{"task":"Atari Games","dataset":"Atari-57","metric_names":["Mean Human Normalized Score","Human World Record Breakthrough"],"rows":[{"id":57678,"task":"Atari Games","parent_task":null,"dataset":"Atari-57","model_name":"LBC","metrics":{"Human World Record Breakthrough":"24","Mean Human Normalized Score":"10077.52%"},"paper_url":"https://arxiv.org/abs/2305.05239v1","paper_title":"Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection","paper_date":"2023-05-09","code_links":[],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57679,"task":"Atari Games","parent_task":null,"dataset":"Atari-57","model_name":"GDI-H3(200M frames)","metrics":{"Human World Record Breakthrough":"22","Mean Human Normalized Score":"9620.98%"},"paper_url":"https://arxiv.org/abs/2106.06232v6","paper_title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","paper_date":"2021-06-11","code_links":[],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57680,"task":"Atari Games","parent_task":null,"dataset":"Atari-57","model_name":"GDI-H3","metrics":{"Human World Record Breakthrough":"22","Mean Human Normalized Score":"9620.33%"},"paper_url":"https://arxiv.org/abs/2206.03192v4","paper_title":"Generalized Data Distribution Iteration","paper_date":"2022-06-07","code_links":[],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57681,"task":"Atari Games","parent_task":null,"dataset":"Atari-57","model_name":"GDI-I3","metrics":{"Human World Record Breakthrough":"17","Mean Human Normalized Score":"7810.1%"},"paper_url":"https://arxiv.org/abs/2206.03192v4","paper_title":"Generalized Data Distribution Iteration","paper_date":"2022-06-07","code_links":[],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57682,"task":"Atari Games","parent_task":null,"dataset":"Atari-57","model_name":"MuZero","metrics":{"Human World Record Breakthrough":"19","Mean Human Normalized Score":"4996.20%"},"paper_url":"https://arxiv.org/abs/1911.08265v2","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_date":"2019-11-19","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"}],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57683,"task":"Atari Games","parent_task":null,"dataset":"Atari-57","model_name":"R2D2","metrics":{"Human World Record Breakthrough":"15","Mean Human Normalized Score":"3374.31%"},"paper_url":"https://openreview.net/forum?id=r1lyTjAqYX","paper_title":"Recurrent Experience Replay in Distributed Reinforcement Learning","paper_date":"2019-05-01","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"}],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57684,"task":"Atari Games","parent_task":null,"dataset":"Atari-57","model_name":"LASER","metrics":{"Human World Record Breakthrough":"7","Mean Human Normalized Score":"1741.36%"},"paper_url":"https://arxiv.org/abs/1909.11583v2","paper_title":"Off-Policy Actor-Critic with Shared Experience Replay","paper_date":"2019-09-25","code_links":[],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57685,"task":"Atari Games","parent_task":null,"dataset":"Atari-57","model_name":"IMPALA, deep","metrics":{"Human World Record Breakthrough":"3","Mean Human Normalized Score":"957.34%"},"paper_url":"http://arxiv.org/abs/1802.01561v3","paper_title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","paper_date":"2018-02-05","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/impala.py"},{"title":"deepmind/haiku","url":"https://github.com/deepmind/haiku"},{"title":"deepmind/rlax","url":"https://github.com/deepmind/rlax"},{"title":"google-deepmind/scalable_agent","url":"https://github.com/google-deepmind/scalable_agent"},{"title":"deepmind/scalable_agent","url":"https://github.com/deepmind/scalable_agent"},{"title":"facebookresearch/torchbeast","url":"https://github.com/facebookresearch/torchbeast"},{"title":"crazydonkey200/neural-symbolic-machines","url":"https://github.com/crazydonkey200/neural-symbolic-machines"},{"title":"deepmind/streetlearn","url":"https://github.com/deepmind/streetlearn"},{"title":"google-deepmind/streetlearn","url":"https://github.com/google-deepmind/streetlearn"},{"title":"jerrodparker20/adaptive-transformers-in-rl","url":"https://github.com/jerrodparker20/adaptive-transformers-in-rl"},{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"google-research/valan","url":"https://github.com/google-research/valan"},{"title":"seolhokim/DistributedRL-Pytorch-Ray","url":"https://github.com/seolhokim/DistributedRL-Pytorch-Ray"},{"title":"facebookresearch/gala","url":"https://github.com/facebookresearch/gala"},{"title":"haje01/impala","url":"https://github.com/haje01/impala"},{"title":"Sheepsody/Batched-Impala-PyTorch","url":"https://github.com/Sheepsody/Batched-Impala-PyTorch"},{"title":"urw7rs/spiralpp","url":"https://github.com/urw7rs/spiralpp"},{"title":"villinvic/Georges","url":"https://github.com/villinvic/Georges"},{"title":"seolhokim/SimpleDistributedRL","url":"https://github.com/seolhokim/SimpleDistributedRL"},{"title":"threewisemonkeys-as/torched_impala","url":"https://github.com/threewisemonkeys-as/torched_impala"},{"title":"theSparta/neural-symbolic-machines","url":"https://github.com/theSparta/neural-symbolic-machines"},{"title":"heiner/scalable_agent","url":"https://github.com/heiner/scalable_agent"},{"title":"windstrip/DeepMind-StreetLearn","url":"https://github.com/windstrip/DeepMind-StreetLearn"}],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57686,"task":"Atari Games","parent_task":null,"dataset":"Atari-57","model_name":"Rainbow DQN","metrics":{"Human World Record Breakthrough":"4","Mean Human Normalized Score":"873.97%"},"paper_url":"http://arxiv.org/abs/1710.02298v1","paper_title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","paper_date":"2017-10-06","code_links":[{"title":"thu-ml/tianshou","url":"https://github.com/thu-ml/tianshou"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"title":"facebookresearch/Horizon","url":"https://github.com/facebookresearch/Horizon"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/rainbow.py"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"Kaixhin/Rainbow","url":"https://github.com/Kaixhin/Rainbow"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"BY571/DQN-Atari-Agents","url":"https://github.com/BY571/DQN-Atari-Agents"},{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"floringogianu/atari-agents","url":"https://github.com/floringogianu/atari-agents"},{"title":"deconlabs/Binanace_trading_simulation","url":"https://github.com/deconlabs/Binanace_trading_simulation"},{"title":"deconlabs/TradingZoo-Dynamic-fee-simulation","url":"https://github.com/deconlabs/TradingZoo-Dynamic-fee-simulation"},{"title":"deconlabs/Binanace-trading-simulation","url":"https://github.com/deconlabs/Binanace-trading-simulation"},{"title":"atavakol/action-hypergraph-networks","url":"https://github.com/atavakol/action-hypergraph-networks"},{"title":"robintyh1/icml2021-pengqlambda","url":"https://github.com/robintyh1/icml2021-pengqlambda"},{"title":"mingyip/Rainbow-Reinforcement-Learning-For-Chess-Games","url":"https://github.com/mingyip/Rainbow-Reinforcement-Learning-For-Chess-Games"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"jacobkooi/hadamax","url":"https://github.com/jacobkooi/hadamax"},{"title":"mohith-sakthivel/rainbow_dqn","url":"https://github.com/mohith-sakthivel/rainbow_dqn"},{"title":"roboticist-by-day/Rainbow_DQN","url":"https://github.com/roboticist-by-day/Rainbow_DQN"},{"title":"liuyuezhang/pyrl","url":"https://github.com/liuyuezhang/pyrl"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"dsapandora/s_cera","url":"https://github.com/dsapandora/s_cera"},{"title":"lireer/ricochet-robot-solver","url":"https://github.com/lireer/ricochet-robot-solver"},{"title":"coreylowman/rl_simply","url":"https://github.com/coreylowman/rl_simply"},{"title":"jvoynow/DQN-analysis-with-2048","url":"https://github.com/jvoynow/DQN-analysis-with-2048"},{"title":"amzoyang/CS-221-Final-Project","url":"https://github.com/amzoyang/CS-221-Final-Project"},{"title":"JayLohokare/banana-world-navigation","url":"https://github.com/JayLohokare/banana-world-navigation"},{"title":"daviddcho/supermario","url":"https://github.com/daviddcho/supermario"},{"title":"htdt/rainbow","url":"https://github.com/htdt/rainbow"},{"title":"odokumaci/rainbow-unity-obstacle-tower-challenge","url":"https://github.com/odokumaci/rainbow-unity-obstacle-tower-challenge"},{"title":"efg59/Rainbow","url":"https://github.com/efg59/Rainbow"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"}],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57687,"task":"Atari Games","parent_task":null,"dataset":"Atari-57","model_name":"M-IQN","metrics":{"Mean Human Normalized Score":"504%"},"paper_url":"https://arxiv.org/abs/2007.14430v3","paper_title":"Munchausen Reinforcement Learning","paper_date":"2020-07-28","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/munchausen_rl"},{"title":"deepmind/acme","url":"https://github.com/deepmind/acme/tree/master/acme/agents/jax/dqn"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"floringogianu/atari-agents","url":"https://github.com/floringogianu/atari-agents"},{"title":"BY571/Munchausen-RL","url":"https://github.com/BY571/Munchausen-RL"},{"title":"lingweizhu/Pytorch-MunchausenActorCritic","url":"https://github.com/lingweizhu/Pytorch-MunchausenActorCritic"}],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57688,"task":"Atari Games","parent_task":null,"dataset":"Atari-57","model_name":"GDI-H3","metrics":{},"paper_url":"https://arxiv.org/abs/2106.06232v6","paper_title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","paper_date":"2021-06-11","code_links":[],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60205,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari-57","model_name":"LBC","metrics":{"Human World Record Breakthrough":"24","Mean Human Normalized Score":"10077.52%"},"paper_url":"https://arxiv.org/abs/2305.05239v1","paper_title":"Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection","paper_date":"2023-05-09","code_links":[],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60206,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari-57","model_name":"GDI-H3(200M frames)","metrics":{"Human World Record Breakthrough":"22","Mean Human Normalized Score":"9620.98%"},"paper_url":"https://arxiv.org/abs/2106.06232v6","paper_title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","paper_date":"2021-06-11","code_links":[],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60207,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari-57","model_name":"GDI-H3","metrics":{"Human World Record Breakthrough":"22","Mean Human Normalized Score":"9620.33%"},"paper_url":"https://arxiv.org/abs/2206.03192v4","paper_title":"Generalized Data Distribution Iteration","paper_date":"2022-06-07","code_links":[],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60208,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari-57","model_name":"GDI-I3","metrics":{"Human World Record Breakthrough":"17","Mean Human Normalized Score":"7810.1%"},"paper_url":"https://arxiv.org/abs/2206.03192v4","paper_title":"Generalized Data Distribution Iteration","paper_date":"2022-06-07","code_links":[],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60209,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari-57","model_name":"MuZero","metrics":{"Human World Record Breakthrough":"19","Mean Human Normalized Score":"4996.20%"},"paper_url":"https://arxiv.org/abs/1911.08265v2","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","paper_date":"2019-11-19","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"}],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60210,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari-57","model_name":"R2D2","metrics":{"Human World Record Breakthrough":"15","Mean Human Normalized Score":"3374.31%"},"paper_url":"https://openreview.net/forum?id=r1lyTjAqYX","paper_title":"Recurrent Experience Replay in Distributed Reinforcement Learning","paper_date":"2019-05-01","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"}],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60211,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari-57","model_name":"LASER","metrics":{"Human World Record Breakthrough":"7","Mean Human Normalized Score":"1741.36%"},"paper_url":"https://arxiv.org/abs/1909.11583v2","paper_title":"Off-Policy Actor-Critic with Shared Experience Replay","paper_date":"2019-09-25","code_links":[],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60212,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari-57","model_name":"IMPALA, deep","metrics":{"Human World Record Breakthrough":"3","Mean Human Normalized Score":"957.34%"},"paper_url":"http://arxiv.org/abs/1802.01561v3","paper_title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","paper_date":"2018-02-05","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/impala.py"},{"title":"deepmind/haiku","url":"https://github.com/deepmind/haiku"},{"title":"deepmind/rlax","url":"https://github.com/deepmind/rlax"},{"title":"google-deepmind/scalable_agent","url":"https://github.com/google-deepmind/scalable_agent"},{"title":"deepmind/scalable_agent","url":"https://github.com/deepmind/scalable_agent"},{"title":"facebookresearch/torchbeast","url":"https://github.com/facebookresearch/torchbeast"},{"title":"crazydonkey200/neural-symbolic-machines","url":"https://github.com/crazydonkey200/neural-symbolic-machines"},{"title":"deepmind/streetlearn","url":"https://github.com/deepmind/streetlearn"},{"title":"google-deepmind/streetlearn","url":"https://github.com/google-deepmind/streetlearn"},{"title":"jerrodparker20/adaptive-transformers-in-rl","url":"https://github.com/jerrodparker20/adaptive-transformers-in-rl"},{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"google-research/valan","url":"https://github.com/google-research/valan"},{"title":"seolhokim/DistributedRL-Pytorch-Ray","url":"https://github.com/seolhokim/DistributedRL-Pytorch-Ray"},{"title":"facebookresearch/gala","url":"https://github.com/facebookresearch/gala"},{"title":"haje01/impala","url":"https://github.com/haje01/impala"},{"title":"Sheepsody/Batched-Impala-PyTorch","url":"https://github.com/Sheepsody/Batched-Impala-PyTorch"},{"title":"urw7rs/spiralpp","url":"https://github.com/urw7rs/spiralpp"},{"title":"villinvic/Georges","url":"https://github.com/villinvic/Georges"},{"title":"seolhokim/SimpleDistributedRL","url":"https://github.com/seolhokim/SimpleDistributedRL"},{"title":"threewisemonkeys-as/torched_impala","url":"https://github.com/threewisemonkeys-as/torched_impala"},{"title":"theSparta/neural-symbolic-machines","url":"https://github.com/theSparta/neural-symbolic-machines"},{"title":"heiner/scalable_agent","url":"https://github.com/heiner/scalable_agent"},{"title":"windstrip/DeepMind-StreetLearn","url":"https://github.com/windstrip/DeepMind-StreetLearn"}],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60213,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari-57","model_name":"Rainbow DQN","metrics":{"Human World Record Breakthrough":"4","Mean Human Normalized Score":"873.97%"},"paper_url":"http://arxiv.org/abs/1710.02298v1","paper_title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","paper_date":"2017-10-06","code_links":[{"title":"thu-ml/tianshou","url":"https://github.com/thu-ml/tianshou"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"title":"facebookresearch/Horizon","url":"https://github.com/facebookresearch/Horizon"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/rainbow.py"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"Kaixhin/Rainbow","url":"https://github.com/Kaixhin/Rainbow"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"BY571/DQN-Atari-Agents","url":"https://github.com/BY571/DQN-Atari-Agents"},{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"floringogianu/atari-agents","url":"https://github.com/floringogianu/atari-agents"},{"title":"deconlabs/Binanace_trading_simulation","url":"https://github.com/deconlabs/Binanace_trading_simulation"},{"title":"deconlabs/TradingZoo-Dynamic-fee-simulation","url":"https://github.com/deconlabs/TradingZoo-Dynamic-fee-simulation"},{"title":"deconlabs/Binanace-trading-simulation","url":"https://github.com/deconlabs/Binanace-trading-simulation"},{"title":"atavakol/action-hypergraph-networks","url":"https://github.com/atavakol/action-hypergraph-networks"},{"title":"robintyh1/icml2021-pengqlambda","url":"https://github.com/robintyh1/icml2021-pengqlambda"},{"title":"mingyip/Rainbow-Reinforcement-Learning-For-Chess-Games","url":"https://github.com/mingyip/Rainbow-Reinforcement-Learning-For-Chess-Games"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"jacobkooi/hadamax","url":"https://github.com/jacobkooi/hadamax"},{"title":"mohith-sakthivel/rainbow_dqn","url":"https://github.com/mohith-sakthivel/rainbow_dqn"},{"title":"roboticist-by-day/Rainbow_DQN","url":"https://github.com/roboticist-by-day/Rainbow_DQN"},{"title":"liuyuezhang/pyrl","url":"https://github.com/liuyuezhang/pyrl"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"dsapandora/s_cera","url":"https://github.com/dsapandora/s_cera"},{"title":"lireer/ricochet-robot-solver","url":"https://github.com/lireer/ricochet-robot-solver"},{"title":"coreylowman/rl_simply","url":"https://github.com/coreylowman/rl_simply"},{"title":"jvoynow/DQN-analysis-with-2048","url":"https://github.com/jvoynow/DQN-analysis-with-2048"},{"title":"amzoyang/CS-221-Final-Project","url":"https://github.com/amzoyang/CS-221-Final-Project"},{"title":"JayLohokare/banana-world-navigation","url":"https://github.com/JayLohokare/banana-world-navigation"},{"title":"daviddcho/supermario","url":"https://github.com/daviddcho/supermario"},{"title":"htdt/rainbow","url":"https://github.com/htdt/rainbow"},{"title":"odokumaci/rainbow-unity-obstacle-tower-challenge","url":"https://github.com/odokumaci/rainbow-unity-obstacle-tower-challenge"},{"title":"efg59/Rainbow","url":"https://github.com/efg59/Rainbow"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"}],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60214,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari-57","model_name":"M-IQN","metrics":{"Mean Human Normalized Score":"504%"},"paper_url":"https://arxiv.org/abs/2007.14430v3","paper_title":"Munchausen Reinforcement Learning","paper_date":"2020-07-28","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/munchausen_rl"},{"title":"deepmind/acme","url":"https://github.com/deepmind/acme/tree/master/acme/agents/jax/dqn"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"floringogianu/atari-agents","url":"https://github.com/floringogianu/atari-agents"},{"title":"BY571/Munchausen-RL","url":"https://github.com/BY571/Munchausen-RL"},{"title":"lingweizhu/Pytorch-MunchausenActorCritic","url":"https://github.com/lingweizhu/Pytorch-MunchausenActorCritic"}],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60215,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari-57","model_name":"GDI-H3","metrics":{},"paper_url":"https://arxiv.org/abs/2106.06232v6","paper_title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","paper_date":"2021-06-11","code_links":[],"metrics_order":"[\"Mean Human Normalized Score\", \"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]}]}