{"task":"Atari Games","dataset":"atari game","metric_names":["Human World Record Breakthrough"],"rows":[{"id":55991,"task":"Atari Games","parent_task":null,"dataset":"atari game","model_name":"GDI-H3","metrics":{"Human World Record Breakthrough":"22"},"paper_url":"https://arxiv.org/abs/2206.03192v4","paper_title":"Generalized Data Distribution Iteration","paper_date":"2022-06-07","code_links":[],"metrics_order":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":55992,"task":"Atari Games","parent_task":null,"dataset":"atari game","model_name":"Muzero","metrics":{"Human World Record Breakthrough":"19"},"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":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":55993,"task":"Atari Games","parent_task":null,"dataset":"atari game","model_name":"Agent57","metrics":{"Human World Record Breakthrough":"18"},"paper_url":"https://arxiv.org/abs/2003.13350v1","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_date":"2020-03-30","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"}],"metrics_order":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":55994,"task":"Atari Games","parent_task":null,"dataset":"atari game","model_name":"Go-Explore","metrics":{"Human World Record Breakthrough":"17"},"paper_url":"https://arxiv.org/abs/1901.10995v4","paper_title":"Go-Explore: a New Approach for Hard-Exploration Problems","paper_date":"2019-01-30","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"}],"metrics_order":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":55995,"task":"Atari Games","parent_task":null,"dataset":"atari game","model_name":"GDI-I3","metrics":{"Human World Record Breakthrough":"17"},"paper_url":"https://arxiv.org/abs/2206.03192v4","paper_title":"Generalized Data Distribution Iteration","paper_date":"2022-06-07","code_links":[],"metrics_order":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":55996,"task":"Atari Games","parent_task":null,"dataset":"atari game","model_name":"R2D2","metrics":{"Human World Record Breakthrough":"15"},"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":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":55997,"task":"Atari Games","parent_task":null,"dataset":"atari game","model_name":"NGU","metrics":{"Human World Record Breakthrough":"8"},"paper_url":"https://arxiv.org/abs/2002.06038v1","paper_title":"Never Give Up: Learning Directed Exploration Strategies","paper_date":"2020-02-14","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"rle-foundation/rlexplore","url":"https://github.com/rle-foundation/rlexplore"},{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"Coac/never-give-up","url":"https://github.com/Coac/never-give-up"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"},{"title":"balloch/rl-exploration-transfer","url":"https://github.com/balloch/rl-exploration-transfer"}],"metrics_order":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":55998,"task":"Atari Games","parent_task":null,"dataset":"atari game","model_name":"Muesli","metrics":{"Human World Record Breakthrough":"5"},"paper_url":"https://arxiv.org/abs/2104.06159v2","paper_title":"Muesli: Combining Improvements in Policy Optimization","paper_date":"2021-04-13","code_links":[{"title":"YuriCat/MuesliJupyterExample","url":"https://github.com/YuriCat/MuesliJupyterExample"},{"title":"Itomigna2/Muesli-lunarlander","url":"https://github.com/Itomigna2/Muesli-lunarlander"}],"metrics_order":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":55999,"task":"Atari Games","parent_task":null,"dataset":"atari game","model_name":"Rainbow","metrics":{"Human World Record Breakthrough":"4"},"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":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58518,"task":"Atari Games","parent_task":"Video Games","dataset":"atari game","model_name":"GDI-H3","metrics":{"Human World Record Breakthrough":"22"},"paper_url":"https://arxiv.org/abs/2206.03192v4","paper_title":"Generalized Data Distribution Iteration","paper_date":"2022-06-07","code_links":[],"metrics_order":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58519,"task":"Atari Games","parent_task":"Video Games","dataset":"atari game","model_name":"Muzero","metrics":{"Human World Record Breakthrough":"19"},"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":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58520,"task":"Atari Games","parent_task":"Video Games","dataset":"atari game","model_name":"Agent57","metrics":{"Human World Record Breakthrough":"18"},"paper_url":"https://arxiv.org/abs/2003.13350v1","paper_title":"Agent57: Outperforming the Atari Human Benchmark","paper_date":"2020-03-30","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"}],"metrics_order":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58521,"task":"Atari Games","parent_task":"Video Games","dataset":"atari game","model_name":"Go-Explore","metrics":{"Human World Record Breakthrough":"17"},"paper_url":"https://arxiv.org/abs/1901.10995v4","paper_title":"Go-Explore: a New Approach for Hard-Exploration Problems","paper_date":"2019-01-30","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"}],"metrics_order":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58522,"task":"Atari Games","parent_task":"Video Games","dataset":"atari game","model_name":"GDI-I3","metrics":{"Human World Record Breakthrough":"17"},"paper_url":"https://arxiv.org/abs/2206.03192v4","paper_title":"Generalized Data Distribution Iteration","paper_date":"2022-06-07","code_links":[],"metrics_order":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58523,"task":"Atari Games","parent_task":"Video Games","dataset":"atari game","model_name":"R2D2","metrics":{"Human World Record Breakthrough":"15"},"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":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58524,"task":"Atari Games","parent_task":"Video Games","dataset":"atari game","model_name":"NGU","metrics":{"Human World Record Breakthrough":"8"},"paper_url":"https://arxiv.org/abs/2002.06038v1","paper_title":"Never Give Up: Learning Directed Exploration Strategies","paper_date":"2020-02-14","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"rle-foundation/rlexplore","url":"https://github.com/rle-foundation/rlexplore"},{"title":"michaelnny/deep_rl_zoo","url":"https://github.com/michaelnny/deep_rl_zoo"},{"title":"Coac/never-give-up","url":"https://github.com/Coac/never-give-up"},{"title":"YHL04/agent57","url":"https://github.com/YHL04/agent57"},{"title":"balloch/rl-exploration-transfer","url":"https://github.com/balloch/rl-exploration-transfer"}],"metrics_order":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58525,"task":"Atari Games","parent_task":"Video Games","dataset":"atari game","model_name":"Muesli","metrics":{"Human World Record Breakthrough":"5"},"paper_url":"https://arxiv.org/abs/2104.06159v2","paper_title":"Muesli: Combining Improvements in Policy Optimization","paper_date":"2021-04-13","code_links":[{"title":"YuriCat/MuesliJupyterExample","url":"https://github.com/YuriCat/MuesliJupyterExample"},{"title":"Itomigna2/Muesli-lunarlander","url":"https://github.com/Itomigna2/Muesli-lunarlander"}],"metrics_order":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58526,"task":"Atari Games","parent_task":"Video Games","dataset":"atari game","model_name":"Rainbow","metrics":{"Human World Record Breakthrough":"4"},"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":"[\"Human World Record Breakthrough\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]}]}