{"task":"Atari Games","dataset":"Atari 2600 Pitfall!","metric_names":["Score"],"rows":[{"id":57552,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"Go-Explore","metrics":{"Score":"102571"},"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":"[\"Score\"]","area":"Playing Games","uses_additional_data":1,"source":"archive","tags":[]},{"id":57553,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"Agent57","metrics":{"Score":"18756.01"},"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":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57554,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"Go-Explore","metrics":{"Score":"6954"},"paper_url":"https://arxiv.org/abs/2004.12919v6","paper_title":"First return, then explore","paper_date":"2020-04-27","code_links":[{"title":"uber-research/go-explore","url":"https://github.com/uber-research/go-explore"},{"title":"qgallouedec/lge","url":"https://github.com/qgallouedec/lge"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57555,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"IQN","metrics":{"Score":"0"},"paper_url":"http://arxiv.org/abs/1806.06923v1","paper_title":"Implicit Quantile Networks for Distributional Reinforcement Learning","paper_date":"2018-06-14","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/iqn.py"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"Kchu/DeepRL_CK","url":"https://github.com/Kchu/DeepRL_CK"},{"title":"ku2482/fqf-iqn-qrdqn.pytorch","url":"https://github.com/ku2482/fqf-iqn-qrdqn.pytorch"},{"title":"ku2482/rljax","url":"https://github.com/ku2482/rljax"},{"title":"BY571/IQN","url":"https://github.com/BY571/IQN"},{"title":"marload/dist-rl-tf2","url":"https://github.com/marload/dist-rl-tf2"},{"title":"marload/DistRL-TensorFlow2","url":"https://github.com/marload/DistRL-TensorFlow2"},{"title":"SeungeonBaek/discrete-agents-test","url":"https://github.com/SeungeonBaek/discrete-agents-test"},{"title":"Abdelhamid-bouzid/Distributional-RL","url":"https://github.com/Abdelhamid-bouzid/Distributional-RL"},{"title":"pihey1995/DistributionalRL","url":"https://github.com/pihey1995/DistributionalRL"},{"title":"sjYoondeltar/IQN_example","url":"https://github.com/sjYoondeltar/IQN_example"},{"title":"sjYoondeltar/myRL_example","url":"https://github.com/sjYoondeltar/myRL_example"},{"title":"ACampero/dopamine","url":"https://github.com/ACampero/dopamine"},{"title":"robinzixuan/IQN_Agent","url":"https://github.com/robinzixuan/IQN_Agent"},{"title":"KatyNTsachi/Hierarchical-RL","url":"https://github.com/KatyNTsachi/Hierarchical-RL"},{"title":"V0LsTeR/dopamine_prioritized_buffer","url":"https://github.com/V0LsTeR/dopamine_prioritized_buffer"},{"title":"V0LsTeR/DQN_heap","url":"https://github.com/V0LsTeR/DQN_heap"},{"title":"GoingMyWay/dopamine_reward_decomposition","url":"https://github.com/GoingMyWay/dopamine_reward_decomposition"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57556,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"MuZero","metrics":{"Score":"0.00"},"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":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57557,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"R2D2","metrics":{"Score":"0.0"},"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":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57558,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"CGP","metrics":{"Score":"0"},"paper_url":"http://arxiv.org/abs/1806.05695v1","paper_title":"Evolving simple programs for playing Atari games","paper_date":"2018-06-14","code_links":[{"title":"ShuhuaGao/gpFlappyBird","url":"https://github.com/ShuhuaGao/gpFlappyBird"},{"title":"JacobLaney/cgp-tetris","url":"https://github.com/JacobLaney/cgp-tetris"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57559,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"NoisyNet-Dueling","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/1706.10295v3","paper_title":"Noisy Networks for Exploration","paper_date":"2017-06-30","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"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57560,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"POP3D","metrics":{"Score":"0"},"paper_url":"http://arxiv.org/abs/1807.00442v4","paper_title":"Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization","paper_date":"2018-07-02","code_links":[{"title":"cxxgtxy/POP3D","url":"https://github.com/cxxgtxy/POP3D"},{"title":"paperwithcode/pop3d","url":"https://github.com/paperwithcode/pop3d"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57561,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"Advantage Learning","metrics":{"Score":"0"},"paper_url":"http://arxiv.org/abs/1512.04860v1","paper_title":"Increasing the Action Gap: New Operators for Reinforcement Learning","paper_date":"2015-12-15","code_links":[{"title":"janhuenermann/neurojs","url":"https://github.com/janhuenermann/neurojs"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57562,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"QR-DQN-1","metrics":{"Score":"0"},"paper_url":"http://arxiv.org/abs/1710.10044v1","paper_title":"Distributional Reinforcement Learning with Quantile Regression","paper_date":"2017-10-27","code_links":[{"title":"DLR-RM/stable-baselines3","url":"https://github.com/DLR-RM/stable-baselines3"},{"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/blob/main/ding/policy/qrdqn.py"},{"title":"Kchu/DeepRL_CK","url":"https://github.com/Kchu/DeepRL_CK"},{"title":"ku2482/fqf-iqn-qrdqn.pytorch","url":"https://github.com/ku2482/fqf-iqn-qrdqn.pytorch"},{"title":"ku2482/rljax","url":"https://github.com/ku2482/rljax"},{"title":"senya-ashukha/quantile-regression-dqn-pytorch","url":"https://github.com/senya-ashukha/quantile-regression-dqn-pytorch"},{"title":"ars-ashuha/quantile-regression-dqn-pytorch","url":"https://github.com/ars-ashuha/quantile-regression-dqn-pytorch"},{"title":"marload/DistRL-TensorFlow2","url":"https://github.com/marload/DistRL-TensorFlow2"},{"title":"marload/dist-rl-tf2","url":"https://github.com/marload/dist-rl-tf2"},{"title":"SeungeonBaek/discrete-agents-test","url":"https://github.com/SeungeonBaek/discrete-agents-test"},{"title":"sannebh/riskaverse_rl","url":"https://github.com/sannebh/riskaverse_rl"},{"title":"Abdelhamid-bouzid/Distributional-RL","url":"https://github.com/Abdelhamid-bouzid/Distributional-RL"},{"title":"ZiyiLiubird/DeepMARL-PyTorch","url":"https://github.com/ZiyiLiubird/DeepMARL-PyTorch"},{"title":"robinzixuan/IQN_Agent","url":"https://github.com/robinzixuan/IQN_Agent"},{"title":"sannebh/riskaverse","url":"https://github.com/sannebh/riskaverse"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57563,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"DreamerV2","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/2010.02193v4","paper_title":"Mastering Atari with Discrete World Models","paper_date":"2020-10-05","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"danijar/dreamerv2","url":"https://github.com/danijar/dreamerv2"},{"title":"andrejorsula/drl_grasping","url":"https://github.com/andrejorsula/drl_grasping"},{"title":"RajGhugare19/dreamerv2","url":"https://github.com/RajGhugare19/dreamerv2"},{"title":"adityabingi/Dreamer","url":"https://github.com/adityabingi/Dreamer"},{"title":"iglu-contest/iglu-builder-baseline-dreamer","url":"https://github.com/iglu-contest/iglu-builder-baseline-dreamer"},{"title":"chandar-lab/LoCA2","url":"https://github.com/chandar-lab/LoCA2"},{"title":"CVC-Lab/SAC-for-H-Bond-Learning","url":"https://github.com/CVC-Lab/SAC-for-H-Bond-Learning"},{"title":"LukeBolly/dreamerv2","url":"https://github.com/LukeBolly/dreamerv2"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57564,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"MuZero (Res2 Adam)","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/2104.06294v1","paper_title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","paper_date":"2021-04-13","code_links":[{"title":"DHDev0/Muzero-unplugged","url":"https://github.com/DHDev0/Muzero-unplugged"},{"title":"enpasos/muzero","url":"https://github.com/enpasos/muzero"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57565,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"GDI-I3","metrics":{"Score":"0"},"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":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57566,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"GDI-I3","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/2206.03192v4","paper_title":"Generalized Data Distribution Iteration","paper_date":"2022-06-07","code_links":[],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57567,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"DNA","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/2206.10027v2","paper_title":"DNA: Proximal Policy Optimization with a Dual Network Architecture","paper_date":"2022-06-20","code_links":[{"title":"maitchison/PPO","url":"https://github.com/maitchison/PPO"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57568,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"SND-V","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/2302.11563v4","paper_title":"Self-supervised network distillation: an effective approach to exploration in sparse reward environments","paper_date":"2023-02-22","code_links":[{"title":"iskandor/snd","url":"https://github.com/iskandor/snd"},{"title":"michalnand/reinforcement_learning","url":"https://github.com/michalnand/reinforcement_learning"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57569,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"SND-VIC","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/2302.11563v4","paper_title":"Self-supervised network distillation: an effective approach to exploration in sparse reward environments","paper_date":"2023-02-22","code_links":[{"title":"iskandor/snd","url":"https://github.com/iskandor/snd"},{"title":"michalnand/reinforcement_learning","url":"https://github.com/michalnand/reinforcement_learning"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57570,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"ASL DDQN","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/2305.04180v3","paper_title":"Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity","paper_date":"2023-05-07","code_links":[{"title":"xinjinghao/color","url":"https://github.com/xinjinghao/color"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57571,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"RND","metrics":{"Score":"-3"},"paper_url":"http://arxiv.org/abs/1810.12894v1","paper_title":"Exploration by Random Network Distillation","paper_date":"2018-10-30","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/reward_model/rnd_reward_model.py"},{"title":"openai/random-network-distillation","url":"https://github.com/openai/random-network-distillation"},{"title":"rle-foundation/rlexplore","url":"https://github.com/rle-foundation/rlexplore"},{"title":"jcwleo/random-network-distillation-pytorch","url":"https://github.com/jcwleo/random-network-distillation-pytorch"},{"title":"alirezakazemipour/ppo-rnd","url":"https://github.com/alirezakazemipour/ppo-rnd"},{"title":"uoe-agents/derl","url":"https://github.com/uoe-agents/derl"},{"title":"microsoft/strategically_efficient_rl","url":"https://github.com/microsoft/strategically_efficient_rl"},{"title":"jhare96/reinforcement-learning","url":"https://github.com/jhare96/reinforcement-learning"},{"title":"DuaneNielsen/rnd","url":"https://github.com/DuaneNielsen/rnd"},{"title":"riveSunder/carle","url":"https://github.com/riveSunder/carle"},{"title":"kngwyu/intrinsic-rewards","url":"https://github.com/kngwyu/intrinsic-rewards"},{"title":"Narsil/rl-baselines","url":"https://github.com/Narsil/rl-baselines"},{"title":"Justkim/random-network-distillation-pytorch","url":"https://github.com/Justkim/random-network-distillation-pytorch"},{"title":"Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-","url":"https://github.com/Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-"},{"title":"balloch/rl-exploration-transfer","url":"https://github.com/balloch/rl-exploration-transfer"},{"title":"LeejwUniverse/RL_Exploration_Pytorch","url":"https://github.com/LeejwUniverse/RL_Exploration_Pytorch"},{"title":"forevergj/multithreading_ppo_RND","url":"https://github.com/forevergj/multithreading_ppo_RND"},{"title":"michalnand/reinforcement_learning","url":"https://github.com/michalnand/reinforcement_learning"},{"title":"jakegrigsby/supersonic","url":"https://github.com/jakegrigsby/supersonic"},{"title":"lgerrets/rl18-curiosity","url":"https://github.com/lgerrets/rl18-curiosity"},{"title":"riveSunder/moving_in_morley","url":"https://github.com/riveSunder/moving_in_morley"},{"title":"bacdavid/RND-O","url":"https://github.com/bacdavid/RND-O"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57572,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"Ape-X","metrics":{"Score":"-0.6"},"paper_url":"http://arxiv.org/abs/1803.00933v1","paper_title":"Distributed Prioritized Experience Replay","paper_date":"2018-03-02","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"vwxyzjn/cleanrl","url":"https://github.com/vwxyzjn/cleanrl"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"uber-research/ape-x","url":"https://github.com/uber-research/ape-x"},{"title":"belepi93/Ape-X","url":"https://github.com/belepi93/Ape-X"},{"title":"neka-nat/distributed_rl","url":"https://github.com/neka-nat/distributed_rl"},{"title":"Lyusungwon/apex_dqn_pytorch","url":"https://github.com/Lyusungwon/apex_dqn_pytorch"},{"title":"dannysdeng/dqn-pytorch","url":"https://github.com/dannysdeng/dqn-pytorch"},{"title":"ku2482/rltorch","url":"https://github.com/ku2482/rltorch"},{"title":"haje01/distper","url":"https://github.com/haje01/distper"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"eladsar/rbi","url":"https://github.com/eladsar/rbi"},{"title":"sherry4186/Distributed-DQN","url":"https://github.com/sherry4186/Distributed-DQN"},{"title":"cindycia/Atari-SAC-Discrete","url":"https://github.com/cindycia/Atari-SAC-Discrete"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57573,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"IMPALA (deep)","metrics":{"Score":"-1.66"},"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":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":57574,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Pitfall!","model_name":"GDI-H3","metrics":{"Score":"-4.345"},"paper_url":"https://arxiv.org/abs/2206.03192v4","paper_title":"Generalized Data Distribution Iteration","paper_date":"2022-06-07","code_links":[],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60079,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"Go-Explore","metrics":{"Score":"102571"},"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":"[\"Score\"]","area":"Playing Games","uses_additional_data":1,"source":"archive","tags":[]},{"id":60080,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"Agent57","metrics":{"Score":"18756.01"},"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":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60081,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"Go-Explore","metrics":{"Score":"6954"},"paper_url":"https://arxiv.org/abs/2004.12919v6","paper_title":"First return, then explore","paper_date":"2020-04-27","code_links":[{"title":"uber-research/go-explore","url":"https://github.com/uber-research/go-explore"},{"title":"qgallouedec/lge","url":"https://github.com/qgallouedec/lge"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60082,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"IQN","metrics":{"Score":"0"},"paper_url":"http://arxiv.org/abs/1806.06923v1","paper_title":"Implicit Quantile Networks for Distributional Reinforcement Learning","paper_date":"2018-06-14","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/iqn.py"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"Kchu/DeepRL_CK","url":"https://github.com/Kchu/DeepRL_CK"},{"title":"ku2482/fqf-iqn-qrdqn.pytorch","url":"https://github.com/ku2482/fqf-iqn-qrdqn.pytorch"},{"title":"ku2482/rljax","url":"https://github.com/ku2482/rljax"},{"title":"BY571/IQN","url":"https://github.com/BY571/IQN"},{"title":"marload/dist-rl-tf2","url":"https://github.com/marload/dist-rl-tf2"},{"title":"marload/DistRL-TensorFlow2","url":"https://github.com/marload/DistRL-TensorFlow2"},{"title":"SeungeonBaek/discrete-agents-test","url":"https://github.com/SeungeonBaek/discrete-agents-test"},{"title":"Abdelhamid-bouzid/Distributional-RL","url":"https://github.com/Abdelhamid-bouzid/Distributional-RL"},{"title":"pihey1995/DistributionalRL","url":"https://github.com/pihey1995/DistributionalRL"},{"title":"sjYoondeltar/IQN_example","url":"https://github.com/sjYoondeltar/IQN_example"},{"title":"sjYoondeltar/myRL_example","url":"https://github.com/sjYoondeltar/myRL_example"},{"title":"ACampero/dopamine","url":"https://github.com/ACampero/dopamine"},{"title":"robinzixuan/IQN_Agent","url":"https://github.com/robinzixuan/IQN_Agent"},{"title":"KatyNTsachi/Hierarchical-RL","url":"https://github.com/KatyNTsachi/Hierarchical-RL"},{"title":"V0LsTeR/dopamine_prioritized_buffer","url":"https://github.com/V0LsTeR/dopamine_prioritized_buffer"},{"title":"V0LsTeR/DQN_heap","url":"https://github.com/V0LsTeR/DQN_heap"},{"title":"GoingMyWay/dopamine_reward_decomposition","url":"https://github.com/GoingMyWay/dopamine_reward_decomposition"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60083,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"MuZero","metrics":{"Score":"0.00"},"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":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60084,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"R2D2","metrics":{"Score":"0.0"},"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":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60085,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"CGP","metrics":{"Score":"0"},"paper_url":"http://arxiv.org/abs/1806.05695v1","paper_title":"Evolving simple programs for playing Atari games","paper_date":"2018-06-14","code_links":[{"title":"ShuhuaGao/gpFlappyBird","url":"https://github.com/ShuhuaGao/gpFlappyBird"},{"title":"JacobLaney/cgp-tetris","url":"https://github.com/JacobLaney/cgp-tetris"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60086,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"NoisyNet-Dueling","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/1706.10295v3","paper_title":"Noisy Networks for Exploration","paper_date":"2017-06-30","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"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60087,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"POP3D","metrics":{"Score":"0"},"paper_url":"http://arxiv.org/abs/1807.00442v4","paper_title":"Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization","paper_date":"2018-07-02","code_links":[{"title":"cxxgtxy/POP3D","url":"https://github.com/cxxgtxy/POP3D"},{"title":"paperwithcode/pop3d","url":"https://github.com/paperwithcode/pop3d"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60088,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"Advantage Learning","metrics":{"Score":"0"},"paper_url":"http://arxiv.org/abs/1512.04860v1","paper_title":"Increasing the Action Gap: New Operators for Reinforcement Learning","paper_date":"2015-12-15","code_links":[{"title":"janhuenermann/neurojs","url":"https://github.com/janhuenermann/neurojs"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60089,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"QR-DQN-1","metrics":{"Score":"0"},"paper_url":"http://arxiv.org/abs/1710.10044v1","paper_title":"Distributional Reinforcement Learning with Quantile Regression","paper_date":"2017-10-27","code_links":[{"title":"DLR-RM/stable-baselines3","url":"https://github.com/DLR-RM/stable-baselines3"},{"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/blob/main/ding/policy/qrdqn.py"},{"title":"Kchu/DeepRL_CK","url":"https://github.com/Kchu/DeepRL_CK"},{"title":"ku2482/fqf-iqn-qrdqn.pytorch","url":"https://github.com/ku2482/fqf-iqn-qrdqn.pytorch"},{"title":"ku2482/rljax","url":"https://github.com/ku2482/rljax"},{"title":"senya-ashukha/quantile-regression-dqn-pytorch","url":"https://github.com/senya-ashukha/quantile-regression-dqn-pytorch"},{"title":"ars-ashuha/quantile-regression-dqn-pytorch","url":"https://github.com/ars-ashuha/quantile-regression-dqn-pytorch"},{"title":"marload/DistRL-TensorFlow2","url":"https://github.com/marload/DistRL-TensorFlow2"},{"title":"marload/dist-rl-tf2","url":"https://github.com/marload/dist-rl-tf2"},{"title":"SeungeonBaek/discrete-agents-test","url":"https://github.com/SeungeonBaek/discrete-agents-test"},{"title":"sannebh/riskaverse_rl","url":"https://github.com/sannebh/riskaverse_rl"},{"title":"Abdelhamid-bouzid/Distributional-RL","url":"https://github.com/Abdelhamid-bouzid/Distributional-RL"},{"title":"ZiyiLiubird/DeepMARL-PyTorch","url":"https://github.com/ZiyiLiubird/DeepMARL-PyTorch"},{"title":"robinzixuan/IQN_Agent","url":"https://github.com/robinzixuan/IQN_Agent"},{"title":"sannebh/riskaverse","url":"https://github.com/sannebh/riskaverse"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60090,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"DreamerV2","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/2010.02193v4","paper_title":"Mastering Atari with Discrete World Models","paper_date":"2020-10-05","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"danijar/dreamerv2","url":"https://github.com/danijar/dreamerv2"},{"title":"andrejorsula/drl_grasping","url":"https://github.com/andrejorsula/drl_grasping"},{"title":"RajGhugare19/dreamerv2","url":"https://github.com/RajGhugare19/dreamerv2"},{"title":"adityabingi/Dreamer","url":"https://github.com/adityabingi/Dreamer"},{"title":"iglu-contest/iglu-builder-baseline-dreamer","url":"https://github.com/iglu-contest/iglu-builder-baseline-dreamer"},{"title":"chandar-lab/LoCA2","url":"https://github.com/chandar-lab/LoCA2"},{"title":"CVC-Lab/SAC-for-H-Bond-Learning","url":"https://github.com/CVC-Lab/SAC-for-H-Bond-Learning"},{"title":"LukeBolly/dreamerv2","url":"https://github.com/LukeBolly/dreamerv2"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60091,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"MuZero (Res2 Adam)","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/2104.06294v1","paper_title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","paper_date":"2021-04-13","code_links":[{"title":"DHDev0/Muzero-unplugged","url":"https://github.com/DHDev0/Muzero-unplugged"},{"title":"enpasos/muzero","url":"https://github.com/enpasos/muzero"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60092,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"GDI-I3","metrics":{"Score":"0"},"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":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60093,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"GDI-I3","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/2206.03192v4","paper_title":"Generalized Data Distribution Iteration","paper_date":"2022-06-07","code_links":[],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60094,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"DNA","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/2206.10027v2","paper_title":"DNA: Proximal Policy Optimization with a Dual Network Architecture","paper_date":"2022-06-20","code_links":[{"title":"maitchison/PPO","url":"https://github.com/maitchison/PPO"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60095,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"SND-V","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/2302.11563v4","paper_title":"Self-supervised network distillation: an effective approach to exploration in sparse reward environments","paper_date":"2023-02-22","code_links":[{"title":"iskandor/snd","url":"https://github.com/iskandor/snd"},{"title":"michalnand/reinforcement_learning","url":"https://github.com/michalnand/reinforcement_learning"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60096,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"SND-VIC","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/2302.11563v4","paper_title":"Self-supervised network distillation: an effective approach to exploration in sparse reward environments","paper_date":"2023-02-22","code_links":[{"title":"iskandor/snd","url":"https://github.com/iskandor/snd"},{"title":"michalnand/reinforcement_learning","url":"https://github.com/michalnand/reinforcement_learning"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60097,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"ASL DDQN","metrics":{"Score":"0"},"paper_url":"https://arxiv.org/abs/2305.04180v3","paper_title":"Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity","paper_date":"2023-05-07","code_links":[{"title":"xinjinghao/color","url":"https://github.com/xinjinghao/color"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60098,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"RND","metrics":{"Score":"-3"},"paper_url":"http://arxiv.org/abs/1810.12894v1","paper_title":"Exploration by Random Network Distillation","paper_date":"2018-10-30","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/reward_model/rnd_reward_model.py"},{"title":"openai/random-network-distillation","url":"https://github.com/openai/random-network-distillation"},{"title":"rle-foundation/rlexplore","url":"https://github.com/rle-foundation/rlexplore"},{"title":"jcwleo/random-network-distillation-pytorch","url":"https://github.com/jcwleo/random-network-distillation-pytorch"},{"title":"alirezakazemipour/ppo-rnd","url":"https://github.com/alirezakazemipour/ppo-rnd"},{"title":"uoe-agents/derl","url":"https://github.com/uoe-agents/derl"},{"title":"microsoft/strategically_efficient_rl","url":"https://github.com/microsoft/strategically_efficient_rl"},{"title":"jhare96/reinforcement-learning","url":"https://github.com/jhare96/reinforcement-learning"},{"title":"DuaneNielsen/rnd","url":"https://github.com/DuaneNielsen/rnd"},{"title":"riveSunder/carle","url":"https://github.com/riveSunder/carle"},{"title":"kngwyu/intrinsic-rewards","url":"https://github.com/kngwyu/intrinsic-rewards"},{"title":"Narsil/rl-baselines","url":"https://github.com/Narsil/rl-baselines"},{"title":"Justkim/random-network-distillation-pytorch","url":"https://github.com/Justkim/random-network-distillation-pytorch"},{"title":"Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-","url":"https://github.com/Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-"},{"title":"balloch/rl-exploration-transfer","url":"https://github.com/balloch/rl-exploration-transfer"},{"title":"LeejwUniverse/RL_Exploration_Pytorch","url":"https://github.com/LeejwUniverse/RL_Exploration_Pytorch"},{"title":"forevergj/multithreading_ppo_RND","url":"https://github.com/forevergj/multithreading_ppo_RND"},{"title":"michalnand/reinforcement_learning","url":"https://github.com/michalnand/reinforcement_learning"},{"title":"jakegrigsby/supersonic","url":"https://github.com/jakegrigsby/supersonic"},{"title":"lgerrets/rl18-curiosity","url":"https://github.com/lgerrets/rl18-curiosity"},{"title":"riveSunder/moving_in_morley","url":"https://github.com/riveSunder/moving_in_morley"},{"title":"bacdavid/RND-O","url":"https://github.com/bacdavid/RND-O"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60099,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"Ape-X","metrics":{"Score":"-0.6"},"paper_url":"http://arxiv.org/abs/1803.00933v1","paper_title":"Distributed Prioritized Experience Replay","paper_date":"2018-03-02","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"vwxyzjn/cleanrl","url":"https://github.com/vwxyzjn/cleanrl"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"uber-research/ape-x","url":"https://github.com/uber-research/ape-x"},{"title":"belepi93/Ape-X","url":"https://github.com/belepi93/Ape-X"},{"title":"neka-nat/distributed_rl","url":"https://github.com/neka-nat/distributed_rl"},{"title":"Lyusungwon/apex_dqn_pytorch","url":"https://github.com/Lyusungwon/apex_dqn_pytorch"},{"title":"dannysdeng/dqn-pytorch","url":"https://github.com/dannysdeng/dqn-pytorch"},{"title":"ku2482/rltorch","url":"https://github.com/ku2482/rltorch"},{"title":"haje01/distper","url":"https://github.com/haje01/distper"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"eladsar/rbi","url":"https://github.com/eladsar/rbi"},{"title":"sherry4186/Distributed-DQN","url":"https://github.com/sherry4186/Distributed-DQN"},{"title":"cindycia/Atari-SAC-Discrete","url":"https://github.com/cindycia/Atari-SAC-Discrete"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60100,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"IMPALA (deep)","metrics":{"Score":"-1.66"},"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":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60101,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Pitfall!","model_name":"GDI-H3","metrics":{"Score":"-4.345"},"paper_url":"https://arxiv.org/abs/2206.03192v4","paper_title":"Generalized Data Distribution Iteration","paper_date":"2022-06-07","code_links":[],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]}]}