{"url":"/task/atari-games","name":"Atari Games","slug":"atari-games","description_markdown":"The Atari 2600 Games task (and dataset) involves training an agent to achieve high game scores.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Playing Atari with Deep Reinforcement Learning](https://arxiv.org/pdf/1312.5602v1.pdf) )</span>","categories":[{"name":"Playing Games","url":"/area/playing-games"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":625,"papers_with_code":313,"benchmarks":65,"benchmark_tables_in_archive":65,"benchmark_tables_shown":65,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":6,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/atari-games-on-atari-2600-freeway","slug":"atari-games-on-atari-2600-freeway","dataset":"Atari 2600 Freeway","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":59,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO-hash","paper_title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","paper_url":"/paper/exploration-a-study-of-count-based","paper_date":"2016-11-15","arxiv_id":"1611.04717","code_links":[{"title":"uoe-agents/derl","url":"https://github.com/uoe-agents/derl"},{"title":"nhynes/abc","url":"https://github.com/nhynes/abc"},{"title":"clementbernardd/Count-Based-Exploration","url":"https://github.com/clementbernardd/Count-Based-Exploration"}],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-breakout","slug":"atari-games-on-atari-2600-breakout","dataset":"Atari 2600 Breakout","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":58,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3(200M frames)","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-qbert","slug":"atari-games-on-atari-2600-qbert","dataset":"Atari 2600 Q*Bert","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":57,"metrics":["Score","Best Score","Return"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/atari-games-on-atari-2600-seaquest","slug":"atari-games-on-atari-2600-seaquest","dataset":"Atari 2600 Seaquest","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":57,"metrics":["Score","Return"],"first_row_in_archive_order":{"model":"GDI-H3(200M frames)","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-space-invaders","slug":"atari-games-on-atari-2600-space-invaders","dataset":"Atari 2600 Space Invaders","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":55,"metrics":["Score","Best Score","Return"],"first_row_in_archive_order":{"model":"GDI-H3(200M frames)","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-venture","slug":"atari-games-on-atari-2600-venture","dataset":"Atari 2600 Venture","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":55,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/atari-games-on-atari-2600-frostbite","slug":"atari-games-on-atari-2600-frostbite","dataset":"Atari 2600 Frostbite","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":53,"metrics":["Score","Best Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}}},{"leaderboard":"/sota/atari-games-on-atari-2600-gravitar","slug":"atari-games-on-atari-2600-gravitar","dataset":"Atari 2600 Gravitar","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":53,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/atari-games-on-atari-2600-pong","slug":"atari-games-on-atari-2600-pong","dataset":"Atari 2600 Pong","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":52,"metrics":["Score"],"first_row_in_archive_order":{"model":"Duel noop","paper_title":"Dueling Network Architectures for Deep Reinforcement Learning","paper_url":"/paper/dueling-network-architectures-for-deep","paper_date":"2015-11-20","arxiv_id":"1511.06581","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"facebookresearch/Horizon","url":"https://github.com/facebookresearch/Horizon"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"ku2482/sac-discrete.pytorch","url":"https://github.com/ku2482/sac-discrete.pytorch"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"BY571/DQN-Atari-Agents","url":"https://github.com/BY571/DQN-Atari-Agents"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"JuliaPOMDP/DeepQLearning.jl","url":"https://github.com/JuliaPOMDP/DeepQLearning.jl"},{"title":"gouxiangchen/dueling-DQN-pytorch","url":"https://github.com/gouxiangchen/dueling-DQN-pytorch"},{"title":"R-Sweke/DeepQ-Decoding","url":"https://github.com/R-Sweke/DeepQ-Decoding"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"ethanmclark1/carla_aebs","url":"https://github.com/ethanmclark1/carla_aebs"},{"title":"clarky104/carla_aebs","url":"https://github.com/clarky104/carla_aebs"},{"title":"KDL-umass/saliency_maps","url":"https://github.com/KDL-umass/saliency_maps"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"alessandrositta/Flatland_challenge","url":"https://github.com/alessandrositta/Flatland_challenge"},{"title":"MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"nathanin/pad","url":"https://github.com/nathanin/pad"},{"title":"zynk13/dueling-dqn-Reinforcement-learning","url":"https://github.com/zynk13/dueling-dqn-Reinforcement-learning"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"prajwalgatti/DRL-Continuous-Control","url":"https://github.com/prajwalgatti/DRL-Continuous-Control"},{"title":"la3lma/chezjulia","url":"https://github.com/la3lma/chezjulia"},{"title":"la3lma/Chez","url":"https://github.com/la3lma/Chez"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"prajwalgatti/DRL-Navigation","url":"https://github.com/prajwalgatti/DRL-Navigation"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning","url":"https://github.com/manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"iDataist/Navigation-with-Deep-Q-Network","url":"https://github.com/iDataist/Navigation-with-Deep-Q-Network"},{"title":"jsztompka/DuelDQN","url":"https://github.com/jsztompka/DuelDQN"},{"title":"170928/-Review-Dueling-Deep-Q-Network","url":"https://github.com/170928/-Review-Dueling-Deep-Q-Network"},{"title":"Brandon-Rozek/DeepRL","url":"https://github.com/Brandon-Rozek/DeepRL"},{"title":"abryeemessi/Wednesday","url":"https://github.com/abryeemessi/Wednesday"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"JBGUIMBAUD/deep-reenforcement-learning","url":"https://github.com/JBGUIMBAUD/deep-reenforcement-learning"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"opplieam/Pong-Deep-RL","url":"https://github.com/opplieam/Pong-Deep-RL"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"}],"syntology":{"n":11,"n_ran":5,"n_unverified":6,"n_pointer_only":6}}},{"leaderboard":"/sota/atari-games-on-atari-2600-private-eye","slug":"atari-games-on-atari-2600-private-eye","dataset":"Atari 2600 Private Eye","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":52,"metrics":["Score"],"first_row_in_archive_order":{"model":"Go-Explore","paper_title":"First return, then explore","paper_url":"/paper/first-return-then-explore","paper_date":"2020-04-27","arxiv_id":"2004.12919","code_links":[{"title":"uber-research/go-explore","url":"https://github.com/uber-research/go-explore"},{"title":"qgallouedec/lge","url":"https://github.com/qgallouedec/lge"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}}},{"leaderboard":"/sota/atari-games-on-atari-2600-montezumas-revenge","slug":"atari-games-on-atari-2600-montezumas-revenge","dataset":"Atari 2600 Montezuma's Revenge","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":50,"metrics":["Score"],"first_row_in_archive_order":{"model":"Go-Explore","paper_title":"First return, then explore","paper_url":"/paper/first-return-then-explore","paper_date":"2020-04-27","arxiv_id":"2004.12919","code_links":[{"title":"uber-research/go-explore","url":"https://github.com/uber-research/go-explore"},{"title":"qgallouedec/lge","url":"https://github.com/qgallouedec/lge"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}}},{"leaderboard":"/sota/atari-games-on-atari-2600-alien","slug":"atari-games-on-atari-2600-alien","dataset":"Atari 2600 Alien","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":49,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}}},{"leaderboard":"/sota/atari-games-on-atari-2600-asterix","slug":"atari-games-on-atari-2600-asterix","dataset":"Atari 2600 Asterix","dataset_url":null,"rows_in_archive":49,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-beam-rider","slug":"atari-games-on-atari-2600-beam-rider","dataset":"Atari 2600 Beam Rider","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":49,"metrics":["Score","Return"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}}},{"leaderboard":"/sota/atari-games-on-atari-2600-crazy-climber","slug":"atari-games-on-atari-2600-crazy-climber","dataset":"Atari 2600 Crazy Climber","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":49,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/atari-games-on-atari-2600-amidar","slug":"atari-games-on-atari-2600-amidar","dataset":"Atari 2600 Amidar","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":48,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/atari-games-on-atari-2600-enduro","slug":"atari-games-on-atari-2600-enduro","dataset":"Atari 2600 Enduro","dataset_url":null,"rows_in_archive":48,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-I3","paper_title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","paper_url":"/paper/gdi-rethinking-what-makes-reinforcement","paper_date":"2021-06-11","arxiv_id":"2106.06232","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-battle-zone","slug":"atari-games-on-atari-2600-battle-zone","dataset":"Atari 2600 Battle Zone","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":47,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/atari-games-on-atari-2600-kangaroo","slug":"atari-games-on-atari-2600-kangaroo","dataset":"Atari 2600 Kangaroo","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":47,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/atari-games-on-atari-2600-ms-pacman","slug":"atari-games-on-atari-2600-ms-pacman","dataset":"Atari 2600 Ms. Pacman","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":47,"metrics":["Score","Best Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}}},{"leaderboard":"/sota/atari-games-on-atari-2600-demon-attack","slug":"atari-games-on-atari-2600-demon-attack","dataset":"Atari 2600 Demon Attack","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":46,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-assault","slug":"atari-games-on-atari-2600-assault","dataset":"Atari 2600 Assault","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":45,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}}},{"leaderboard":"/sota/atari-games-on-atari-2600-bank-heist","slug":"atari-games-on-atari-2600-bank-heist","dataset":"Atari 2600 Bank Heist","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":45,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero (Res2 Adam)","paper_title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","paper_url":"/paper/online-and-offline-reinforcement-learning-by","paper_date":"2021-04-13","arxiv_id":"2104.06294","code_links":[{"title":"DHDev0/Muzero-unplugged","url":"https://github.com/DHDev0/Muzero-unplugged"},{"title":"enpasos/muzero","url":"https://github.com/enpasos/muzero"}],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-boxing","slug":"atari-games-on-atari-2600-boxing","dataset":"Atari 2600 Boxing","dataset_url":null,"rows_in_archive":45,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}}},{"leaderboard":"/sota/atari-games-on-atari-2600-centipede","slug":"atari-games-on-atari-2600-centipede","dataset":"Atari 2600 Centipede","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":45,"metrics":["Score"],"first_row_in_archive_order":{"model":"Go-Explore","paper_title":"First return, then explore","paper_url":"/paper/first-return-then-explore","paper_date":"2020-04-27","arxiv_id":"2004.12919","code_links":[{"title":"uber-research/go-explore","url":"https://github.com/uber-research/go-explore"},{"title":"qgallouedec/lge","url":"https://github.com/qgallouedec/lge"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}}},{"leaderboard":"/sota/atari-games-on-atari-2600-chopper-command","slug":"atari-games-on-atari-2600-chopper-command","dataset":"Atari 2600 Chopper Command","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":45,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","paper_url":"/paper/gdi-rethinking-what-makes-reinforcement","paper_date":"2021-06-11","arxiv_id":"2106.06232","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-james-bond","slug":"atari-games-on-atari-2600-james-bond","dataset":"Atari 2600 James Bond","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":45,"metrics":["Score","Medium Human-Normalized Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-krull","slug":"atari-games-on-atari-2600-krull","dataset":"Atari 2600 Krull","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":45,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-bowling","slug":"atari-games-on-atari-2600-bowling","dataset":"Atari 2600 Bowling","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":44,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}}},{"leaderboard":"/sota/atari-games-on-atari-2600-fishing-derby","slug":"atari-games-on-atari-2600-fishing-derby","dataset":"Atari 2600 Fishing Derby","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":44,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}}},{"leaderboard":"/sota/atari-games-on-atari-2600-hero","slug":"atari-games-on-atari-2600-hero","dataset":"Atari 2600 HERO","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":44,"metrics":["Score","Best Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/atari-games-on-atari-2600-road-runner","slug":"atari-games-on-atari-2600-road-runner","dataset":"Atari 2600 Road Runner","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":44,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-time-pilot","slug":"atari-games-on-atari-2600-time-pilot","dataset":"Atari 2600 Time Pilot","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":44,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}}},{"leaderboard":"/sota/atari-games-on-atari-2600-tutankham","slug":"atari-games-on-atari-2600-tutankham","dataset":"Atari 2600 Tutankham","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":44,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/atari-games-on-atari-2600-up-and-down","slug":"atari-games-on-atari-2600-up-and-down","dataset":"Atari 2600 Up and Down","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":44,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-I3","paper_title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","paper_url":"/paper/gdi-rethinking-what-makes-reinforcement","paper_date":"2021-06-11","arxiv_id":"2106.06232","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-asteroids","slug":"atari-games-on-atari-2600-asteroids","dataset":"Atari 2600 Asteroids","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-double-dunk","slug":"atari-games-on-atari-2600-double-dunk","dataset":"Atari 2600 Double Dunk","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"UCT","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","paper_url":"/paper/the-arcade-learning-environment-an-evaluation","paper_date":"2012-07-19","arxiv_id":"1207.4708","code_links":[{"title":"mgbellemare/Arcade-Learning-Environment","url":"https://github.com/mgbellemare/Arcade-Learning-Environment"},{"title":"kenjyoung/MinAtar","url":"https://github.com/kenjyoung/MinAtar"},{"title":"nandomp/AICollaboratory","url":"https://github.com/nandomp/AICollaboratory"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/atari-games-on-atari-2600-gopher","slug":"atari-games-on-atari-2600-gopher","dataset":"Atari 2600 Gopher","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-I3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-ice-hockey","slug":"atari-games-on-atari-2600-ice-hockey","dataset":"Atari 2600 Ice Hockey","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-kung-fu-master","slug":"atari-games-on-atari-2600-kung-fu-master","dataset":"Atari 2600 Kung-Fu Master","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-name-this-game","slug":"atari-games-on-atari-2600-name-this-game","dataset":"Atari 2600 Name This Game","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}}},{"leaderboard":"/sota/atari-games-on-atari-2600-star-gunner","slug":"atari-games-on-atari-2600-star-gunner","dataset":"Atari 2600 Star Gunner","dataset_url":null,"rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/atari-games-on-atari-2600-tennis","slug":"atari-games-on-atari-2600-tennis","dataset":"Atari 2600 Tennis","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":43,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-I3","paper_title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","paper_url":"/paper/gdi-rethinking-what-makes-reinforcement","paper_date":"2021-06-11","arxiv_id":"2106.06232","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-atlantis","slug":"atari-games-on-atari-2600-atlantis","dataset":"Atari 2600 Atlantis","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":42,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-robotank","slug":"atari-games-on-atari-2600-robotank","dataset":"Atari 2600 Robotank","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":42,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}}},{"leaderboard":"/sota/atari-games-on-atari-2600-video-pinball","slug":"atari-games-on-atari-2600-video-pinball","dataset":"Atari 2600 Video Pinball","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":42,"metrics":["Score"],"first_row_in_archive_order":{"model":"R2D2","paper_title":"Recurrent Experience Replay in Distributed Reinforcement Learning","paper_url":"/paper/recurrent-experience-replay-in-distributed","paper_date":"2019-05-01","arxiv_id":null,"code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/r2d2.py"},{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"garymm/earl","url":"https://github.com/garymm/earl/tree/master/earl/agents/r2d2"}],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-river-raid","slug":"atari-games-on-atari-2600-river-raid","dataset":"Atari 2600 River Raid","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":41,"metrics":["Score","Best Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}}},{"leaderboard":"/sota/atari-games-on-atari-2600-wizard-of-wor","slug":"atari-games-on-atari-2600-wizard-of-wor","dataset":"Atari 2600 Wizard of Wor","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":41,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}}},{"leaderboard":"/sota/atari-games-on-atari-2600-zaxxon","slug":"atari-games-on-atari-2600-zaxxon","dataset":"Atari 2600 Zaxxon","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":41,"metrics":["Score"],"first_row_in_archive_order":{"model":"MuZero","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_url":"/paper/mastering-atari-go-chess-and-shogi-by","paper_date":"2019-11-19","arxiv_id":"1911.08265","code_links":[{"title":"werner-duvaud/muzero-general","url":"https://github.com/werner-duvaud/muzero-general"},{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"},{"title":"koulanurag/muzero-pytorch","url":"https://github.com/koulanurag/muzero-pytorch"},{"title":"johan-gras/MuZero","url":"https://github.com/johan-gras/MuZero"},{"title":"kaesve/muzero","url":"https://github.com/kaesve/muzero"},{"title":"Zeta36/muzero","url":"https://github.com/Zeta36/muzero"},{"title":"YuriCat/MuZeroJupyterExample","url":"https://github.com/YuriCat/MuZeroJupyterExample"},{"title":"DHDev0/Muzero","url":"https://github.com/DHDev0/Muzero"},{"title":"foersterrobert/MuZero","url":"https://github.com/foersterrobert/MuZero"},{"title":"k-lombard/CS4641_Project","url":"https://github.com/k-lombard/CS4641_Project"},{"title":"k-lombard/Deep-Learning-Chess-AI","url":"https://github.com/k-lombard/Deep-Learning-Chess-AI"},{"title":"JuanCCS/muzero-jc","url":"https://github.com/JuanCCS/muzero-jc"},{"title":"ZiyuanMa/reversi","url":"https://github.com/ZiyuanMa/reversi"},{"title":"Miatto-research-group/muzero","url":"https://github.com/Miatto-research-group/muzero"},{"title":"colindbrown/columbia-deep-learning-project","url":"https://github.com/colindbrown/columbia-deep-learning-project"},{"title":"SHRIVP/muzero","url":"https://github.com/SHRIVP/muzero"},{"title":"dmiracle/muzero-starter","url":"https://github.com/dmiracle/muzero-starter"},{"title":"snjstudent/MyMuzero","url":"https://github.com/snjstudent/MyMuzero"}],"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}}},{"leaderboard":"/sota/atari-games-on-atari-2600-berzerk","slug":"atari-games-on-atari-2600-berzerk","dataset":"Atari 2600 Berzerk","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":39,"metrics":["Score"],"first_row_in_archive_order":{"model":"Go-Explore","paper_title":"First return, then explore","paper_url":"/paper/first-return-then-explore","paper_date":"2020-04-27","arxiv_id":"2004.12919","code_links":[{"title":"uber-research/go-explore","url":"https://github.com/uber-research/go-explore"},{"title":"qgallouedec/lge","url":"https://github.com/qgallouedec/lge"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}}},{"leaderboard":"/sota/atari-games-on-atari-2600-pitfall","slug":"atari-games-on-atari-2600-pitfall","dataset":"Atari 2600 Pitfall!","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":23,"metrics":["Score"],"first_row_in_archive_order":{"model":"Go-Explore","paper_title":"Go-Explore: a New Approach for Hard-Exploration Problems","paper_url":"/paper/go-explore-a-new-approach-for-hard","paper_date":"2019-01-30","arxiv_id":"1901.10995","code_links":[{"title":"uber-research/go-explore","url":"https://github.com/uber-research/go-explore"},{"title":"Adeikalam/Go-Explore","url":"https://github.com/Adeikalam/Go-Explore"},{"title":"Dorozhko-Anton/go-explore","url":"https://github.com/Dorozhko-Anton/go-explore"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}}},{"leaderboard":"/sota/atari-games-on-atari-2600-skiing","slug":"atari-games-on-atari-2600-skiing","dataset":"Atari 2600 Skiing","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":23,"metrics":["Score"],"first_row_in_archive_order":{"model":"Best Learner","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","paper_url":"/paper/the-arcade-learning-environment-an-evaluation","paper_date":"2012-07-19","arxiv_id":"1207.4708","code_links":[{"title":"mgbellemare/Arcade-Learning-Environment","url":"https://github.com/mgbellemare/Arcade-Learning-Environment"},{"title":"kenjyoung/MinAtar","url":"https://github.com/kenjyoung/MinAtar"},{"title":"nandomp/AICollaboratory","url":"https://github.com/nandomp/AICollaboratory"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/atari-games-on-atari-2600-solaris","slug":"atari-games-on-atari-2600-solaris","dataset":"Atari 2600 Solaris","dataset_url":null,"rows_in_archive":23,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/atari-games-on-atari-2600-defender","slug":"atari-games-on-atari-2600-defender","dataset":"Atari 2600 Defender","dataset_url":null,"rows_in_archive":21,"metrics":["Score"],"first_row_in_archive_order":{"model":"CGP","paper_title":"Evolving simple programs for playing Atari games","paper_url":"/paper/evolving-simple-programs-for-playing-atari","paper_date":"2018-06-14","arxiv_id":"1806.05695","code_links":[{"title":"ShuhuaGao/gpFlappyBird","url":"https://github.com/ShuhuaGao/gpFlappyBird"},{"title":"JacobLaney/cgp-tetris","url":"https://github.com/JacobLaney/cgp-tetris"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/atari-games-on-atari-2600-phoenix","slug":"atari-games-on-atari-2600-phoenix","dataset":"Atari 2600 Phoenix","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":21,"metrics":["Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-yars-revenge","slug":"atari-games-on-atari-2600-yars-revenge","dataset":"Atari 2600 Yars Revenge","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":17,"metrics":["Score"],"first_row_in_archive_order":{"model":"Agent57","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_url":"/paper/agent57-outperforming-the-atari-human","paper_date":"2020-03-30","arxiv_id":"2003.13350","code_links":[{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"pocokhc/agent57","url":"https://github.com/pocokhc/agent57"},{"title":"yuta0821/agent57_pytorch","url":"https://github.com/yuta0821/agent57_pytorch"},{"title":"Nkluge-correa/teeny-tiny_castle","url":"https://github.com/Nkluge-correa/teeny-tiny_castle"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/atari-games-on-atari-2600-surround","slug":"atari-games-on-atari-2600-surround","dataset":"Atari 2600 Surround","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":15,"metrics":["Score"],"first_row_in_archive_order":{"model":"NoisyNet-Dueling","paper_title":"Noisy Networks for Exploration","paper_url":"/paper/noisy-networks-for-exploration","paper_date":"2017-06-30","arxiv_id":"1706.10295","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"Kaixhin/NoisyNet-A3C","url":"https://github.com/Kaixhin/NoisyNet-A3C"},{"title":"BY571/DQN-Atari-Agents","url":"https://github.com/BY571/DQN-Atari-Agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"seungjaeryanlee/rldb","url":"https://github.com/seungjaeryanlee/rldb"},{"title":"behzadanksu/rl-attack","url":"https://github.com/behzadanksu/rl-attack"},{"title":"LilTwo/DRL-using-PyTorch","url":"https://github.com/LilTwo/DRL-using-PyTorch"},{"title":"hw9603/DQfD-PyTorch","url":"https://github.com/hw9603/DQfD-PyTorch"},{"title":"thomashirtz/noisy-networks","url":"https://github.com/thomashirtz/noisy-networks"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"YanSong97/Master-thesis","url":"https://github.com/YanSong97/Master-thesis"},{"title":"behzadanksu/rlattack-dev","url":"https://github.com/behzadanksu/rlattack-dev"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}}},{"leaderboard":"/sota/atari-games-on-atari-games","slug":"atari-games-on-atari-games","dataset":"Atari games","dataset_url":null,"rows_in_archive":12,"metrics":["Mean Human Normalized Score","Medium Human-Normalized Score"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-57","slug":"atari-games-on-atari-57","dataset":"Atari-57","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":11,"metrics":["Mean Human Normalized Score","Human World Record Breakthrough"],"first_row_in_archive_order":{"model":"LBC","paper_title":"Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection","paper_url":"/paper/learnable-behavior-control-breaking-atari","paper_date":"2023-05-09","arxiv_id":"2305.05239","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-game","slug":"atari-games-on-atari-game","dataset":"atari game","dataset_url":null,"rows_in_archive":9,"metrics":["Human World Record Breakthrough"],"first_row_in_archive_order":{"model":"GDI-H3","paper_title":"Generalized Data Distribution Iteration","paper_url":"/paper/generalized-data-distribution-iteration","paper_date":"2022-06-07","arxiv_id":"2206.03192","code_links":[],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-elevator-action","slug":"atari-games-on-atari-2600-elevator-action","dataset":"Atari 2600 Elevator Action","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":3,"metrics":["Score"],"first_row_in_archive_order":{"model":"Persistent AL","paper_title":"Increasing the Action Gap: New Operators for Reinforcement Learning","paper_url":"/paper/increasing-the-action-gap-new-operators-for","paper_date":"2015-12-15","arxiv_id":"1512.04860","code_links":[{"title":"janhuenermann/neurojs","url":"https://github.com/janhuenermann/neurojs"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"}],"syntology":null}},{"leaderboard":"/sota/atari-games-on-atari-2600-pooyan","slug":"atari-games-on-atari-2600-pooyan","dataset":"Atari 2600 Pooyan","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":3,"metrics":["Score"],"first_row_in_archive_order":{"model":"UCT","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","paper_url":"/paper/the-arcade-learning-environment-an-evaluation","paper_date":"2012-07-19","arxiv_id":"1207.4708","code_links":[{"title":"mgbellemare/Arcade-Learning-Environment","url":"https://github.com/mgbellemare/Arcade-Learning-Environment"},{"title":"kenjyoung/MinAtar","url":"https://github.com/kenjyoung/MinAtar"},{"title":"nandomp/AICollaboratory","url":"https://github.com/nandomp/AICollaboratory"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/atari-games-on-atari-2600-carnival","slug":"atari-games-on-atari-2600-carnival","dataset":"Atari 2600 Carnival","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"UCT","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","paper_url":"/paper/the-arcade-learning-environment-an-evaluation","paper_date":"2012-07-19","arxiv_id":"1207.4708","code_links":[{"title":"mgbellemare/Arcade-Learning-Environment","url":"https://github.com/mgbellemare/Arcade-Learning-Environment"},{"title":"kenjyoung/MinAtar","url":"https://github.com/kenjyoung/MinAtar"},{"title":"nandomp/AICollaboratory","url":"https://github.com/nandomp/AICollaboratory"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/atari-games-on-atari-2600-journey-escape","slug":"atari-games-on-atari-2600-journey-escape","dataset":"Atari 2600 Journey Escape","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"UCT","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","paper_url":"/paper/the-arcade-learning-environment-an-evaluation","paper_date":"2012-07-19","arxiv_id":"1207.4708","code_links":[{"title":"mgbellemare/Arcade-Learning-Environment","url":"https://github.com/mgbellemare/Arcade-Learning-Environment"},{"title":"kenjyoung/MinAtar","url":"https://github.com/kenjyoung/MinAtar"},{"title":"nandomp/AICollaboratory","url":"https://github.com/nandomp/AICollaboratory"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/atari-games-on-atari-pong","slug":"atari-games-on-atari-pong","dataset":"Atari Pong","dataset_url":null,"rows_in_archive":1,"metrics":["Total Reward"],"first_row_in_archive_order":{"model":"GATN-TL-Atari Pong","paper_title":"Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains","paper_url":"/paper/generalized-adaptive-transfer-network","paper_date":"2025-07-02","arxiv_id":"2507.03026","code_links":[{"title":"abhi460729/GATN","url":"https://github.com/abhi460729/GATN"}],"syntology":null}}],"datasets":[{"url":"/dataset/arcade-learning-environment","name":"Arcade Learning Environment","full_name":"Arcade Learning Environment","num_papers_in_archive":366},{"url":"/dataset/dqn-replay-dataset","name":"DQN Replay Dataset","full_name":"","num_papers_in_archive":31},{"url":"/dataset/atari-head","name":"Atari-HEAD","full_name":null,"num_papers_in_archive":9},{"url":"/dataset/atari-grand-challenge","name":"Atari Grand Challenge","full_name":"","num_papers_in_archive":7},{"url":"/dataset/atariari","name":"AtariARI","full_name":"Atari Annotated RAM Interface","num_papers_in_archive":6},{"url":"/dataset/caglar","name":"RLU","full_name":"RL Unplugged","num_papers_in_archive":2}],"subtasks":[{"url":"/task/montezumas-revenge","name":"Montezuma's Revenge"}],"parent_tasks":[{"url":"/task/video-games","name":"Video Games"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":313,"tagged_in_all":625,"items":[{"url":"/paper/playing-atari-with-deep-reinforcement","title":"Playing Atari with Deep Reinforcement Learning","date":"2013-12-19","arxiv_id":"1312.5602","repositories_listed":112,"syntology":{"n":117,"n_ran":56,"n_unverified":61,"n_pointer_only":56}},{"url":"/paper/deep-reinforcement-learning-with-double-q","title":"Deep Reinforcement Learning with Double Q-learning","date":"2015-09-22","arxiv_id":"1509.06461","repositories_listed":97,"syntology":{"n":106,"n_ran":55,"n_unverified":51,"n_pointer_only":57}},{"url":"/paper/prioritized-experience-replay","title":"Prioritized Experience Replay","date":"2015-11-18","arxiv_id":"1511.05952","repositories_listed":77,"syntology":{"n":111,"n_ran":78,"n_unverified":33,"n_pointer_only":43}},{"url":"/paper/dueling-network-architectures-for-deep","title":"Dueling Network Architectures for Deep Reinforcement Learning","date":"2015-11-20","arxiv_id":"1511.06581","repositories_listed":73,"syntology":{"n":11,"n_ran":5,"n_unverified":6,"n_pointer_only":6}},{"url":"/paper/asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","arxiv_id":"1602.01783","repositories_listed":70,"syntology":{"n":95,"n_ran":38,"n_unverified":57,"n_pointer_only":12}},{"url":"/paper/rainbow-combining-improvements-in-deep","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","date":"2017-10-06","arxiv_id":"1710.02298","repositories_listed":34,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/overcoming-catastrophic-forgetting-in-neural","title":"Overcoming catastrophic forgetting in neural networks","date":"2016-12-02","arxiv_id":"1612.00796","repositories_listed":29,"syntology":{"n":22,"n_ran":14,"n_unverified":8,"n_pointer_only":4}},{"url":"/paper/an-intriguing-failing-of-convolutional-neural","title":"An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution","date":"2018-07-09","arxiv_id":"1807.03247","repositories_listed":24,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/impala-scalable-distributed-deep-rl-with","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","date":"2018-02-05","arxiv_id":"1802.01561","repositories_listed":24,"syntology":{"n":34,"n_ran":16,"n_unverified":18,"n_pointer_only":3}},{"url":"/paper/trust-region-policy-optimization","title":"Trust Region Policy Optimization","date":"2015-02-19","arxiv_id":"1502.05477","repositories_listed":24,"syntology":{"n":17,"n_ran":7,"n_unverified":10,"n_pointer_only":7}},{"url":"/paper/evolution-strategies-as-a-scalable","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","date":"2017-03-10","arxiv_id":"1703.03864","repositories_listed":23,"syntology":{"n":29,"n_ran":7,"n_unverified":22,"n_pointer_only":1}},{"url":"/paper/exploration-by-random-network-distillation","title":"Exploration by Random Network Distillation","date":"2018-10-30","arxiv_id":"1810.12894","repositories_listed":22,"syntology":{"n":43,"n_ran":26,"n_unverified":17,"n_pointer_only":15}},{"url":"/paper/a-distributional-perspective-on-reinforcement","title":"A Distributional Perspective on Reinforcement Learning","date":"2017-07-21","arxiv_id":"1707.06887","repositories_listed":22,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/decision-transformer-reinforcement-learning","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","date":"2021-06-02","arxiv_id":"2106.01345","repositories_listed":20,"syntology":{"n":26,"n_ran":17,"n_unverified":9,"n_pointer_only":6}},{"url":"/paper/implicit-quantile-networks-for-distributional","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","date":"2018-06-14","arxiv_id":"1806.06923","repositories_listed":19,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/mastering-atari-go-chess-and-shogi-by","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","date":"2019-11-19","arxiv_id":"1911.08265","repositories_listed":18,"syntology":{"n":64,"n_ran":43,"n_unverified":21,"n_pointer_only":62}},{"url":"/paper/distributional-reinforcement-learning-with-1","title":"Distributional Reinforcement Learning with Quantile Regression","date":"2017-10-27","arxiv_id":"1710.10044","repositories_listed":17,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/distributed-prioritized-experience-replay","title":"Distributed Prioritized Experience Replay","date":"2018-03-02","arxiv_id":"1803.00933","repositories_listed":15,"syntology":{"n":15,"n_ran":0,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/noisy-networks-for-exploration","title":"Noisy Networks for Exploration","date":"2017-06-30","arxiv_id":"1706.10295","repositories_listed":15,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/benchmarking-deep-reinforcement-learning-for","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","date":"2016-04-22","arxiv_id":"1604.06778","repositories_listed":15,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/soft-actor-critic-for-discrete-action","title":"Soft Actor-Critic for Discrete Action Settings","date":"2019-10-16","arxiv_id":"1910.07207","repositories_listed":13,"syntology":{"n":18,"n_ran":4,"n_unverified":14,"n_pointer_only":3}},{"url":"/paper/vizdoom-a-doom-based-ai-research-platform-for","title":"ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning","date":"2016-05-06","arxiv_id":"1605.02097","repositories_listed":10,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":5}},{"url":"/paper/mastering-atari-with-discrete-world-models-1","title":"Mastering Atari with Discrete World Models","date":"2020-10-05","arxiv_id":"2010.02193","repositories_listed":9,"syntology":{"n":15,"n_ran":3,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/accelerated-methods-for-deep-reinforcement","title":"Accelerated Methods for Deep Reinforcement Learning","date":"2018-03-07","arxiv_id":"1803.02811","repositories_listed":8,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/scalable-trust-region-method-for-deep","title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","date":"2017-08-17","arxiv_id":"1708.05144","repositories_listed":8,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/human-level-control-through-deep","title":"Human level control through deep reinforcement learning","date":"2015-02-25","arxiv_id":null,"repositories_listed":8,"syntology":null},{"url":"/paper/curl-contrastive-unsupervised-representations","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","date":"2020-04-08","arxiv_id":"2004.04136","repositories_listed":7,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/unsupervised-state-representation-learning-in","title":"Unsupervised State Representation Learning in Atari","date":"2019-06-19","arxiv_id":"1906.08226","repositories_listed":7,"syntology":{"n":10,"n_ran":3,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/fractal-ai-a-fragile-theory-of-intelligence","title":"Fractal AI: A fragile theory of intelligence","date":"2018-03-13","arxiv_id":"1803.05049","repositories_listed":7,"syntology":null},{"url":"/paper/revisiting-the-arcade-learning-environment","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","date":"2017-09-18","arxiv_id":"1709.06009","repositories_listed":7,"syntology":null}],"syntology_records":27,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}