task":"Atari Games","dataset":"Atari 2600 Seaquest","model":"DQN hs","rank_in_archive_order":34,"of":57,"metrics":{"Score":"4216.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-seaquest","task":"Atari Games","dataset":"Atari 2600 Seaquest","model":"Prior+Duel hs","rank_in_archive_order":44,"of":57,"metrics":{"Score":"1431.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-space-invaders","task":"Atari Games","dataset":"Atari 2600 Space Invaders","model":"Prior+Duel hs","rank_in_archive_order":18,"of":55,"metrics":{"Score":"8978.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-space-invaders","task":"Atari Games","dataset":"Atari 2600 Space Invaders","model":"DDQN (tuned) hs","rank_in_archive_order":32,"of":55,"metrics":{"Score":"2628.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-space-invaders","task":"Atari Games","dataset":"Atari 2600 Space Invaders","model":"DQN noop","rank_in_archive_order":39,"of":55,"metrics":{"Score":"1692.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-space-invaders","task":"Atari Games","dataset":"Atari 2600 Space Invaders","model":"DQN hs","rank_in_archive_order":41,"of":55,"metrics":{"Score":"1293.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-star-gunner","task":"Atari Games","dataset":"Atari 2600 Star Gunner","model":"Prior+Duel hs","rank_in_archive_order":14,"of":43,"metrics":{"Score":"127073.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-star-gunner","task":"Atari Games","dataset":"Atari 2600 Star Gunner","model":"DDQN (tuned) hs","rank_in_archive_order":28,"of":43,"metrics":{"Score":"58365.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-star-gunner","task":"Atari Games","dataset":"Atari 2600 Star Gunner","model":"DQN noop","rank_in_archive_order":31,"of":43,"metrics":{"Score":"54282.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-star-gunner","task":"Atari Games","dataset":"Atari 2600 Star Gunner","model":"DQN hs","rank_in_archive_order":32,"of":43,"metrics":{"Score":"52970.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tennis","task":"Atari Games","dataset":"Atari 2600 Tennis","model":"DQN noop","rank_in_archive_order":13,"of":43,"metrics":{"Score":"12.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tennis","task":"Atari Games","dataset":"Atari 2600 Tennis","model":"DQN hs","rank_in_archive_order":15,"of":43,"metrics":{"Score":"11.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tennis","task":"Atari Games","dataset":"Atari 2600 Tennis","model":"DDQN (tuned) hs","rank_in_archive_order":32,"of":43,"metrics":{"Score":"-7.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tennis","task":"Atari Games","dataset":"Atari 2600 Tennis","model":"Prior+Duel hs","rank_in_archive_order":33,"of":43,"metrics":{"Score":"-13.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-time-pilot","task":"Atari Games","dataset":"Atari 2600 Time Pilot","model":"DDQN (tuned) hs","rank_in_archive_order":31,"of":44,"metrics":{"Score":"6608.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-time-pilot","task":"Atari Games","dataset":"Atari 2600 Time Pilot","model":"Prior+Duel hs","rank_in_archive_order":37,"of":44,"metrics":{"Score":"4871.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-time-pilot","task":"Atari Games","dataset":"Atari 2600 Time Pilot","model":"DQN noop","rank_in_archive_order":38,"of":44,"metrics":{"Score":"4870.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-time-pilot","task":"Atari Games","dataset":"Atari 2600 Time Pilot","model":"DQN hs","rank_in_archive_order":40,"of":44,"metrics":{"Score":"4786.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tutankham","task":"Atari Games","dataset":"Atari 2600 Tutankham","model":"Prior+Duel hs","rank_in_archive_order":36,"of":44,"metrics":{"Score":"108.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tutankham","task":"Atari Games","dataset":"Atari 2600 Tutankham","model":"DDQN (tuned) hs","rank_in_archive_order":38,"of":44,"metrics":{"Score":"92.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tutankham","task":"Atari Games","dataset":"Atari 2600 Tutankham","model":"DQN noop","rank_in_archive_order":39,"of":44,"metrics":{"Score":"68.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tutankham","task":"Atari Games","dataset":"Atari 2600 Tutankham","model":"DQN hs","rank_in_archive_order":42,"of":44,"metrics":{"Score":"45.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-up-and-down","task":"Atari Games","dataset":"Atari 2600 Up and Down","model":"Prior+Duel hs","rank_in_archive_order":29,"of":44,"metrics":{"Score":"22681.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-up-and-down","task":"Atari Games","dataset":"Atari 2600 Up and Down","model":"DDQN (tuned) hs","rank_in_archive_order":31,"of":44,"metrics":{"Score":"19086.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-up-and-down","task":"Atari Games","dataset":"Atari 2600 Up and Down","model":"DQN noop","rank_in_archive_order":37,"of":44,"metrics":{"Score":"9989.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-up-and-down","task":"Atari Games","dataset":"Atari 2600 Up and Down","model":"DQN hs","rank_in_archive_order":40,"of":44,"metrics":{"Score":"8038.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-venture","task":"Atari Games","dataset":"Atari 2600 Venture","model":"DQN noop","rank_in_archive_order":30,"of":55,"metrics":{"Score":"163.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-venture","task":"Atari Games","dataset":"Atari 2600 Venture","model":"DQN hs","rank_in_archive_order":31,"of":55,"metrics":{"Score":"136.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-venture","task":"Atari Games","dataset":"Atari 2600 Venture","model":"Prior+Duel hs","rank_in_archive_order":41,"of":55,"metrics":{"Score":"29.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-venture","task":"Atari Games","dataset":"Atari 2600 Venture","model":"DDQN (tuned) hs","rank_in_archive_order":44,"of":55,"metrics":{"Score":"21.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-video-pinball","task":"Atari Games","dataset":"Atari 2600 Video Pinball","model":"Prior+Duel hs","rank_in_archive_order":20,"of":42,"metrics":{"Score":"447408.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-video-pinball","task":"Atari Games","dataset":"Atari 2600 Video Pinball","model":"DDQN (tuned) hs","rank_in_archive_order":21,"of":42,"metrics":{"Score":"367823.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-video-pinball","task":"Atari Games","dataset":"Atari 2600 Video Pinball","model":"DQN noop","rank_in_archive_order":27,"of":42,"metrics":{"Score":"196760.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-video-pinball","task":"Atari Games","dataset":"Atari 2600 Video Pinball","model":"DQN hs","rank_in_archive_order":29,"of":42,"metrics":{"Score":"154414.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-wizard-of-wor","task":"Atari Games","dataset":"Atari 2600 Wizard of Wor","model":"Prior+Duel hs","rank_in_archive_order":18,"of":41,"metrics":{"Score":"10471.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-wizard-of-wor","task":"Atari Games","dataset":"Atari 2600 Wizard of Wor","model":"DDQN (tuned) hs","rank_in_archive_order":29,"of":41,"metrics":{"Score":"6201.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-wizard-of-wor","task":"Atari Games","dataset":"Atari 2600 Wizard of Wor","model":"DQN noop","rank_in_archive_order":37,"of":41,"metrics":{"Score":"2704.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-wizard-of-wor","task":"Atari Games","dataset":"Atari 2600 Wizard of Wor","model":"DQN hs","rank_in_archive_order":39,"of":41,"metrics":{"Score":"1609.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-zaxxon","task":"Atari Games","dataset":"Atari 2600 Zaxxon","model":"Prior+Duel hs","rank_in_archive_order":23,"of":41,"metrics":{"Score":"11320.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-zaxxon","task":"Atari Games","dataset":"Atari 2600 Zaxxon","model":"DDQN (tuned) hs","rank_in_archive_order":32,"of":41,"metrics":{"Score":"8593.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-zaxxon","task":"Atari Games","dataset":"Atari 2600 Zaxxon","model":"DQN noop","rank_in_archive_order":35,"of":41,"metrics":{"Score":"5363.0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-zaxxon","task":"Atari Games","dataset":"Atari 2600 Zaxxon","model":"DQN hs","rank_in_archive_order":37,"of":41,"metrics":{"Score":"4412.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1509.06461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1509.06461"}},"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/wtingda/DeepRLBreakout","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ianlimle/ItsMeMario","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wmol4/Pytorch_DDQN_Unity_Navigation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepmind/rlax","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nbopardi/smb","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pathway/alphaxos","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shehrum/RL_Navigation","reach":null},{"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/hemilpanchiwala/Dueling_Network_Architectures","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Denbergvanthijs/imbDRL","reach":{"status":"ok","spdx":"Apache-2.0"}},{"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/aman-khurana/deep-q-learning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jadag/DDQN_mario","reach":{"status":"ok"}},{"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/dxyang/DQN_pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/utarumo/RL_implementation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cove9988/TradingGym","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhengant/dqn_reversi","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PeterJochem/Double_Deep_QLearning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Roman-Kozachek/TradeBot","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ifestus/rl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guillaumeboniface/bananaland","reach":null}],"summary":{"ran":54,"ran_fixture":1,"unverified":51},"by_repo_kind":{"listed":{"samples":106,"ran":55,"repositories":37}},"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":57,"samples":[{"code_sha256_prefix":"5f8524dc2a2cab41","entry":"Agent","repo":"seacevedo/ReinforcementLearningProjects","repo_kind":"listed","path":"ddqn.py","file_url":"https://github.com/seacevedo/ReinforcementLearningProjects/blob/HEAD/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":"5f8524dc2a2cab41"}},{"code_sha256_prefix":"3836a1d32ca55617","entry":"Agent","repo":"Adrelf/DRL-navigation","repo_kind":"listed","path":"brain/dqn_agent.py","file_url":"https://github.com/Adrelf/DRL-navigation/blob/HEAD/brain/dqn_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":"3836a1d32ca55617"}},{"code_sha256_prefix":"ac9572223e61f5cf","entry":"AgentConfig","repo":"kmdanielduan/DQN_Family_PyTorch","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/kmdanielduan/DQN_Family_PyTorch/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":"ac9572223e61f5cf"}},{"code_sha256_prefix":"570c12d7a6123152","entry":"AgentMemory","repo":"guillaumeboniface/bananaland","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/guillaumeboniface/bananaland/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":"570c12d7a6123152"}},{"code_sha256_prefix":"6f4c156ef811e511","entry":"Atari_DQN","repo":"botforge/simplementation","repo_kind":"listed","path":"2.DOUBLE-DQN_Deep-Reinforcement-Learning-with-Double-Q-Learning-van-Hasselt-etal-2015/double-dqn_atari.py","file_url":"https://github.com/botforge/simplementation/blob/HEAD/2.DOUBLE-DQN_Deep-Reinforcement-Learning-with-Double-Q-Learning-van-Hasselt-etal-2015/double-dqn_atari.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":"6f4c156ef811e511"}},{"code_sha256_prefix":"e8bea3ffc28d3e32","entry":"ConvNet","repo":"seacevedo/ReinforcementLearningProjects","repo_kind":"listed","path":"ddqn.py","file_url":"https://github.com/seacevedo/ReinforcementLearningProjects/blob/HEAD/ddqn.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":"e8bea3ffc28d3e32"}},{"code_sha256_prefix":"d7c5b75c3f5b0451","entry":"ConvNet","repo":"yzheng51/rl-dino-run","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/yzheng51/rl-dino-run/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7c5b75c3f5b0451"}},{"code_sha256_prefix":"247f8b58095cdb6d","entry":"DDQNAgent","repo":"philtabor/Deep-Q-Learning-Paper-To-Code","repo_kind":"listed","path":"DDQN/ddqn_agent.py","file_url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code/blob/HEAD/DDQN/ddqn_agent.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":"247f8b58095cdb6d"}},{"code_sha256_prefix":"00919eeae2ebc39b","entry":"DDQNAgent","repo":"MEOWMEOW114/nd893-p1-navigation-banana","repo_kind":"listed","path":"dqn/double_dqn_agent.py","file_url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana/blob/HEAD/dqn/double_dqn_agent.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":"00919eeae2ebc39b"}},{"code_sha256_prefix":"dc6c2d1d1cffa8c3","entry":"DDQNAgent","repo":"jezzarax/drlnd_p1_navigation","repo_kind":"listed","path":"agents.py","file_url":"https://github.com/jezzarax/drlnd_p1_navigation/blob/HEAD/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":"dc6c2d1d1cffa8c3"}},{"code_sha256_prefix":"f145e7ca739738a0","entry":"DDQNAgent","repo":"mohit8935/Deep-Q-Learning-Paper","repo_kind":"listed","path":"DDQN/ddqn_agent.py","file_url":"https://github.com/mohit8935/Deep-Q-Learning-Paper/blob/HEAD/DDQN/ddqn_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":"f145e7ca739738a0"}},{"code_sha256_prefix":"8002739ef399b9f8","entry":"DQN","repo":"xgfelicia/Reinforcement-Learning","repo_kind":"listed","path":"Cartpole/double-dqn.py","file_url":"https://github.com/xgfelicia/Reinforcement-Learning/blob/HEAD/Cartpole/double-dqn.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":"8002739ef399b9f8"}},{"code_sha256_prefix":"249aaac189a4c179","entry":"DQN","repo":"kmdanielduan/DQN_Family_PyTorch","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/kmdanielduan/DQN_Family_PyTorch/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":"249aaac189a4c179"}},{"code_sha256_prefix":"0493df484647c5af","entry":"DQN","repo":"hamishs/JAX-RL","repo_kind":"listed","path":"src/jax_rl/algorithms/dqn.py","file_url":"https://github.com/hamishs/JAX-RL/blob/HEAD/src/jax_rl/algorithms/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":"0493df484647c5af"}},{"code_sha256_prefix":"4cd993bb1241d36c","entry":"DQN","repo":"yzheng51/rl-dino-run","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/yzheng51/rl-dino-run/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4cd993bb1241d36c"}},{"code_sha256_prefix":"c758b36e7d16e2ef","entry":"DQNAgent","repo":"matthewsparr/Deep-Zork","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/matthewsparr/Deep-Zork/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":"c758b36e7d16e2ef"}},{"code_sha256_prefix":"bfb3e0ae3cba8f2e","entry":"DQNagent","repo":"xgfelicia/Reinforcement-Learning","repo_kind":"listed","path":"Cartpole/double-dqn.py","file_url":"https://github.com/xgfelicia/Reinforcement-Learning/blob/HEAD/Cartpole/double-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":"bfb3e0ae3cba8f2e"}},{"code_sha256_prefix":"85c944ddae8c9df8","entry":"DeepQNetowrk","repo":"fengsterooni/dql","repo_kind":"listed","path":"DDQN/ddqn_agent.py","file_url":"https://github.com/fengsterooni/dql/blob/HEAD/DDQN/ddqn_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":"85c944ddae8c9df8"}},{"code_sha256_prefix":"458d686bba2350d3","entry":"DeepQNetwork","repo":"philtabor/Deep-Q-Learning-Paper-To-Code","repo_kind":"listed","path":"DDQN/ddqn_agent.py","file_url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code/blob/HEAD/DDQN/ddqn_agent.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":"458d686bba2350d3"}},{"code_sha256_prefix":"99ac309143b7cf78","entry":"DoubleDQN","repo":"yzheng51/rl-dino-run","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/yzheng51/rl-dino-run/blob/HEAD/agent.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":"99ac309143b7cf78"}},{"code_sha256_prefix":"be74745caf4bf744","entry":"DuelingDQN","repo":"daviddcho/supermario","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/daviddcho/supermario/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":"be74745caf4bf744"}},{"code_sha256_prefix":"216682c7c24d1664","entry":"DummyAgent","repo":"jezzarax/drlnd_p1_navigation","repo_kind":"listed","path":"agents.py","file_url":"https://github.com/jezzarax/drlnd_p1_navigation/blob/HEAD/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":"216682c7c24d1664"}},{"code_sha256_prefix":"77c8ec6c865240fa","entry":"ExperienceReplay","repo":"daviddcho/supermario","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/daviddcho/supermario/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":"77c8ec6c865240fa"}},{"code_sha256_prefix":"986cc90d7e4eeaf2","entry":"ExperienceReplay","repo":"hamishs/JAX-RL","repo_kind":"listed","path":"src/jax_rl/algorithms/dqn.py","file_url":"https://github.com/hamishs/JAX-RL/blob/HEAD/src/jax_rl/algorithms/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":"986cc90d7e4eeaf2"}},{"code_sha256_prefix":"42487fb842418ae5","entry":"FixedSize_BinarySearchTree","repo":"1jsingh/rl_navigation","repo_kind":"listed","path":"agents/dqn_agent.py","file_url":"https://github.com/1jsingh/rl_navigation/blob/HEAD/agents/dqn_agent.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":"42487fb842418ae5"}},{"code_sha256_prefix":"c852318db796f171","entry":"LinearAnneal","repo":"yzheng51/rl-dino-run","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/yzheng51/rl-dino-run/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c852318db796f171"}},{"code_sha256_prefix":"5c959f3eff13eb01","entry":"MLP","repo":"guillaumeboniface/bananaland","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/guillaumeboniface/bananaland/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":"5c959f3eff13eb01"}},{"code_sha256_prefix":"dc87a7e1418f9bb3","entry":"Memory","repo":"utarumo/RL_implementation","repo_kind":"listed","path":"dqn_atari.py","file_url":"https://github.com/utarumo/RL_implementation/blob/HEAD/dqn_atari.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":"dc87a7e1418f9bb3"}},{"code_sha256_prefix":"127094b1a1600120","entry":"Net","repo":"OscarHuangWind/Preference-Guided-DQN-Atari","repo_kind":"listed","path":"DRL.py","file_url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari/blob/HEAD/DRL.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":"127094b1a1600120"}},{"code_sha256_prefix":"9ca97885778aa8a2","entry":"Net","repo":"yzheng51/rl-dino-run","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/yzheng51/rl-dino-run/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9ca97885778aa8a2"}},{"code_sha256_prefix":"01fc22f5d7228bdb","entry":"Network","repo":"HussonnoisMaxence/RL_Algorithms","repo_kind":"listed","path":"QLearning/D2QN/D2QN.py","file_url":"https://github.com/HussonnoisMaxence/RL_Algorithms/blob/HEAD/QLearning/D2QN/D2QN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"01fc22f5d7228bdb"}},{"code_sha256_prefix":"896578e9d4f08299","entry":"Node","repo":"1jsingh/rl_navigation","repo_kind":"listed","path":"agents/dqn_agent.py","file_url":"https://github.com/1jsingh/rl_navigation/blob/HEAD/agents/dqn_agent.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":"896578e9d4f08299"}},{"code_sha256_prefix":"00c916fc3622888b","entry":"NoisyLinear","repo":"daviddcho/supermario","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/daviddcho/supermario/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":"00c916fc3622888b"}},{"code_sha256_prefix":"0c36fb52695342c8","entry":"PER","repo":"OscarHuangWind/Preference-Guided-DQN-Atari","repo_kind":"listed","path":"DRL.py","file_url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari/blob/HEAD/DRL.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":"0c36fb52695342c8"}},{"code_sha256_prefix":"f9462232ec862c47","entry":"QNetwork","repo":"MEOWMEOW114/nd893-p1-navigation-banana","repo_kind":"listed","path":"dqn/double_dqn_agent.py","file_url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana/blob/HEAD/dqn/double_dqn_agent.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":"f9462232ec862c47"}},{"code_sha256_prefix":"01d2de07d88f7c3a","entry":"QNetwork","repo":"Adrelf/DRL-navigation","repo_kind":"listed","path":"brain/dqn_agent.py","file_url":"https://github.com/Adrelf/DRL-navigation/blob/HEAD/brain/dqn_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":"01d2de07d88f7c3a"}},{"code_sha256_prefix":"308d7ccd559f5f3b","entry":"QNetwork_128","repo":"microsoft/med-deadend","repo_kind":"listed","path":"rl.py","file_url":"https://github.com/microsoft/med-deadend/blob/HEAD/rl.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":"308d7ccd559f5f3b"}},{"code_sha256_prefix":"24430ed056d60e5e","entry":"QNetwork_64","repo":"microsoft/med-deadend","repo_kind":"listed","path":"rl.py","file_url":"https://github.com/microsoft/med-deadend/blob/HEAD/rl.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":"24430ed056d60e5e"}},{"code_sha256_prefix":"07905d0466e42900","entry":"QNetwork_6464","repo":"microsoft/med-deadend","repo_kind":"listed","path":"rl.py","file_url":"https://github.com/microsoft/med-deadend/blob/HEAD/rl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"07905d0466e42900"}},{"code_sha256_prefix":"124226e5906f2192","entry":"Q_model","repo":"guillaumeboniface/bananaland","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/guillaumeboniface/bananaland/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":"124226e5906f2192"}},{"code_sha256_prefix":"286e69c369a502d4","entry":"Qnetwork","repo":"1jsingh/rl_navigation","repo_kind":"listed","path":"agents/dqn_agent.py","file_url":"https://github.com/1jsingh/rl_navigation/blob/HEAD/agents/dqn_agent.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":"286e69c369a502d4"}},{"code_sha256_prefix":"2a2892343a3359ee","entry":"ReplayBuffer","repo":"philtabor/Deep-Q-Learning-Paper-To-Code","repo_kind":"listed","path":"DDQN/ddqn_agent.py","file_url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code/blob/HEAD/DDQN/ddqn_agent.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":"2a2892343a3359ee"}},{"code_sha256_prefix":"dcd7958b0ad16526","entry":"ReplayBuffer","repo":"MEOWMEOW114/nd893-p1-navigation-banana","repo_kind":"listed","path":"dqn/double_dqn_agent.py","file_url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana/blob/HEAD/dqn/double_dqn_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":"dcd7958b0ad16526"}},{"code_sha256_prefix":"56d9058560cd0b68","entry":"ReplayBuffer","repo":"marload/DeepRL-TensorFlow2","repo_kind":"listed","path":"DoubleDQN/DoubleDQN_Discrete.py","file_url":"https://github.com/marload/DeepRL-TensorFlow2/blob/HEAD/DoubleDQN/DoubleDQN_Discrete.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":"56d9058560cd0b68"}},{"code_sha256_prefix":"41d448d208226341","entry":"ReplayBuffer","repo":"mohit8935/Deep-Q-Learning-Paper","repo_kind":"listed","path":"DDQN/ddqn_agent.py","file_url":"https://github.com/mohit8935/Deep-Q-Learning-Paper/blob/HEAD/DDQN/ddqn_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":"41d448d208226341"}},{"code_sha256_prefix":"0e225401249db6d9","entry":"ReplayBuffer","repo":"Adrelf/DRL-navigation","repo_kind":"listed","path":"brain/dqn_agent.py","file_url":"https://github.com/Adrelf/DRL-navigation/blob/HEAD/brain/dqn_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":"0e225401249db6d9"}},{"code_sha256_prefix":"1a174f4ed5cef5f4","entry":"ReplayMemory","repo":"kmdanielduan/DQN_Family_PyTorch","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/kmdanielduan/DQN_Family_PyTorch/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":"1a174f4ed5cef5f4"}},{"code_sha256_prefix":"61d763d7c26919c1","entry":"ReplayMemory","repo":"OscarHuangWind/Preference-Guided-DQN-Atari","repo_kind":"listed","path":"DRL.py","file_url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari/blob/HEAD/DRL.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":"61d763d7c26919c1"}},{"code_sha256_prefix":"1d2063c27405ec4e","entry":"ReplayMemory","repo":"ssainz/reinforcement_learning_algorithms","repo_kind":"listed","path":"non_jupyter/Frozen_Lake_DDQN.py","file_url":"https://github.com/ssainz/reinforcement_learning_algorithms/blob/HEAD/non_jupyter/Frozen_Lake_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":"1d2063c27405ec4e"}},{"code_sha256_prefix":"352c0c157af8514e","entry":"StateProcessor","repo":"yzheng51/rl-dino-run","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/yzheng51/rl-dino-run/blob/HEAD/agent.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":"352c0c157af8514e"}},{"code_sha256_prefix":"c4667f9f629308c9","entry":"SumTree","repo":"OscarHuangWind/Preference-Guided-DQN-Atari","repo_kind":"listed","path":"DRL.py","file_url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari/blob/HEAD/DRL.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":"c4667f9f629308c9"}},{"code_sha256_prefix":"f5e528a822875813","entry":"SumTree","repo":"utarumo/RL_implementation","repo_kind":"listed","path":"dqn_atari.py","file_url":"https://github.com/utarumo/RL_implementation/blob/HEAD/dqn_atari.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":"f5e528a822875813"}},{"code_sha256_prefix":"1652d7453e55d633","entry":"Transition","repo":"hamishs/JAX-RL","repo_kind":"listed","path":"src/jax_rl/algorithms/dqn.py","file_url":"https://github.com/hamishs/JAX-RL/blob/HEAD/src/jax_rl/algorithms/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":"1652d7453e55d633"}},{"code_sha256_prefix":"df05e7e72c42e52a","entry":"double_q_learning","repo":"deepmind/rlax","repo_kind":"listed","path":"rlax/_src/value_learning.py","file_url":"https://github.com/deepmind/rlax/blob/HEAD/rlax/_src/value_learning.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":"df05e7e72c42e52a"}},{"code_sha256_prefix":"c71291d513eadb0c","entry":"q_net","repo":"ssainz/reinforcement_learning_algorithms","repo_kind":"listed","path":"non_jupyter/Frozen_Lake_DDQN.py","file_url":"https://github.com/ssainz/reinforcement_learning_algorithms/blob/HEAD/non_jupyter/Frozen_Lake_DDQN.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":"c71291d513eadb0c"}},{"code_sha256_prefix":"60f968e2c7d67881","entry":"ActionStateModel","repo":"marload/DeepRL-TensorFlow2","repo_kind":"listed","path":"DoubleDQN/DoubleDQN_Discrete.py","file_url":"https://github.com/marload/DeepRL-TensorFlow2/blob/HEAD/DoubleDQN/DoubleDQN_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":"60f968e2c7d67881"}},{"code_sha256_prefix":"f370c556306eb621","entry":"Agent","repo":"1jsingh/rl_navigation","repo_kind":"listed","path":"agents/dqn_agent.py","file_url":"https://github.com/1jsingh/rl_navigation/blob/HEAD/agents/dqn_agent.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":"f370c556306eb621"}},{"code_sha256_prefix":"1324ea2444e296ba","entry":"Agent","repo":"kmdanielduan/DQN_Family_PyTorch","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/kmdanielduan/DQN_Family_PyTorch/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":"1324ea2444e296ba"}},{"code_sha256_prefix":"684dac16bf6352e6","entry":"Agent","repo":"marload/DeepRL-TensorFlow2","repo_kind":"listed","path":"DoubleDQN/DoubleDQN_Discrete.py","file_url":"https://github.com/marload/DeepRL-TensorFlow2/blob/HEAD/DoubleDQN/DoubleDQN_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":"684dac16bf6352e6"}},{"code_sha256_prefix":"a812e436e77634de","entry":"Agent","repo":"PeterJochem/Deep_RL","repo_kind":"listed","path":"DDQN/BBreaker/myAgent.py","file_url":"https://github.com/PeterJochem/Deep_RL/blob/HEAD/DDQN/BBreaker/myAgent.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":"a812e436e77634de"}},{"code_sha256_prefix":"1f87bb3ad2308635","entry":"Agent","repo":"utarumo/RL_implementation","repo_kind":"listed","path":"dqn_atari.py","file_url":"https://github.com/utarumo/RL_implementation/blob/HEAD/dqn_atari.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":"1f87bb3ad2308635"}},{"code_sha256_prefix":"d258022cfdb2a560","entry":"Agent","repo":"shehrum/RL_Navigation","repo_kind":"listed","path":"dqn_agent.py","file_url":"https://github.com/shehrum/RL_Navigation/blob/HEAD/dqn_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":"d258022cfdb2a560"}},{"code_sha256_prefix":"7802ec0bd30c8512","entry":"Agent","repo":"HussonnoisMaxence/RL_Algorithms","repo_kind":"listed","path":"QLearning/D2QN/D2QN.py","file_url":"https://github.com/HussonnoisMaxence/RL_Algorithms/blob/HEAD/QLearning/D2QN/D2QN.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":"7802ec0bd30c8512"}},{"code_sha256_prefix":"59b97ac055efa363","entry":"Agent","repo":"tkcoding/DeepRL","repo_kind":"listed","path":"Banana_Navigator/Agent.py","file_url":"https://github.com/tkcoding/DeepRL/blob/HEAD/Banana_Navigator/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":"59b97ac055efa363"}},{"code_sha256_prefix":"52999846a5c49f96","entry":"Agent","repo":"NikolausBerl/Udacity_DRLN_Navigation_Project","repo_kind":"listed","path":"dqn_agent.py","file_url":"https://github.com/NikolausBerl/Udacity_DRLN_Navigation_Project/blob/HEAD/dqn_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":"52999846a5c49f96"}},{"code_sha256_prefix":"39984e4ec10e928e","entry":"CNN","repo":"ifestus/rl","repo_kind":"listed","path":"dqn/dqn.py","file_url":"https://github.com/ifestus/rl/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":"39984e4ec10e928e"}},{"code_sha256_prefix":"79adffedd37f2627","entry":"DDQN","repo":"hamishs/JAX-RL","repo_kind":"listed","path":"src/jax_rl/algorithms/dqn.py","file_url":"https://github.com/hamishs/JAX-RL/blob/HEAD/src/jax_rl/algorithms/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":"79adffedd37f2627"}},{"code_sha256_prefix":"dd41380cda3330bf","entry":"DDQN","repo":"ifestus/rl","repo_kind":"listed","path":"dqn/dqn.py","file_url":"https://github.com/ifestus/rl/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":"dd41380cda3330bf"}},{"code_sha256_prefix":"49bf52df6b0d3ead","entry":"DDQNAgent","repo":"fengsterooni/dql","repo_kind":"listed","path":"DDQN/ddqn_agent.py","file_url":"https://github.com/fengsterooni/dql/blob/HEAD/DDQN/ddqn_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":"49bf52df6b0d3ead"}},{"code_sha256_prefix":"8538006c32c0f609","entry":"DLQAgent","repo":"guillaumeboniface/bananaland","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/guillaumeboniface/bananaland/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":"8538006c32c0f609"}},{"code_sha256_prefix":"5964c193c9302049","entry":"DQN","repo":"OscarHuangWind/Preference-Guided-DQN-Atari","repo_kind":"listed","path":"DRL.py","file_url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari/blob/HEAD/DRL.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":"5964c193c9302049"}},{"code_sha256_prefix":"2c00e8186282ff76","entry":"DQN","repo":"ifestus/rl","repo_kind":"listed","path":"dqn/dqn.py","file_url":"https://github.com/ifestus/rl/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":"2c00e8186282ff76"}},{"code_sha256_prefix":"39cd1cea29282ec1","entry":"DQN","repo":"tensorlayer/RLzoo","repo_kind":"listed","path":"rlzoo/algorithms/dqn/dqn.py","file_url":"https://github.com/tensorlayer/RLzoo/blob/HEAD/rlzoo/algorithms/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"39cd1cea29282ec1"}},{"code_sha256_prefix":"b9e4d950b7bc9105","entry":"DQNAgent","repo":"MEOWMEOW114/nd893-p1-navigation-banana","repo_kind":"listed","path":"dqn/double_dqn_agent.py","file_url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana/blob/HEAD/dqn/double_dqn_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":"b9e4d950b7bc9105"}},{"code_sha256_prefix":"4c3c6bab1314cb4b","entry":"DQNAgent","repo":"daviddcho/supermario","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/daviddcho/supermario/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":"4c3c6bab1314cb4b"}},{"code_sha256_prefix":"9c6c6632e740cb42","entry":"DQNAgent","repo":"Roman-Kozachek/TradeBot","repo_kind":"listed","path":"classes/agent.py","file_url":"https://github.com/Roman-Kozachek/TradeBot/blob/HEAD/classes/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":"9c6c6632e740cb42"}},{"code_sha256_prefix":"74d1f509eb3cf7cb","entry":"DeepQNetwork","repo":"jeffery1236/Atari_DoubleDeepQNetwork","repo_kind":"listed","path":"DDQAgent.py","file_url":"https://github.com/jeffery1236/Atari_DoubleDeepQNetwork/blob/HEAD/DDQAgent.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":"74d1f509eb3cf7cb"}},{"code_sha256_prefix":"b62844075843cfc9","entry":"DoubleDQAgent","repo":"jeffery1236/Atari_DoubleDeepQNetwork","repo_kind":"listed","path":"DDQAgent.py","file_url":"https://github.com/jeffery1236/Atari_DoubleDeepQNetwork/blob/HEAD/DDQAgent.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":"b62844075843cfc9"}},{"code_sha256_prefix":"f7926a68b7bdd88d","entry":"DoubleDQN","repo":"JustinStitt/acrobotDDQN","repo_kind":"listed","path":"DDQN.py","file_url":"https://github.com/JustinStitt/acrobotDDQN/blob/HEAD/DDQN.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":"f7926a68b7bdd88d"}},{"code_sha256_prefix":"b028432950562bdb","entry":"DuelingDDQNAgent","repo":"hemilpanchiwala/Dueling-Network-Architectures","repo_kind":"listed","path":"DuelingDDQNAgent.py","file_url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures/blob/HEAD/DuelingDDQNAgent.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":"b028432950562bdb"}},{"code_sha256_prefix":"db8c50b16d68e727","entry":"DuelingDeepQNetwork","repo":"hemilpanchiwala/Dueling-Network-Architectures","repo_kind":"listed","path":"DuelingDDQNAgent.py","file_url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures/blob/HEAD/DuelingDDQNAgent.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":"db8c50b16d68e727"}},{"code_sha256_prefix":"cbdc121eed816162","entry":"EnvConfig","repo":"kmdanielduan/DQN_Family_PyTorch","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/kmdanielduan/DQN_Family_PyTorch/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":"cbdc121eed816162"}},{"code_sha256_prefix":"1adc6959fb824443","entry":"ExperienceReplayMemory","repo":"hemilpanchiwala/Dueling-Network-Architectures","repo_kind":"listed","path":"DuelingDDQNAgent.py","file_url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures/blob/HEAD/DuelingDDQNAgent.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":"1adc6959fb824443"}},{"code_sha256_prefix":"5fcfb5dfeec4ae38","entry":"HyperParam","repo":"yzheng51/rl-dino-run","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/yzheng51/rl-dino-run/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5fcfb5dfeec4ae38"}},{"code_sha256_prefix":"908cf1edb8faa4b5","entry":"Logger","repo":"daviddcho/supermario","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/daviddcho/supermario/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":"908cf1edb8faa4b5"}},{"code_sha256_prefix":"1124c41973a96953","entry":"NeuralQLearner","repo":"yukezhu/tensorflow-reinforce","repo_kind":"listed","path":"rl/neural_q_learner.py","file_url":"https://github.com/yukezhu/tensorflow-reinforce/blob/HEAD/rl/neural_q_learner.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":"1124c41973a96953"}},{"code_sha256_prefix":"78e16e24720e0320","entry":"PrioritizedReplayBuffer","repo":"tensorlayer/RLzoo","repo_kind":"listed","path":"rlzoo/algorithms/dqn/dqn.py","file_url":"https://github.com/tensorlayer/RLzoo/blob/HEAD/rlzoo/algorithms/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"78e16e24720e0320"}},{"code_sha256_prefix":"228f9f075525f9a2","entry":"RL","repo":"microsoft/med-deadend","repo_kind":"listed","path":"rl.py","file_url":"https://github.com/microsoft/med-deadend/blob/HEAD/rl.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":"228f9f075525f9a2"}},{"code_sha256_prefix":"f07ed06c9c4c4e7c","entry":"ReplayBuffer","repo":"1jsingh/rl_navigation","repo_kind":"listed","path":"agents/dqn_agent.py","file_url":"https://github.com/1jsingh/rl_navigation/blob/HEAD/agents/dqn_agent.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":"f07ed06c9c4c4e7c"}},{"code_sha256_prefix":"15af333b2f369749","entry":"ReplayBuffer","repo":"fengsterooni/dql","repo_kind":"listed","path":"DDQN/ddqn_agent.py","file_url":"https://github.com/fengsterooni/dql/blob/HEAD/DDQN/ddqn_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":"15af333b2f369749"}},{"code_sha256_prefix":"fd4b196396e41a0f","entry":"ReplayBuffer","repo":"shehrum/RL_Navigation","repo_kind":"listed","path":"dqn_agent.py","file_url":"https://github.com/shehrum/RL_Navigation/blob/HEAD/dqn_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":"fd4b196396e41a0f"}},{"code_sha256_prefix":"28d5d41e56d53b63","entry":"ReplayBuffer","repo":"jeffery1236/Atari_DoubleDeepQNetwork","repo_kind":"listed","path":"DDQAgent.py","file_url":"https://github.com/jeffery1236/Atari_DoubleDeepQNetwork/blob/HEAD/DDQAgent.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":"28d5d41e56d53b63"}},{"code_sha256_prefix":"fd50d6e813cead15","entry":"ReplayMemory","repo":"HussonnoisMaxence/RL_Algorithms","repo_kind":"listed","path":"QLearning/D2QN/D2QN.py","file_url":"https://github.com/HussonnoisMaxence/RL_Algorithms/blob/HEAD/QLearning/D2QN/D2QN.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":"fd50d6e813cead15"}},{"code_sha256_prefix":"0645b4b6b8caa2a3","entry":"_weights_init","repo":"botforge/simplementation","repo_kind":"listed","path":"2.DOUBLE-DQN_Deep-Reinforcement-Learning-with-Double-Q-Learning-van-Hasselt-etal-2015/double-dqn_atari.py","file_url":"https://github.com/botforge/simplementation/blob/HEAD/2.DOUBLE-DQN_Deep-Reinforcement-Learning-with-Double-Q-Learning-van-Hasselt-etal-2015/double-dqn_atari.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":"0645b4b6b8caa2a3"}},{"code_sha256_prefix":"e407d6ccfa049980","entry":"absolute_scope_name","repo":"hill-a/stable-baselines","repo_kind":"listed","path":"stable_baselines/deepq/build_graph.py","file_url":"https://github.com/hill-a/stable-baselines/blob/HEAD/stable_baselines/deepq/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":"e407d6ccfa049980"}},{"code_sha256_prefix":"ca48ef0e750004ab","entry":"build_act","repo":"hill-a/stable-baselines","repo_kind":"listed","path":"stable_baselines/deepq/build_graph.py","file_url":"https://github.com/hill-a/stable-baselines/blob/HEAD/stable_baselines/deepq/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":"ca48ef0e750004ab"}},{"code_sha256_prefix":"467a140347947f78","entry":"build_act_with_param_noise","repo":"hill-a/stable-baselines","repo_kind":"listed","path":"stable_baselines/deepq/build_graph.py","file_url":"https://github.com/hill-a/stable-baselines/blob/HEAD/stable_baselines/deepq/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":"467a140347947f78"}},{"code_sha256_prefix":"495764c8da29ad3c","entry":"build_train","repo":"hill-a/stable-baselines","repo_kind":"listed","path":"stable_baselines/deepq/build_graph.py","file_url":"https://github.com/hill-a/stable-baselines/blob/HEAD/stable_baselines/deepq/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":"495764c8da29ad3c"}},{"code_sha256_prefix":"e04b6449372dffb4","entry":"compute_loss","repo":"near32/regym","repo_kind":"listed","path":"regym/rl_algorithms/algorithms/DQN/ddqn_loss.py","file_url":"https://github.com/near32/regym/blob/HEAD/regym/rl_algorithms/algorithms/DQN/ddqn_loss.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":"e04b6449372dffb4"}},{"code_sha256_prefix":"f9790043f512484c","entry":"default_param_noise_filter","repo":"hill-a/stable-baselines","repo_kind":"listed","path":"stable_baselines/deepq/build_graph.py","file_url":"https://github.com/hill-a/stable-baselines/blob/HEAD/stable_baselines/deepq/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":"f9790043f512484c"}},{"code_sha256_prefix":"de8bc6ac984a0475","entry":"init_weights","repo":"microsoft/med-deadend","repo_kind":"listed","path":"rl.py","file_url":"https://github.com/microsoft/med-deadend/blob/HEAD/rl.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":"de8bc6ac984a0475"}},{"code_sha256_prefix":"a70a2154eb543432","entry":"make_atari","repo":"jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning","repo_kind":"listed","path":"ddqn/utils/atari_wrappers.py","file_url":"https://github.com/jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning/blob/HEAD/ddqn/utils/atari_wrappers.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":"a70a2154eb543432"}},{"code_sha256_prefix":"c596c533af422c46","entry":"optimize_model","repo":"ssainz/reinforcement_learning_algorithms","repo_kind":"listed","path":"non_jupyter/Frozen_Lake_DDQN.py","file_url":"https://github.com/ssainz/reinforcement_learning_algorithms/blob/HEAD/non_jupyter/Frozen_Lake_DDQN.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":"c596c533af422c46"}},{"code_sha256_prefix":"e27ff7ad1ae26a0e","entry":"scope_name","repo":"hill-a/stable-baselines","repo_kind":"listed","path":"stable_baselines/deepq/build_graph.py","file_url":"https://github.com/hill-a/stable-baselines/blob/HEAD/stable_baselines/deepq/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":"e27ff7ad1ae26a0e"}},{"code_sha256_prefix":"7994dd5a6da7dcf7","entry":"scope_vars","repo":"hill-a/stable-baselines","repo_kind":"listed","path":"stable_baselines/deepq/build_graph.py","file_url":"https://github.com/hill-a/stable-baselines/blob/HEAD/stable_baselines/deepq/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":"7994dd5a6da7dcf7"}},{"code_sha256_prefix":"3b5c0e5667fd4eaa","entry":"wrap_deepmind","repo":"jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning","repo_kind":"listed","path":"ddqn/utils/atari_wrappers.py","file_url":"https://github.com/jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning/blob/HEAD/ddqn/utils/atari_wrappers.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":"3b5c0e5667fd4eaa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}