{"task":"Atari Games","dataset":"Atari 2600 Berzerk","metric_names":["Score"],"rows":[{"id":58043,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"Go-Explore","metrics":{"Score":"197376"},"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":58044,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"MuZero","metrics":{"Score":"85932.60"},"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":58045,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"Agent57","metrics":{"Score":"61507.83"},"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":58046,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"Ape-X","metrics":{"Score":"57196.7"},"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":58047,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"R2D2","metrics":{"Score":"53318.7"},"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":58048,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"DNA","metrics":{"Score":"19789"},"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":58049,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"GDI-H3","metrics":{"Score":"14649"},"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":58050,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"FQF","metrics":{"Score":"12422.2"},"paper_url":"https://arxiv.org/abs/1911.02140v3","paper_title":"Fully Parameterized Quantile Function for Distributional Reinforcement Learning","paper_date":"2019-11-05","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"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":"microsoft/FQF","url":"https://github.com/microsoft/FQF"},{"title":"BY571/FQF-and-Extensions","url":"https://github.com/BY571/FQF-and-Extensions"},{"title":"robinzixuan/IQN_Agent","url":"https://github.com/robinzixuan/IQN_Agent"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58051,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"GDI-I3","metrics":{"Score":"7607"},"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":58052,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"GDI-I3","metrics":{"Score":"7607"},"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":58053,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"Prior+Duel noop","metrics":{"Score":"3409.0"},"paper_url":"http://arxiv.org/abs/1511.06581v3","paper_title":"Dueling Network Architectures for Deep Reinforcement Learning","paper_date":"2015-11-20","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"facebookresearch/Horizon","url":"https://github.com/facebookresearch/Horizon"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"ku2482/sac-discrete.pytorch","url":"https://github.com/ku2482/sac-discrete.pytorch"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"BY571/DQN-Atari-Agents","url":"https://github.com/BY571/DQN-Atari-Agents"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"JuliaPOMDP/DeepQLearning.jl","url":"https://github.com/JuliaPOMDP/DeepQLearning.jl"},{"title":"gouxiangchen/dueling-DQN-pytorch","url":"https://github.com/gouxiangchen/dueling-DQN-pytorch"},{"title":"R-Sweke/DeepQ-Decoding","url":"https://github.com/R-Sweke/DeepQ-Decoding"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"ethanmclark1/carla_aebs","url":"https://github.com/ethanmclark1/carla_aebs"},{"title":"clarky104/carla_aebs","url":"https://github.com/clarky104/carla_aebs"},{"title":"KDL-umass/saliency_maps","url":"https://github.com/KDL-umass/saliency_maps"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"alessandrositta/Flatland_challenge","url":"https://github.com/alessandrositta/Flatland_challenge"},{"title":"MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"nathanin/pad","url":"https://github.com/nathanin/pad"},{"title":"zynk13/dueling-dqn-Reinforcement-learning","url":"https://github.com/zynk13/dueling-dqn-Reinforcement-learning"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"prajwalgatti/DRL-Continuous-Control","url":"https://github.com/prajwalgatti/DRL-Continuous-Control"},{"title":"la3lma/chezjulia","url":"https://github.com/la3lma/chezjulia"},{"title":"la3lma/Chez","url":"https://github.com/la3lma/Chez"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"prajwalgatti/DRL-Navigation","url":"https://github.com/prajwalgatti/DRL-Navigation"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning","url":"https://github.com/manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"iDataist/Navigation-with-Deep-Q-Network","url":"https://github.com/iDataist/Navigation-with-Deep-Q-Network"},{"title":"jsztompka/DuelDQN","url":"https://github.com/jsztompka/DuelDQN"},{"title":"170928/-Review-Dueling-Deep-Q-Network","url":"https://github.com/170928/-Review-Dueling-Deep-Q-Network"},{"title":"Brandon-Rozek/DeepRL","url":"https://github.com/Brandon-Rozek/DeepRL"},{"title":"abryeemessi/Wednesday","url":"https://github.com/abryeemessi/Wednesday"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"JBGUIMBAUD/deep-reenforcement-learning","url":"https://github.com/JBGUIMBAUD/deep-reenforcement-learning"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"opplieam/Pong-Deep-RL","url":"https://github.com/opplieam/Pong-Deep-RL"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58054,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"QR-DQN-1","metrics":{"Score":"3117"},"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":58055,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"MuZero (Res2 Adam)","metrics":{"Score":"2705.82"},"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":58056,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"ASL DDQN","metrics":{"Score":"2597.2"},"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":58057,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"Reactor 500M","metrics":{"Score":"2303.1"},"paper_url":"http://arxiv.org/abs/1704.04651v2","paper_title":"The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning","paper_date":"2017-04-15","code_links":[],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58058,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"Prior+Duel hs","metrics":{"Score":"2178.6"},"paper_url":"http://arxiv.org/abs/1509.06461v3","paper_title":"Deep Reinforcement Learning with Double Q-learning","paper_date":"2015-09-22","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"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":"MaximeVandegar/Papers-in-100-Lines-of-Code","url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Deep_Reinforcement_Learning_with_Double_Q_learning"},{"title":"deepmind/rlax","url":"https://github.com/deepmind/rlax"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"yukezhu/tensorflow-reinforce","url":"https://github.com/yukezhu/tensorflow-reinforce"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"YuansongFeng/MadMario","url":"https://github.com/YuansongFeng/MadMario"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning","url":"https://github.com/jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning"},{"title":"microsoft/med-deadend","url":"https://github.com/microsoft/med-deadend"},{"title":"xtma/simple-pytorch-rl","url":"https://github.com/xtma/simple-pytorch-rl"},{"title":"moduIo/Deep-Q-network","url":"https://github.com/moduIo/Deep-Q-network"},{"title":"Denbergvanthijs/imbDRL","url":"https://github.com/Denbergvanthijs/imbDRL"},{"title":"kochlisGit/autonomous-vehicles-agent","url":"https://github.com/kochlisGit/autonomous-vehicles-agent"},{"title":"matthewsparr/Deep-Zork","url":"https://github.com/matthewsparr/Deep-Zork"},{"title":"hamishs/JAX-RL","url":"https://github.com/hamishs/JAX-RL"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"anh-nn01/Lunar-Lander-Double-Deep-Q-Networks","url":"https://github.com/anh-nn01/Lunar-Lander-Double-Deep-Q-Networks"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"PeterJochem/Double_Deep_QLearning","url":"https://github.com/PeterJochem/Double_Deep_QLearning"},{"title":"PeterJochem/Deep_RL","url":"https://github.com/PeterJochem/Deep_RL"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"pathway/alphaxos","url":"https://github.com/pathway/alphaxos"},{"title":"OscarHuangWind/Preference-Guided-DQN-Atari","url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari"},{"title":"paintception/Deep-Quality-Value-Family-","url":"https://github.com/paintception/Deep-Quality-Value-Family-"},{"title":"paintception/Deep-Quality-Value-Family","url":"https://github.com/paintception/Deep-Quality-Value-Family"},{"title":"KelvinYang0320/deepbots-panda","url":"https://github.com/KelvinYang0320/deepbots-panda"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"tkcoding/Stock_DRL","url":"https://github.com/tkcoding/Stock_DRL"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"yzheng51/rl-dino-run","url":"https://github.com/yzheng51/rl-dino-run"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"amirmirzaei79/CartPole-DQN-And-DDQN","url":"https://github.com/amirmirzaei79/CartPole-DQN-And-DDQN"},{"title":"xgfelicia/Reinforcement-Learning","url":"https://github.com/xgfelicia/Reinforcement-Learning"},{"title":"RandyDeng/gym_connect4","url":"https://github.com/RandyDeng/gym_connect4"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"Rabrg/dqn","url":"https://github.com/Rabrg/dqn"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"molomono/CartPole_Optimized_DDQN","url":"https://github.com/molomono/CartPole_Optimized_DDQN"},{"title":"Roman-Kozachek/TradeBot","url":"https://github.com/Roman-Kozachek/TradeBot"},{"title":"gznyyb/deep_reinforcement_learning_Pong","url":"https://github.com/gznyyb/deep_reinforcement_learning_Pong"},{"title":"lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning","url":"https://github.com/lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning"},{"title":"ifestus/rl","url":"https://github.com/ifestus/rl"},{"title":"wmol4/Pytorch_DDQN_Unity_Navigation","url":"https://github.com/wmol4/Pytorch_DDQN_Unity_Navigation"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"jadag/DDQN_mario","url":"https://github.com/jadag/DDQN_mario"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"jvoynow/DQN-analysis-with-2048","url":"https://github.com/jvoynow/DQN-analysis-with-2048"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"aman-khurana/deep-q-learning","url":"https://github.com/aman-khurana/deep-q-learning"},{"title":"yaxinchen666/dce_pricingRL","url":"https://github.com/yaxinchen666/dce_pricingRL"},{"title":"puppetect/TradingBot-tensorflow","url":"https://github.com/puppetect/TradingBot-tensorflow"},{"title":"ianlimle/ItsMeMario","url":"https://github.com/ianlimle/ItsMeMario"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"NikolausBerl/Udacity_DRLN_Navigation_Project","url":"https://github.com/NikolausBerl/Udacity_DRLN_Navigation_Project"},{"title":"jeffery1236/Atari_DoubleDeepQNetwork","url":"https://github.com/jeffery1236/Atari_DoubleDeepQNetwork"},{"title":"Codernauti/Exploration-of-DQN-in-CartPole-Environment","url":"https://github.com/Codernauti/Exploration-of-DQN-in-CartPole-Environment"},{"title":"JustinStitt/acrobotDDQN","url":"https://github.com/JustinStitt/acrobotDDQN"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"},{"title":"zhengant/dqn_reversi","url":"https://github.com/zhengant/dqn_reversi"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"daviddcho/supermario","url":"https://github.com/daviddcho/supermario"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"seacevedo/ReinforcementLearningProjects","url":"https://github.com/seacevedo/ReinforcementLearningProjects"},{"title":"JonasRSV/DQNTensorflow","url":"https://github.com/JonasRSV/DQNTensorflow"},{"title":"ssainz/reinforcement_learning_algorithms","url":"https://github.com/ssainz/reinforcement_learning_algorithms"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"tkcoding/DeepRL","url":"https://github.com/tkcoding/DeepRL"},{"title":"JonasRSV/DQN","url":"https://github.com/JonasRSV/DQN"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58059,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"NoisyNet-Dueling","metrics":{"Score":"1896"},"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":58060,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"IMPALA (deep)","metrics":{"Score":"1852.70"},"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":58061,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"C51 noop","metrics":{"Score":"1645.0"},"paper_url":"http://arxiv.org/abs/1707.06887v1","paper_title":"A Distributional Perspective on Reinforcement Learning","paper_date":"2017-07-21","code_links":[{"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/c51.py"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"Stable-Baselines-Team/stable-baselines3-contrib","url":"https://github.com/Stable-Baselines-Team/stable-baselines3-contrib"},{"title":"Kchu/DeepRL_CK","url":"https://github.com/Kchu/DeepRL_CK"},{"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":"marload/dist-rl-tf2","url":"https://github.com/marload/dist-rl-tf2"},{"title":"marload/DistRL-TensorFlow2","url":"https://github.com/marload/DistRL-TensorFlow2"},{"title":"kochlisGit/autonomous-vehicles-agent","url":"https://github.com/kochlisGit/autonomous-vehicles-agent"},{"title":"qgallouedec/deep_rl","url":"https://github.com/qgallouedec/deep_rl"},{"title":"Abdelhamid-bouzid/Distributional-RL","url":"https://github.com/Abdelhamid-bouzid/Distributional-RL"},{"title":"pihey1995/DistributionalRL","url":"https://github.com/pihey1995/DistributionalRL"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment"},{"title":"parilo/gym_bipedal_walker_v2_solution","url":"https://github.com/parilo/gym_bipedal_walker_v2_solution"},{"title":"eric-yim/fin_map","url":"https://github.com/eric-yim/fin_map"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"shuli0808/DQN","url":"https://github.com/shuli0808/DQN"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58062,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"Duel noop","metrics":{"Score":"1472.6"},"paper_url":"http://arxiv.org/abs/1511.06581v3","paper_title":"Dueling Network Architectures for Deep Reinforcement Learning","paper_date":"2015-11-20","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"facebookresearch/Horizon","url":"https://github.com/facebookresearch/Horizon"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"ku2482/sac-discrete.pytorch","url":"https://github.com/ku2482/sac-discrete.pytorch"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"BY571/DQN-Atari-Agents","url":"https://github.com/BY571/DQN-Atari-Agents"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"JuliaPOMDP/DeepQLearning.jl","url":"https://github.com/JuliaPOMDP/DeepQLearning.jl"},{"title":"gouxiangchen/dueling-DQN-pytorch","url":"https://github.com/gouxiangchen/dueling-DQN-pytorch"},{"title":"R-Sweke/DeepQ-Decoding","url":"https://github.com/R-Sweke/DeepQ-Decoding"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"ethanmclark1/carla_aebs","url":"https://github.com/ethanmclark1/carla_aebs"},{"title":"clarky104/carla_aebs","url":"https://github.com/clarky104/carla_aebs"},{"title":"KDL-umass/saliency_maps","url":"https://github.com/KDL-umass/saliency_maps"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"alessandrositta/Flatland_challenge","url":"https://github.com/alessandrositta/Flatland_challenge"},{"title":"MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"nathanin/pad","url":"https://github.com/nathanin/pad"},{"title":"zynk13/dueling-dqn-Reinforcement-learning","url":"https://github.com/zynk13/dueling-dqn-Reinforcement-learning"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"prajwalgatti/DRL-Continuous-Control","url":"https://github.com/prajwalgatti/DRL-Continuous-Control"},{"title":"la3lma/chezjulia","url":"https://github.com/la3lma/chezjulia"},{"title":"la3lma/Chez","url":"https://github.com/la3lma/Chez"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"prajwalgatti/DRL-Navigation","url":"https://github.com/prajwalgatti/DRL-Navigation"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning","url":"https://github.com/manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"iDataist/Navigation-with-Deep-Q-Network","url":"https://github.com/iDataist/Navigation-with-Deep-Q-Network"},{"title":"jsztompka/DuelDQN","url":"https://github.com/jsztompka/DuelDQN"},{"title":"170928/-Review-Dueling-Deep-Q-Network","url":"https://github.com/170928/-Review-Dueling-Deep-Q-Network"},{"title":"Brandon-Rozek/DeepRL","url":"https://github.com/Brandon-Rozek/DeepRL"},{"title":"abryeemessi/Wednesday","url":"https://github.com/abryeemessi/Wednesday"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"JBGUIMBAUD/deep-reenforcement-learning","url":"https://github.com/JBGUIMBAUD/deep-reenforcement-learning"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"opplieam/Pong-Deep-RL","url":"https://github.com/opplieam/Pong-Deep-RL"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58063,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"A3C FF (1 day) hs","metrics":{"Score":"1433.4"},"paper_url":"http://arxiv.org/abs/1602.01783v2","paper_title":"Asynchronous Methods for Deep Reinforcement Learning","paper_date":"2016-02-04","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"DLR-RM/stable-baselines3","url":"https://github.com/DLR-RM/stable-baselines3"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/A3C-Gym"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"pytorch/rl","url":"https://github.com/pytorch/rl/tree/main/examples/a2c"},{"title":"ikostrikov/pytorch-a3c","url":"https://github.com/ikostrikov/pytorch-a3c"},{"title":"Khrylx/PyTorch-RL","url":"https://github.com/Khrylx/PyTorch-RL"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"openai/universe-starter-agent","url":"https://github.com/openai/universe-starter-agent"},{"title":"uvipen/Super-mario-bros-A3C-pytorch","url":"https://github.com/uvipen/Super-mario-bros-A3C-pytorch"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"dickreuter/neuron_poker","url":"https://github.com/dickreuter/neuron_poker"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"marload/deep-rl-tf2","url":"https://github.com/marload/deep-rl-tf2"},{"title":"miyosuda/async_deep_reinforce","url":"https://github.com/miyosuda/async_deep_reinforce"},{"title":"yukezhu/tensorflow-reinforce","url":"https://github.com/yukezhu/tensorflow-reinforce"},{"title":"muupan/async-rl","url":"https://github.com/muupan/async-rl"},{"title":"bentrevett/pytorch-rl","url":"https://github.com/bentrevett/pytorch-rl"},{"title":"Kaixhin/ACER","url":"https://github.com/Kaixhin/ACER"},{"title":"lcswillems/torch-ac","url":"https://github.com/lcswillems/torch-ac"},{"title":"Nasdin/ReinforcementLearning-AtariGame","url":"https://github.com/Nasdin/ReinforcementLearning-AtariGame"},{"title":"Kaixhin/NoisyNet-A3C","url":"https://github.com/Kaixhin/NoisyNet-A3C"},{"title":"khanhptnk/bandit-nmt","url":"https://github.com/khanhptnk/bandit-nmt"},{"title":"arnomoonens/yarll","url":"https://github.com/arnomoonens/yarll"},{"title":"traai/async-deep-rl","url":"https://github.com/traai/async-deep-rl"},{"title":"deepsense-ai/Distributed-BA3C","url":"https://github.com/deepsense-ai/Distributed-BA3C"},{"title":"ikostrikov/pytorch-rl","url":"https://github.com/ikostrikov/pytorch-rl"},{"title":"nvlabs/gbrl_sb3","url":"https://github.com/nvlabs/gbrl_sb3"},{"title":"ShibiHe/Q-Optimality-Tightening","url":"https://github.com/ShibiHe/Q-Optimality-Tightening"},{"title":"qihongl/dlstm-demo","url":"https://github.com/qihongl/dlstm-demo"},{"title":"MatheusMRFM/A3C-LSTM-with-Tensorflow","url":"https://github.com/MatheusMRFM/A3C-LSTM-with-Tensorflow"},{"title":"roop-pal/Meta-Learning-for-StarCraft-II-Minigames","url":"https://github.com/roop-pal/Meta-Learning-for-StarCraft-II-Minigames"},{"title":"4rChon/NL-FuN","url":"https://github.com/4rChon/NL-FuN"},{"title":"braemt/attentive-multi-task-deep-reinforcement-learning","url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning"},{"title":"Sheepsody/Batched-Impala-PyTorch","url":"https://github.com/Sheepsody/Batched-Impala-PyTorch"},{"title":"avillemin/Minecraft-AI","url":"https://github.com/avillemin/Minecraft-AI"},{"title":"bkhmsi/meta-rl-harlow","url":"https://github.com/bkhmsi/meta-rl-harlow"},{"title":"mavischer/DRRL","url":"https://github.com/mavischer/DRRL"},{"title":"grananqvist/reinforcement-learning-super-mario-A3C","url":"https://github.com/grananqvist/reinforcement-learning-super-mario-A3C"},{"title":"brett-daley/fast-dqn","url":"https://github.com/brett-daley/fast-dqn"},{"title":"vladfi1/universe-starter-agent","url":"https://github.com/vladfi1/universe-starter-agent"},{"title":"qihongl/demo-advantage-actor-critic","url":"https://github.com/qihongl/demo-advantage-actor-critic"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"dsinghnegi/atari_RL_agent","url":"https://github.com/dsinghnegi/atari_RL_agent"},{"title":"Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment"},{"title":"gungui98/deeprl-a3c-ai2thor","url":"https://github.com/gungui98/deeprl-a3c-ai2thor"},{"title":"amanda-lambda/hack-flappy-bird-drl","url":"https://github.com/amanda-lambda/hack-flappy-bird-drl"},{"title":"amanda-lambda/drl-experiments","url":"https://github.com/amanda-lambda/drl-experiments"},{"title":"Zartris/TD3_continuous_control","url":"https://github.com/Zartris/TD3_continuous_control"},{"title":"liuyuezhang/pyrl","url":"https://github.com/liuyuezhang/pyrl"},{"title":"InSpaceAI/RL-Zoo","url":"https://github.com/InSpaceAI/RL-Zoo"},{"title":"N0r9st/a2c-jax","url":"https://github.com/N0r9st/a2c-jax"},{"title":"amaudruz/RL_openaigym","url":"https://github.com/amaudruz/RL_openaigym"},{"title":"cdesilv1/sc2_ai_cdes","url":"https://github.com/cdesilv1/sc2_ai_cdes"},{"title":"wxj77/TransferReinforcementLearning","url":"https://github.com/wxj77/TransferReinforcementLearning"},{"title":"joshiatul/game_playing","url":"https://github.com/joshiatul/game_playing"},{"title":"sainijagjit/A3C-Pytorch","url":"https://github.com/sainijagjit/A3C-Pytorch"},{"title":"alexmlamb/blocks_rl_gru_setup","url":"https://github.com/alexmlamb/blocks_rl_gru_setup"},{"title":"PaulCharnay/Projet_AIF","url":"https://github.com/PaulCharnay/Projet_AIF"},{"title":"sharan-dce/A3C","url":"https://github.com/sharan-dce/A3C"},{"title":"danielpolimac/Ispit_Inteligentni_Agenti","url":"https://github.com/danielpolimac/Ispit_Inteligentni_Agenti"},{"title":"AI-RG/rl-experiments","url":"https://github.com/AI-RG/rl-experiments"},{"title":"natsumeS/analysis","url":"https://github.com/natsumeS/analysis"},{"title":"aabbeell/reinforcementLearning.a2c.gym","url":"https://github.com/aabbeell/reinforcementLearning.a2c.gym"},{"title":"Jzar/Space-Invaders-DQN","url":"https://github.com/Jzar/Space-Invaders-DQN"},{"title":"JulT1/RL_SS19","url":"https://github.com/JulT1/RL_SS19"},{"title":"ofekluis/sonic_project_ss19","url":"https://github.com/ofekluis/sonic_project_ss19"},{"title":"hulanwin/A3C-DRL","url":"https://github.com/hulanwin/A3C-DRL"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58064,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"Persistent AL","metrics":{"Score":"1328.25"},"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":58065,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"Prior noop","metrics":{"Score":"1305.6"},"paper_url":"http://arxiv.org/abs/1511.05952v4","paper_title":"Prioritized Experience Replay","paper_date":"2015-11-18","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"ku2482/sac-discrete.pytorch","url":"https://github.com/ku2482/sac-discrete.pytorch"},{"title":"instadeepai/flashbax","url":"https://github.com/instadeepai/flashbax"},{"title":"SimonRamstedt/ddpg","url":"https://github.com/SimonRamstedt/ddpg"},{"title":"Damcy/prioritized-experience-replay","url":"https://github.com/Damcy/prioritized-experience-replay"},{"title":"backgom2357/Recommender_system_via_deep_RL","url":"https://github.com/backgom2357/Recommender_system_via_deep_RL"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"toshikwa/soft-actor-critic.pytorch","url":"https://github.com/toshikwa/soft-actor-critic.pytorch"},{"title":"ku2482/soft-actor-critic.pytorch","url":"https://github.com/ku2482/soft-actor-critic.pytorch"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"Howuhh/prioritized_experience_replay","url":"https://github.com/Howuhh/prioritized_experience_replay"},{"title":"JuliaPOMDP/DeepQLearning.jl","url":"https://github.com/JuliaPOMDP/DeepQLearning.jl"},{"title":"dtak/hip-mdp-public","url":"https://github.com/dtak/hip-mdp-public"},{"title":"xinjinghao/sparrow-v1","url":"https://github.com/xinjinghao/sparrow-v1"},{"title":"atavakol/action-hypergraph-networks","url":"https://github.com/atavakol/action-hypergraph-networks"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"Guillaume-Cr/lunar_lander_per","url":"https://github.com/Guillaume-Cr/lunar_lander_per"},{"title":"kayuksel/pytorch-ars","url":"https://github.com/kayuksel/pytorch-ars"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"Suryavf/SelfDrivingCar","url":"https://github.com/Suryavf/SelfDrivingCar"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"Arrabonae/openai_DDDQN","url":"https://github.com/Arrabonae/openai_DDDQN"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"MathPhysSim/PER-NAF","url":"https://github.com/MathPhysSim/PER-NAF"},{"title":"KAIST-AILab/deeprl_practice_colab","url":"https://github.com/KAIST-AILab/deeprl_practice_colab"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"VictorZuanazzi/Project_RL","url":"https://github.com/VictorZuanazzi/Project_RL"},{"title":"Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"yzheng51/rl-dino-run","url":"https://github.com/yzheng51/rl-dino-run"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"emiled16/Beyond_prioritized_experience_replay","url":"https://github.com/emiled16/Beyond_prioritized_experience_replay"},{"title":"7starsea/Prioritized-Experience-Replay","url":"https://github.com/7starsea/Prioritized-Experience-Replay"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"justinmaojones/starr","url":"https://github.com/justinmaojones/starr"},{"title":"CharlotteMorrison/Baxter-VREP","url":"https://github.com/CharlotteMorrison/Baxter-VREP"},{"title":"iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient","url":"https://github.com/iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"iDataist/Tennis-With-Multi-Agent-Reinforcement","url":"https://github.com/iDataist/Tennis-With-Multi-Agent-Reinforcement"},{"title":"ACampero/dopamine","url":"https://github.com/ACampero/dopamine"},{"title":"iDataist/Navigation-with-Deep-Q-Network","url":"https://github.com/iDataist/Navigation-with-Deep-Q-Network"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"KatyNTsachi/Hierarchical-RL","url":"https://github.com/KatyNTsachi/Hierarchical-RL"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"CharlotteMorrison/Baxter-Research","url":"https://github.com/CharlotteMorrison/Baxter-Research"},{"title":"ameet-1997/Prioritized_Experience_Replay","url":"https://github.com/ameet-1997/Prioritized_Experience_Replay"},{"title":"CSCI4850/S20-team3-project","url":"https://github.com/CSCI4850/S20-team3-project"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"Clement-Hui/Q-Learning","url":"https://github.com/Clement-Hui/Q-Learning"},{"title":"tphanson/xupr-drl","url":"https://github.com/tphanson/xupr-drl"},{"title":"snhwang/p3_collab-compet","url":"https://github.com/snhwang/p3_collab-compet"},{"title":"CharlotteMorrison/Baxter-VREP-Version-2","url":"https://github.com/CharlotteMorrison/Baxter-VREP-Version-2"},{"title":"snhwang/p2-continuous-control-SNH","url":"https://github.com/snhwang/p2-continuous-control-SNH"},{"title":"snhwang/p1_navigation_SNH","url":"https://github.com/snhwang/p1_navigation_SNH"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"},{"title":"VasaKiDD/TD3-deep-rl-research","url":"https://github.com/VasaKiDD/TD3-deep-rl-research"},{"title":"V0LsTeR/dopamine_prioritized_buffer","url":"https://github.com/V0LsTeR/dopamine_prioritized_buffer"},{"title":"sunfex/weighted-sac","url":"https://github.com/sunfex/weighted-sac"},{"title":"anhtu293/NeurIPS-2019-Challenge","url":"https://github.com/anhtu293/NeurIPS-2019-Challenge"},{"title":"Brandon-Rozek/DeepRL","url":"https://github.com/Brandon-Rozek/DeepRL"},{"title":"V0LsTeR/DQN_heap","url":"https://github.com/V0LsTeR/DQN_heap"},{"title":"olonok69/Udacity_Banana_Unity","url":"https://github.com/olonok69/Udacity_Banana_Unity"},{"title":"seacevedo/ReinforcementLearningProjects","url":"https://github.com/seacevedo/ReinforcementLearningProjects"},{"title":"MrDaubinet/collaboration-and-competition","url":"https://github.com/MrDaubinet/collaboration-and-competition"},{"title":"yusme/DDPG","url":"https://github.com/yusme/DDPG"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"GoingMyWay/dopamine_reward_decomposition","url":"https://github.com/GoingMyWay/dopamine_reward_decomposition"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58066,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"DDQN (tuned) noop","metrics":{"Score":"1225.4"},"paper_url":"http://arxiv.org/abs/1511.06581v3","paper_title":"Dueling Network Architectures for Deep Reinforcement Learning","paper_date":"2015-11-20","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"facebookresearch/Horizon","url":"https://github.com/facebookresearch/Horizon"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"ku2482/sac-discrete.pytorch","url":"https://github.com/ku2482/sac-discrete.pytorch"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"BY571/DQN-Atari-Agents","url":"https://github.com/BY571/DQN-Atari-Agents"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"JuliaPOMDP/DeepQLearning.jl","url":"https://github.com/JuliaPOMDP/DeepQLearning.jl"},{"title":"gouxiangchen/dueling-DQN-pytorch","url":"https://github.com/gouxiangchen/dueling-DQN-pytorch"},{"title":"R-Sweke/DeepQ-Decoding","url":"https://github.com/R-Sweke/DeepQ-Decoding"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"ethanmclark1/carla_aebs","url":"https://github.com/ethanmclark1/carla_aebs"},{"title":"clarky104/carla_aebs","url":"https://github.com/clarky104/carla_aebs"},{"title":"KDL-umass/saliency_maps","url":"https://github.com/KDL-umass/saliency_maps"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"alessandrositta/Flatland_challenge","url":"https://github.com/alessandrositta/Flatland_challenge"},{"title":"MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"nathanin/pad","url":"https://github.com/nathanin/pad"},{"title":"zynk13/dueling-dqn-Reinforcement-learning","url":"https://github.com/zynk13/dueling-dqn-Reinforcement-learning"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"prajwalgatti/DRL-Continuous-Control","url":"https://github.com/prajwalgatti/DRL-Continuous-Control"},{"title":"la3lma/chezjulia","url":"https://github.com/la3lma/chezjulia"},{"title":"la3lma/Chez","url":"https://github.com/la3lma/Chez"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"prajwalgatti/DRL-Navigation","url":"https://github.com/prajwalgatti/DRL-Navigation"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning","url":"https://github.com/manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"iDataist/Navigation-with-Deep-Q-Network","url":"https://github.com/iDataist/Navigation-with-Deep-Q-Network"},{"title":"jsztompka/DuelDQN","url":"https://github.com/jsztompka/DuelDQN"},{"title":"170928/-Review-Dueling-Deep-Q-Network","url":"https://github.com/170928/-Review-Dueling-Deep-Q-Network"},{"title":"Brandon-Rozek/DeepRL","url":"https://github.com/Brandon-Rozek/DeepRL"},{"title":"abryeemessi/Wednesday","url":"https://github.com/abryeemessi/Wednesday"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"JBGUIMBAUD/deep-reenforcement-learning","url":"https://github.com/JBGUIMBAUD/deep-reenforcement-learning"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"opplieam/Pong-Deep-RL","url":"https://github.com/opplieam/Pong-Deep-RL"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58067,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"DDQN+Pop-Art noop","metrics":{"Score":"1199.6"},"paper_url":"http://arxiv.org/abs/1602.07714v2","paper_title":"Learning values across many orders of magnitude","paper_date":"2016-02-24","code_links":[],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58068,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"CGP","metrics":{"Score":"1138"},"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":58069,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"IQN","metrics":{"Score":"1053"},"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":58070,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"DDQN (tuned) hs","metrics":{"Score":"1011.1"},"paper_url":"http://arxiv.org/abs/1509.06461v3","paper_title":"Deep Reinforcement Learning with Double Q-learning","paper_date":"2015-09-22","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"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":"MaximeVandegar/Papers-in-100-Lines-of-Code","url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Deep_Reinforcement_Learning_with_Double_Q_learning"},{"title":"deepmind/rlax","url":"https://github.com/deepmind/rlax"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"yukezhu/tensorflow-reinforce","url":"https://github.com/yukezhu/tensorflow-reinforce"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"YuansongFeng/MadMario","url":"https://github.com/YuansongFeng/MadMario"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning","url":"https://github.com/jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning"},{"title":"microsoft/med-deadend","url":"https://github.com/microsoft/med-deadend"},{"title":"xtma/simple-pytorch-rl","url":"https://github.com/xtma/simple-pytorch-rl"},{"title":"moduIo/Deep-Q-network","url":"https://github.com/moduIo/Deep-Q-network"},{"title":"Denbergvanthijs/imbDRL","url":"https://github.com/Denbergvanthijs/imbDRL"},{"title":"kochlisGit/autonomous-vehicles-agent","url":"https://github.com/kochlisGit/autonomous-vehicles-agent"},{"title":"matthewsparr/Deep-Zork","url":"https://github.com/matthewsparr/Deep-Zork"},{"title":"hamishs/JAX-RL","url":"https://github.com/hamishs/JAX-RL"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"anh-nn01/Lunar-Lander-Double-Deep-Q-Networks","url":"https://github.com/anh-nn01/Lunar-Lander-Double-Deep-Q-Networks"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"PeterJochem/Double_Deep_QLearning","url":"https://github.com/PeterJochem/Double_Deep_QLearning"},{"title":"PeterJochem/Deep_RL","url":"https://github.com/PeterJochem/Deep_RL"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"pathway/alphaxos","url":"https://github.com/pathway/alphaxos"},{"title":"OscarHuangWind/Preference-Guided-DQN-Atari","url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari"},{"title":"paintception/Deep-Quality-Value-Family-","url":"https://github.com/paintception/Deep-Quality-Value-Family-"},{"title":"paintception/Deep-Quality-Value-Family","url":"https://github.com/paintception/Deep-Quality-Value-Family"},{"title":"KelvinYang0320/deepbots-panda","url":"https://github.com/KelvinYang0320/deepbots-panda"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"tkcoding/Stock_DRL","url":"https://github.com/tkcoding/Stock_DRL"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"yzheng51/rl-dino-run","url":"https://github.com/yzheng51/rl-dino-run"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"amirmirzaei79/CartPole-DQN-And-DDQN","url":"https://github.com/amirmirzaei79/CartPole-DQN-And-DDQN"},{"title":"xgfelicia/Reinforcement-Learning","url":"https://github.com/xgfelicia/Reinforcement-Learning"},{"title":"RandyDeng/gym_connect4","url":"https://github.com/RandyDeng/gym_connect4"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"Rabrg/dqn","url":"https://github.com/Rabrg/dqn"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"molomono/CartPole_Optimized_DDQN","url":"https://github.com/molomono/CartPole_Optimized_DDQN"},{"title":"Roman-Kozachek/TradeBot","url":"https://github.com/Roman-Kozachek/TradeBot"},{"title":"gznyyb/deep_reinforcement_learning_Pong","url":"https://github.com/gznyyb/deep_reinforcement_learning_Pong"},{"title":"lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning","url":"https://github.com/lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning"},{"title":"ifestus/rl","url":"https://github.com/ifestus/rl"},{"title":"wmol4/Pytorch_DDQN_Unity_Navigation","url":"https://github.com/wmol4/Pytorch_DDQN_Unity_Navigation"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"jadag/DDQN_mario","url":"https://github.com/jadag/DDQN_mario"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"jvoynow/DQN-analysis-with-2048","url":"https://github.com/jvoynow/DQN-analysis-with-2048"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"aman-khurana/deep-q-learning","url":"https://github.com/aman-khurana/deep-q-learning"},{"title":"yaxinchen666/dce_pricingRL","url":"https://github.com/yaxinchen666/dce_pricingRL"},{"title":"puppetect/TradingBot-tensorflow","url":"https://github.com/puppetect/TradingBot-tensorflow"},{"title":"ianlimle/ItsMeMario","url":"https://github.com/ianlimle/ItsMeMario"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"NikolausBerl/Udacity_DRLN_Navigation_Project","url":"https://github.com/NikolausBerl/Udacity_DRLN_Navigation_Project"},{"title":"jeffery1236/Atari_DoubleDeepQNetwork","url":"https://github.com/jeffery1236/Atari_DoubleDeepQNetwork"},{"title":"Codernauti/Exploration-of-DQN-in-CartPole-Environment","url":"https://github.com/Codernauti/Exploration-of-DQN-in-CartPole-Environment"},{"title":"JustinStitt/acrobotDDQN","url":"https://github.com/JustinStitt/acrobotDDQN"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"},{"title":"zhengant/dqn_reversi","url":"https://github.com/zhengant/dqn_reversi"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"daviddcho/supermario","url":"https://github.com/daviddcho/supermario"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"seacevedo/ReinforcementLearningProjects","url":"https://github.com/seacevedo/ReinforcementLearningProjects"},{"title":"JonasRSV/DQNTensorflow","url":"https://github.com/JonasRSV/DQNTensorflow"},{"title":"ssainz/reinforcement_learning_algorithms","url":"https://github.com/ssainz/reinforcement_learning_algorithms"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"tkcoding/DeepRL","url":"https://github.com/tkcoding/DeepRL"},{"title":"JonasRSV/DQN","url":"https://github.com/JonasRSV/DQN"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58071,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"Duel hs","metrics":{"Score":"910.6"},"paper_url":"http://arxiv.org/abs/1511.06581v3","paper_title":"Dueling Network Architectures for Deep Reinforcement Learning","paper_date":"2015-11-20","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"facebookresearch/Horizon","url":"https://github.com/facebookresearch/Horizon"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"ku2482/sac-discrete.pytorch","url":"https://github.com/ku2482/sac-discrete.pytorch"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"BY571/DQN-Atari-Agents","url":"https://github.com/BY571/DQN-Atari-Agents"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"JuliaPOMDP/DeepQLearning.jl","url":"https://github.com/JuliaPOMDP/DeepQLearning.jl"},{"title":"gouxiangchen/dueling-DQN-pytorch","url":"https://github.com/gouxiangchen/dueling-DQN-pytorch"},{"title":"R-Sweke/DeepQ-Decoding","url":"https://github.com/R-Sweke/DeepQ-Decoding"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"ethanmclark1/carla_aebs","url":"https://github.com/ethanmclark1/carla_aebs"},{"title":"clarky104/carla_aebs","url":"https://github.com/clarky104/carla_aebs"},{"title":"KDL-umass/saliency_maps","url":"https://github.com/KDL-umass/saliency_maps"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"alessandrositta/Flatland_challenge","url":"https://github.com/alessandrositta/Flatland_challenge"},{"title":"MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"nathanin/pad","url":"https://github.com/nathanin/pad"},{"title":"zynk13/dueling-dqn-Reinforcement-learning","url":"https://github.com/zynk13/dueling-dqn-Reinforcement-learning"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"prajwalgatti/DRL-Continuous-Control","url":"https://github.com/prajwalgatti/DRL-Continuous-Control"},{"title":"la3lma/chezjulia","url":"https://github.com/la3lma/chezjulia"},{"title":"la3lma/Chez","url":"https://github.com/la3lma/Chez"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"prajwalgatti/DRL-Navigation","url":"https://github.com/prajwalgatti/DRL-Navigation"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning","url":"https://github.com/manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"iDataist/Navigation-with-Deep-Q-Network","url":"https://github.com/iDataist/Navigation-with-Deep-Q-Network"},{"title":"jsztompka/DuelDQN","url":"https://github.com/jsztompka/DuelDQN"},{"title":"170928/-Review-Dueling-Deep-Q-Network","url":"https://github.com/170928/-Review-Dueling-Deep-Q-Network"},{"title":"Brandon-Rozek/DeepRL","url":"https://github.com/Brandon-Rozek/DeepRL"},{"title":"abryeemessi/Wednesday","url":"https://github.com/abryeemessi/Wednesday"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"JBGUIMBAUD/deep-reenforcement-learning","url":"https://github.com/JBGUIMBAUD/deep-reenforcement-learning"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"opplieam/Pong-Deep-RL","url":"https://github.com/opplieam/Pong-Deep-RL"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58072,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"Prior hs","metrics":{"Score":"865.9"},"paper_url":"http://arxiv.org/abs/1511.05952v4","paper_title":"Prioritized Experience Replay","paper_date":"2015-11-18","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"ku2482/sac-discrete.pytorch","url":"https://github.com/ku2482/sac-discrete.pytorch"},{"title":"instadeepai/flashbax","url":"https://github.com/instadeepai/flashbax"},{"title":"SimonRamstedt/ddpg","url":"https://github.com/SimonRamstedt/ddpg"},{"title":"Damcy/prioritized-experience-replay","url":"https://github.com/Damcy/prioritized-experience-replay"},{"title":"backgom2357/Recommender_system_via_deep_RL","url":"https://github.com/backgom2357/Recommender_system_via_deep_RL"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"toshikwa/soft-actor-critic.pytorch","url":"https://github.com/toshikwa/soft-actor-critic.pytorch"},{"title":"ku2482/soft-actor-critic.pytorch","url":"https://github.com/ku2482/soft-actor-critic.pytorch"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"Howuhh/prioritized_experience_replay","url":"https://github.com/Howuhh/prioritized_experience_replay"},{"title":"JuliaPOMDP/DeepQLearning.jl","url":"https://github.com/JuliaPOMDP/DeepQLearning.jl"},{"title":"dtak/hip-mdp-public","url":"https://github.com/dtak/hip-mdp-public"},{"title":"xinjinghao/sparrow-v1","url":"https://github.com/xinjinghao/sparrow-v1"},{"title":"atavakol/action-hypergraph-networks","url":"https://github.com/atavakol/action-hypergraph-networks"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"Guillaume-Cr/lunar_lander_per","url":"https://github.com/Guillaume-Cr/lunar_lander_per"},{"title":"kayuksel/pytorch-ars","url":"https://github.com/kayuksel/pytorch-ars"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"Suryavf/SelfDrivingCar","url":"https://github.com/Suryavf/SelfDrivingCar"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"Arrabonae/openai_DDDQN","url":"https://github.com/Arrabonae/openai_DDDQN"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"MathPhysSim/PER-NAF","url":"https://github.com/MathPhysSim/PER-NAF"},{"title":"KAIST-AILab/deeprl_practice_colab","url":"https://github.com/KAIST-AILab/deeprl_practice_colab"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"VictorZuanazzi/Project_RL","url":"https://github.com/VictorZuanazzi/Project_RL"},{"title":"Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"yzheng51/rl-dino-run","url":"https://github.com/yzheng51/rl-dino-run"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"emiled16/Beyond_prioritized_experience_replay","url":"https://github.com/emiled16/Beyond_prioritized_experience_replay"},{"title":"7starsea/Prioritized-Experience-Replay","url":"https://github.com/7starsea/Prioritized-Experience-Replay"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"justinmaojones/starr","url":"https://github.com/justinmaojones/starr"},{"title":"CharlotteMorrison/Baxter-VREP","url":"https://github.com/CharlotteMorrison/Baxter-VREP"},{"title":"iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient","url":"https://github.com/iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"iDataist/Tennis-With-Multi-Agent-Reinforcement","url":"https://github.com/iDataist/Tennis-With-Multi-Agent-Reinforcement"},{"title":"ACampero/dopamine","url":"https://github.com/ACampero/dopamine"},{"title":"iDataist/Navigation-with-Deep-Q-Network","url":"https://github.com/iDataist/Navigation-with-Deep-Q-Network"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"KatyNTsachi/Hierarchical-RL","url":"https://github.com/KatyNTsachi/Hierarchical-RL"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"CharlotteMorrison/Baxter-Research","url":"https://github.com/CharlotteMorrison/Baxter-Research"},{"title":"ameet-1997/Prioritized_Experience_Replay","url":"https://github.com/ameet-1997/Prioritized_Experience_Replay"},{"title":"CSCI4850/S20-team3-project","url":"https://github.com/CSCI4850/S20-team3-project"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"Clement-Hui/Q-Learning","url":"https://github.com/Clement-Hui/Q-Learning"},{"title":"tphanson/xupr-drl","url":"https://github.com/tphanson/xupr-drl"},{"title":"snhwang/p3_collab-compet","url":"https://github.com/snhwang/p3_collab-compet"},{"title":"CharlotteMorrison/Baxter-VREP-Version-2","url":"https://github.com/CharlotteMorrison/Baxter-VREP-Version-2"},{"title":"snhwang/p2-continuous-control-SNH","url":"https://github.com/snhwang/p2-continuous-control-SNH"},{"title":"snhwang/p1_navigation_SNH","url":"https://github.com/snhwang/p1_navigation_SNH"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"},{"title":"VasaKiDD/TD3-deep-rl-research","url":"https://github.com/VasaKiDD/TD3-deep-rl-research"},{"title":"V0LsTeR/dopamine_prioritized_buffer","url":"https://github.com/V0LsTeR/dopamine_prioritized_buffer"},{"title":"sunfex/weighted-sac","url":"https://github.com/sunfex/weighted-sac"},{"title":"anhtu293/NeurIPS-2019-Challenge","url":"https://github.com/anhtu293/NeurIPS-2019-Challenge"},{"title":"Brandon-Rozek/DeepRL","url":"https://github.com/Brandon-Rozek/DeepRL"},{"title":"V0LsTeR/DQN_heap","url":"https://github.com/V0LsTeR/DQN_heap"},{"title":"olonok69/Udacity_Banana_Unity","url":"https://github.com/olonok69/Udacity_Banana_Unity"},{"title":"seacevedo/ReinforcementLearningProjects","url":"https://github.com/seacevedo/ReinforcementLearningProjects"},{"title":"MrDaubinet/collaboration-and-competition","url":"https://github.com/MrDaubinet/collaboration-and-competition"},{"title":"yusme/DDPG","url":"https://github.com/yusme/DDPG"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"GoingMyWay/dopamine_reward_decomposition","url":"https://github.com/GoingMyWay/dopamine_reward_decomposition"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58073,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"A3C LSTM hs","metrics":{"Score":"862.2"},"paper_url":"http://arxiv.org/abs/1602.01783v2","paper_title":"Asynchronous Methods for Deep Reinforcement Learning","paper_date":"2016-02-04","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"DLR-RM/stable-baselines3","url":"https://github.com/DLR-RM/stable-baselines3"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/A3C-Gym"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"pytorch/rl","url":"https://github.com/pytorch/rl/tree/main/examples/a2c"},{"title":"ikostrikov/pytorch-a3c","url":"https://github.com/ikostrikov/pytorch-a3c"},{"title":"Khrylx/PyTorch-RL","url":"https://github.com/Khrylx/PyTorch-RL"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"openai/universe-starter-agent","url":"https://github.com/openai/universe-starter-agent"},{"title":"uvipen/Super-mario-bros-A3C-pytorch","url":"https://github.com/uvipen/Super-mario-bros-A3C-pytorch"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"dickreuter/neuron_poker","url":"https://github.com/dickreuter/neuron_poker"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"marload/deep-rl-tf2","url":"https://github.com/marload/deep-rl-tf2"},{"title":"miyosuda/async_deep_reinforce","url":"https://github.com/miyosuda/async_deep_reinforce"},{"title":"yukezhu/tensorflow-reinforce","url":"https://github.com/yukezhu/tensorflow-reinforce"},{"title":"muupan/async-rl","url":"https://github.com/muupan/async-rl"},{"title":"bentrevett/pytorch-rl","url":"https://github.com/bentrevett/pytorch-rl"},{"title":"Kaixhin/ACER","url":"https://github.com/Kaixhin/ACER"},{"title":"lcswillems/torch-ac","url":"https://github.com/lcswillems/torch-ac"},{"title":"Nasdin/ReinforcementLearning-AtariGame","url":"https://github.com/Nasdin/ReinforcementLearning-AtariGame"},{"title":"Kaixhin/NoisyNet-A3C","url":"https://github.com/Kaixhin/NoisyNet-A3C"},{"title":"khanhptnk/bandit-nmt","url":"https://github.com/khanhptnk/bandit-nmt"},{"title":"arnomoonens/yarll","url":"https://github.com/arnomoonens/yarll"},{"title":"traai/async-deep-rl","url":"https://github.com/traai/async-deep-rl"},{"title":"deepsense-ai/Distributed-BA3C","url":"https://github.com/deepsense-ai/Distributed-BA3C"},{"title":"ikostrikov/pytorch-rl","url":"https://github.com/ikostrikov/pytorch-rl"},{"title":"nvlabs/gbrl_sb3","url":"https://github.com/nvlabs/gbrl_sb3"},{"title":"ShibiHe/Q-Optimality-Tightening","url":"https://github.com/ShibiHe/Q-Optimality-Tightening"},{"title":"qihongl/dlstm-demo","url":"https://github.com/qihongl/dlstm-demo"},{"title":"MatheusMRFM/A3C-LSTM-with-Tensorflow","url":"https://github.com/MatheusMRFM/A3C-LSTM-with-Tensorflow"},{"title":"roop-pal/Meta-Learning-for-StarCraft-II-Minigames","url":"https://github.com/roop-pal/Meta-Learning-for-StarCraft-II-Minigames"},{"title":"4rChon/NL-FuN","url":"https://github.com/4rChon/NL-FuN"},{"title":"braemt/attentive-multi-task-deep-reinforcement-learning","url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning"},{"title":"Sheepsody/Batched-Impala-PyTorch","url":"https://github.com/Sheepsody/Batched-Impala-PyTorch"},{"title":"avillemin/Minecraft-AI","url":"https://github.com/avillemin/Minecraft-AI"},{"title":"bkhmsi/meta-rl-harlow","url":"https://github.com/bkhmsi/meta-rl-harlow"},{"title":"mavischer/DRRL","url":"https://github.com/mavischer/DRRL"},{"title":"grananqvist/reinforcement-learning-super-mario-A3C","url":"https://github.com/grananqvist/reinforcement-learning-super-mario-A3C"},{"title":"brett-daley/fast-dqn","url":"https://github.com/brett-daley/fast-dqn"},{"title":"vladfi1/universe-starter-agent","url":"https://github.com/vladfi1/universe-starter-agent"},{"title":"qihongl/demo-advantage-actor-critic","url":"https://github.com/qihongl/demo-advantage-actor-critic"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"dsinghnegi/atari_RL_agent","url":"https://github.com/dsinghnegi/atari_RL_agent"},{"title":"Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment"},{"title":"gungui98/deeprl-a3c-ai2thor","url":"https://github.com/gungui98/deeprl-a3c-ai2thor"},{"title":"amanda-lambda/hack-flappy-bird-drl","url":"https://github.com/amanda-lambda/hack-flappy-bird-drl"},{"title":"amanda-lambda/drl-experiments","url":"https://github.com/amanda-lambda/drl-experiments"},{"title":"Zartris/TD3_continuous_control","url":"https://github.com/Zartris/TD3_continuous_control"},{"title":"liuyuezhang/pyrl","url":"https://github.com/liuyuezhang/pyrl"},{"title":"InSpaceAI/RL-Zoo","url":"https://github.com/InSpaceAI/RL-Zoo"},{"title":"N0r9st/a2c-jax","url":"https://github.com/N0r9st/a2c-jax"},{"title":"amaudruz/RL_openaigym","url":"https://github.com/amaudruz/RL_openaigym"},{"title":"cdesilv1/sc2_ai_cdes","url":"https://github.com/cdesilv1/sc2_ai_cdes"},{"title":"wxj77/TransferReinforcementLearning","url":"https://github.com/wxj77/TransferReinforcementLearning"},{"title":"joshiatul/game_playing","url":"https://github.com/joshiatul/game_playing"},{"title":"sainijagjit/A3C-Pytorch","url":"https://github.com/sainijagjit/A3C-Pytorch"},{"title":"alexmlamb/blocks_rl_gru_setup","url":"https://github.com/alexmlamb/blocks_rl_gru_setup"},{"title":"PaulCharnay/Projet_AIF","url":"https://github.com/PaulCharnay/Projet_AIF"},{"title":"sharan-dce/A3C","url":"https://github.com/sharan-dce/A3C"},{"title":"danielpolimac/Ispit_Inteligentni_Agenti","url":"https://github.com/danielpolimac/Ispit_Inteligentni_Agenti"},{"title":"AI-RG/rl-experiments","url":"https://github.com/AI-RG/rl-experiments"},{"title":"natsumeS/analysis","url":"https://github.com/natsumeS/analysis"},{"title":"aabbeell/reinforcementLearning.a2c.gym","url":"https://github.com/aabbeell/reinforcementLearning.a2c.gym"},{"title":"Jzar/Space-Invaders-DQN","url":"https://github.com/Jzar/Space-Invaders-DQN"},{"title":"JulT1/RL_SS19","url":"https://github.com/JulT1/RL_SS19"},{"title":"ofekluis/sonic_project_ss19","url":"https://github.com/ofekluis/sonic_project_ss19"},{"title":"hulanwin/A3C-DRL","url":"https://github.com/hulanwin/A3C-DRL"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58074,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"A3C FF hs","metrics":{"Score":"817.9"},"paper_url":"http://arxiv.org/abs/1602.01783v2","paper_title":"Asynchronous Methods for Deep Reinforcement Learning","paper_date":"2016-02-04","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"DLR-RM/stable-baselines3","url":"https://github.com/DLR-RM/stable-baselines3"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/A3C-Gym"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"pytorch/rl","url":"https://github.com/pytorch/rl/tree/main/examples/a2c"},{"title":"ikostrikov/pytorch-a3c","url":"https://github.com/ikostrikov/pytorch-a3c"},{"title":"Khrylx/PyTorch-RL","url":"https://github.com/Khrylx/PyTorch-RL"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"openai/universe-starter-agent","url":"https://github.com/openai/universe-starter-agent"},{"title":"uvipen/Super-mario-bros-A3C-pytorch","url":"https://github.com/uvipen/Super-mario-bros-A3C-pytorch"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"dickreuter/neuron_poker","url":"https://github.com/dickreuter/neuron_poker"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"marload/deep-rl-tf2","url":"https://github.com/marload/deep-rl-tf2"},{"title":"miyosuda/async_deep_reinforce","url":"https://github.com/miyosuda/async_deep_reinforce"},{"title":"yukezhu/tensorflow-reinforce","url":"https://github.com/yukezhu/tensorflow-reinforce"},{"title":"muupan/async-rl","url":"https://github.com/muupan/async-rl"},{"title":"bentrevett/pytorch-rl","url":"https://github.com/bentrevett/pytorch-rl"},{"title":"Kaixhin/ACER","url":"https://github.com/Kaixhin/ACER"},{"title":"lcswillems/torch-ac","url":"https://github.com/lcswillems/torch-ac"},{"title":"Nasdin/ReinforcementLearning-AtariGame","url":"https://github.com/Nasdin/ReinforcementLearning-AtariGame"},{"title":"Kaixhin/NoisyNet-A3C","url":"https://github.com/Kaixhin/NoisyNet-A3C"},{"title":"khanhptnk/bandit-nmt","url":"https://github.com/khanhptnk/bandit-nmt"},{"title":"arnomoonens/yarll","url":"https://github.com/arnomoonens/yarll"},{"title":"traai/async-deep-rl","url":"https://github.com/traai/async-deep-rl"},{"title":"deepsense-ai/Distributed-BA3C","url":"https://github.com/deepsense-ai/Distributed-BA3C"},{"title":"ikostrikov/pytorch-rl","url":"https://github.com/ikostrikov/pytorch-rl"},{"title":"nvlabs/gbrl_sb3","url":"https://github.com/nvlabs/gbrl_sb3"},{"title":"ShibiHe/Q-Optimality-Tightening","url":"https://github.com/ShibiHe/Q-Optimality-Tightening"},{"title":"qihongl/dlstm-demo","url":"https://github.com/qihongl/dlstm-demo"},{"title":"MatheusMRFM/A3C-LSTM-with-Tensorflow","url":"https://github.com/MatheusMRFM/A3C-LSTM-with-Tensorflow"},{"title":"roop-pal/Meta-Learning-for-StarCraft-II-Minigames","url":"https://github.com/roop-pal/Meta-Learning-for-StarCraft-II-Minigames"},{"title":"4rChon/NL-FuN","url":"https://github.com/4rChon/NL-FuN"},{"title":"braemt/attentive-multi-task-deep-reinforcement-learning","url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning"},{"title":"Sheepsody/Batched-Impala-PyTorch","url":"https://github.com/Sheepsody/Batched-Impala-PyTorch"},{"title":"avillemin/Minecraft-AI","url":"https://github.com/avillemin/Minecraft-AI"},{"title":"bkhmsi/meta-rl-harlow","url":"https://github.com/bkhmsi/meta-rl-harlow"},{"title":"mavischer/DRRL","url":"https://github.com/mavischer/DRRL"},{"title":"grananqvist/reinforcement-learning-super-mario-A3C","url":"https://github.com/grananqvist/reinforcement-learning-super-mario-A3C"},{"title":"brett-daley/fast-dqn","url":"https://github.com/brett-daley/fast-dqn"},{"title":"vladfi1/universe-starter-agent","url":"https://github.com/vladfi1/universe-starter-agent"},{"title":"qihongl/demo-advantage-actor-critic","url":"https://github.com/qihongl/demo-advantage-actor-critic"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"dsinghnegi/atari_RL_agent","url":"https://github.com/dsinghnegi/atari_RL_agent"},{"title":"Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment"},{"title":"gungui98/deeprl-a3c-ai2thor","url":"https://github.com/gungui98/deeprl-a3c-ai2thor"},{"title":"amanda-lambda/hack-flappy-bird-drl","url":"https://github.com/amanda-lambda/hack-flappy-bird-drl"},{"title":"amanda-lambda/drl-experiments","url":"https://github.com/amanda-lambda/drl-experiments"},{"title":"Zartris/TD3_continuous_control","url":"https://github.com/Zartris/TD3_continuous_control"},{"title":"liuyuezhang/pyrl","url":"https://github.com/liuyuezhang/pyrl"},{"title":"InSpaceAI/RL-Zoo","url":"https://github.com/InSpaceAI/RL-Zoo"},{"title":"N0r9st/a2c-jax","url":"https://github.com/N0r9st/a2c-jax"},{"title":"amaudruz/RL_openaigym","url":"https://github.com/amaudruz/RL_openaigym"},{"title":"cdesilv1/sc2_ai_cdes","url":"https://github.com/cdesilv1/sc2_ai_cdes"},{"title":"wxj77/TransferReinforcementLearning","url":"https://github.com/wxj77/TransferReinforcementLearning"},{"title":"joshiatul/game_playing","url":"https://github.com/joshiatul/game_playing"},{"title":"sainijagjit/A3C-Pytorch","url":"https://github.com/sainijagjit/A3C-Pytorch"},{"title":"alexmlamb/blocks_rl_gru_setup","url":"https://github.com/alexmlamb/blocks_rl_gru_setup"},{"title":"PaulCharnay/Projet_AIF","url":"https://github.com/PaulCharnay/Projet_AIF"},{"title":"sharan-dce/A3C","url":"https://github.com/sharan-dce/A3C"},{"title":"danielpolimac/Ispit_Inteligentni_Agenti","url":"https://github.com/danielpolimac/Ispit_Inteligentni_Agenti"},{"title":"AI-RG/rl-experiments","url":"https://github.com/AI-RG/rl-experiments"},{"title":"natsumeS/analysis","url":"https://github.com/natsumeS/analysis"},{"title":"aabbeell/reinforcementLearning.a2c.gym","url":"https://github.com/aabbeell/reinforcementLearning.a2c.gym"},{"title":"Jzar/Space-Invaders-DQN","url":"https://github.com/Jzar/Space-Invaders-DQN"},{"title":"JulT1/RL_SS19","url":"https://github.com/JulT1/RL_SS19"},{"title":"ofekluis/sonic_project_ss19","url":"https://github.com/ofekluis/sonic_project_ss19"},{"title":"hulanwin/A3C-DRL","url":"https://github.com/hulanwin/A3C-DRL"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58075,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"DreamerV2","metrics":{"Score":"810"},"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":58076,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"Advantage Learning","metrics":{"Score":"747.26"},"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":58077,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"ES FF (1 hour) noop","metrics":{"Score":"686.0"},"paper_url":"http://arxiv.org/abs/1703.03864v2","paper_title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","paper_date":"2017-03-10","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"openai/evolution-strategies-starter","url":"https://github.com/openai/evolution-strategies-starter"},{"title":"atgambardella/pytorch-es","url":"https://github.com/atgambardella/pytorch-es"},{"title":"rasmusbergpalm/evostrat","url":"https://github.com/rasmusbergpalm/evostrat"},{"title":"nnaisense/pgpelib","url":"https://github.com/nnaisense/pgpelib"},{"title":"ShangtongZhang/DistributedES","url":"https://github.com/ShangtongZhang/DistributedES"},{"title":"evaboost/evaboost","url":"https://github.com/evaboost/evaboost"},{"title":"enajx/ES","url":"https://github.com/enajx/ES"},{"title":"fiberleif/evolution-strategies","url":"https://github.com/fiberleif/evolution-strategies"},{"title":"neuro-soup/es-torch","url":"https://github.com/neuro-soup/es-torch"},{"title":"stavrosgreece/MultiAgentLearning","url":"https://github.com/stavrosgreece/MultiAgentLearning"},{"title":"FlixCoder/rust-es-optimizer","url":"https://github.com/FlixCoder/rust-es-optimizer"},{"title":"MohammadAsadolahi/Gradient-Free-Reinforcement-Learning-solving-Openai-gym-LunarLanderV2-by-Evolution-Strategy-python","url":"https://github.com/MohammadAsadolahi/Gradient-Free-Reinforcement-Learning-solving-Openai-gym-LunarLanderV2-by-Evolution-Strategy-python/blob/main/README.md"},{"title":"silvialuu/DRL-2018","url":"https://github.com/silvialuu/DRL-2018"},{"title":"susanwe/ope_worldmodels","url":"https://github.com/susanwe/ope_worldmodels"},{"title":"czen88/qtrader","url":"https://github.com/czen88/qtrader"},{"title":"aspk/space_battle","url":"https://github.com/aspk/space_battle"},{"title":"shakti365/nes","url":"https://github.com/shakti365/nes"},{"title":"cesch97/NeuroEvolution","url":"https://github.com/cesch97/NeuroEvolution"},{"title":"alisidd/Evolution-Strategies","url":"https://github.com/alisidd/Evolution-Strategies"},{"title":"AnshMittal1811/AugmentedRandomSearch","url":"https://github.com/AnshMittal1811/AugmentedRandomSearch"},{"title":"patniemeyer/ga-autoencoder","url":"https://github.com/patniemeyer/ga-autoencoder"},{"title":"neilsgp/RL-Algorithms","url":"https://github.com/neilsgp/RL-Algorithms"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58078,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"Best Baseline","metrics":{"Score":"670"},"paper_url":"http://arxiv.org/abs/1207.4708v2","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","paper_date":"2012-07-19","code_links":[{"title":"mgbellemare/Arcade-Learning-Environment","url":"https://github.com/mgbellemare/Arcade-Learning-Environment"},{"title":"kenjyoung/MinAtar","url":"https://github.com/kenjyoung/MinAtar"},{"title":"nandomp/AICollaboratory","url":"https://github.com/nandomp/AICollaboratory"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58079,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"DQN noop","metrics":{"Score":"585.6"},"paper_url":"http://arxiv.org/abs/1509.06461v3","paper_title":"Deep Reinforcement Learning with Double Q-learning","paper_date":"2015-09-22","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"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":"MaximeVandegar/Papers-in-100-Lines-of-Code","url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Deep_Reinforcement_Learning_with_Double_Q_learning"},{"title":"deepmind/rlax","url":"https://github.com/deepmind/rlax"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"yukezhu/tensorflow-reinforce","url":"https://github.com/yukezhu/tensorflow-reinforce"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"YuansongFeng/MadMario","url":"https://github.com/YuansongFeng/MadMario"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning","url":"https://github.com/jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning"},{"title":"microsoft/med-deadend","url":"https://github.com/microsoft/med-deadend"},{"title":"xtma/simple-pytorch-rl","url":"https://github.com/xtma/simple-pytorch-rl"},{"title":"moduIo/Deep-Q-network","url":"https://github.com/moduIo/Deep-Q-network"},{"title":"Denbergvanthijs/imbDRL","url":"https://github.com/Denbergvanthijs/imbDRL"},{"title":"kochlisGit/autonomous-vehicles-agent","url":"https://github.com/kochlisGit/autonomous-vehicles-agent"},{"title":"matthewsparr/Deep-Zork","url":"https://github.com/matthewsparr/Deep-Zork"},{"title":"hamishs/JAX-RL","url":"https://github.com/hamishs/JAX-RL"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"anh-nn01/Lunar-Lander-Double-Deep-Q-Networks","url":"https://github.com/anh-nn01/Lunar-Lander-Double-Deep-Q-Networks"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"PeterJochem/Double_Deep_QLearning","url":"https://github.com/PeterJochem/Double_Deep_QLearning"},{"title":"PeterJochem/Deep_RL","url":"https://github.com/PeterJochem/Deep_RL"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"pathway/alphaxos","url":"https://github.com/pathway/alphaxos"},{"title":"OscarHuangWind/Preference-Guided-DQN-Atari","url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari"},{"title":"paintception/Deep-Quality-Value-Family-","url":"https://github.com/paintception/Deep-Quality-Value-Family-"},{"title":"paintception/Deep-Quality-Value-Family","url":"https://github.com/paintception/Deep-Quality-Value-Family"},{"title":"KelvinYang0320/deepbots-panda","url":"https://github.com/KelvinYang0320/deepbots-panda"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"tkcoding/Stock_DRL","url":"https://github.com/tkcoding/Stock_DRL"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"yzheng51/rl-dino-run","url":"https://github.com/yzheng51/rl-dino-run"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"amirmirzaei79/CartPole-DQN-And-DDQN","url":"https://github.com/amirmirzaei79/CartPole-DQN-And-DDQN"},{"title":"xgfelicia/Reinforcement-Learning","url":"https://github.com/xgfelicia/Reinforcement-Learning"},{"title":"RandyDeng/gym_connect4","url":"https://github.com/RandyDeng/gym_connect4"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"Rabrg/dqn","url":"https://github.com/Rabrg/dqn"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"molomono/CartPole_Optimized_DDQN","url":"https://github.com/molomono/CartPole_Optimized_DDQN"},{"title":"Roman-Kozachek/TradeBot","url":"https://github.com/Roman-Kozachek/TradeBot"},{"title":"gznyyb/deep_reinforcement_learning_Pong","url":"https://github.com/gznyyb/deep_reinforcement_learning_Pong"},{"title":"lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning","url":"https://github.com/lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning"},{"title":"ifestus/rl","url":"https://github.com/ifestus/rl"},{"title":"wmol4/Pytorch_DDQN_Unity_Navigation","url":"https://github.com/wmol4/Pytorch_DDQN_Unity_Navigation"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"jadag/DDQN_mario","url":"https://github.com/jadag/DDQN_mario"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"jvoynow/DQN-analysis-with-2048","url":"https://github.com/jvoynow/DQN-analysis-with-2048"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"aman-khurana/deep-q-learning","url":"https://github.com/aman-khurana/deep-q-learning"},{"title":"yaxinchen666/dce_pricingRL","url":"https://github.com/yaxinchen666/dce_pricingRL"},{"title":"puppetect/TradingBot-tensorflow","url":"https://github.com/puppetect/TradingBot-tensorflow"},{"title":"ianlimle/ItsMeMario","url":"https://github.com/ianlimle/ItsMeMario"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"NikolausBerl/Udacity_DRLN_Navigation_Project","url":"https://github.com/NikolausBerl/Udacity_DRLN_Navigation_Project"},{"title":"jeffery1236/Atari_DoubleDeepQNetwork","url":"https://github.com/jeffery1236/Atari_DoubleDeepQNetwork"},{"title":"Codernauti/Exploration-of-DQN-in-CartPole-Environment","url":"https://github.com/Codernauti/Exploration-of-DQN-in-CartPole-Environment"},{"title":"JustinStitt/acrobotDDQN","url":"https://github.com/JustinStitt/acrobotDDQN"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"},{"title":"zhengant/dqn_reversi","url":"https://github.com/zhengant/dqn_reversi"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"daviddcho/supermario","url":"https://github.com/daviddcho/supermario"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"seacevedo/ReinforcementLearningProjects","url":"https://github.com/seacevedo/ReinforcementLearningProjects"},{"title":"JonasRSV/DQNTensorflow","url":"https://github.com/JonasRSV/DQNTensorflow"},{"title":"ssainz/reinforcement_learning_algorithms","url":"https://github.com/ssainz/reinforcement_learning_algorithms"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"tkcoding/DeepRL","url":"https://github.com/tkcoding/DeepRL"},{"title":"JonasRSV/DQN","url":"https://github.com/JonasRSV/DQN"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58080,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"Best Learner","metrics":{"Score":"501.3"},"paper_url":"http://arxiv.org/abs/1207.4708v2","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","paper_date":"2012-07-19","code_links":[{"title":"mgbellemare/Arcade-Learning-Environment","url":"https://github.com/mgbellemare/Arcade-Learning-Environment"},{"title":"kenjyoung/MinAtar","url":"https://github.com/kenjyoung/MinAtar"},{"title":"nandomp/AICollaboratory","url":"https://github.com/nandomp/AICollaboratory"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":58081,"task":"Atari Games","parent_task":null,"dataset":"Atari 2600 Berzerk","model_name":"DQN hs","metrics":{"Score":"493.4"},"paper_url":"http://arxiv.org/abs/1509.06461v3","paper_title":"Deep Reinforcement Learning with Double Q-learning","paper_date":"2015-09-22","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"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":"MaximeVandegar/Papers-in-100-Lines-of-Code","url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Deep_Reinforcement_Learning_with_Double_Q_learning"},{"title":"deepmind/rlax","url":"https://github.com/deepmind/rlax"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"yukezhu/tensorflow-reinforce","url":"https://github.com/yukezhu/tensorflow-reinforce"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"YuansongFeng/MadMario","url":"https://github.com/YuansongFeng/MadMario"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning","url":"https://github.com/jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning"},{"title":"microsoft/med-deadend","url":"https://github.com/microsoft/med-deadend"},{"title":"xtma/simple-pytorch-rl","url":"https://github.com/xtma/simple-pytorch-rl"},{"title":"moduIo/Deep-Q-network","url":"https://github.com/moduIo/Deep-Q-network"},{"title":"Denbergvanthijs/imbDRL","url":"https://github.com/Denbergvanthijs/imbDRL"},{"title":"kochlisGit/autonomous-vehicles-agent","url":"https://github.com/kochlisGit/autonomous-vehicles-agent"},{"title":"matthewsparr/Deep-Zork","url":"https://github.com/matthewsparr/Deep-Zork"},{"title":"hamishs/JAX-RL","url":"https://github.com/hamishs/JAX-RL"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"anh-nn01/Lunar-Lander-Double-Deep-Q-Networks","url":"https://github.com/anh-nn01/Lunar-Lander-Double-Deep-Q-Networks"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"PeterJochem/Double_Deep_QLearning","url":"https://github.com/PeterJochem/Double_Deep_QLearning"},{"title":"PeterJochem/Deep_RL","url":"https://github.com/PeterJochem/Deep_RL"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"pathway/alphaxos","url":"https://github.com/pathway/alphaxos"},{"title":"OscarHuangWind/Preference-Guided-DQN-Atari","url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari"},{"title":"paintception/Deep-Quality-Value-Family-","url":"https://github.com/paintception/Deep-Quality-Value-Family-"},{"title":"paintception/Deep-Quality-Value-Family","url":"https://github.com/paintception/Deep-Quality-Value-Family"},{"title":"KelvinYang0320/deepbots-panda","url":"https://github.com/KelvinYang0320/deepbots-panda"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"tkcoding/Stock_DRL","url":"https://github.com/tkcoding/Stock_DRL"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"yzheng51/rl-dino-run","url":"https://github.com/yzheng51/rl-dino-run"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"amirmirzaei79/CartPole-DQN-And-DDQN","url":"https://github.com/amirmirzaei79/CartPole-DQN-And-DDQN"},{"title":"xgfelicia/Reinforcement-Learning","url":"https://github.com/xgfelicia/Reinforcement-Learning"},{"title":"RandyDeng/gym_connect4","url":"https://github.com/RandyDeng/gym_connect4"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"Rabrg/dqn","url":"https://github.com/Rabrg/dqn"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"molomono/CartPole_Optimized_DDQN","url":"https://github.com/molomono/CartPole_Optimized_DDQN"},{"title":"Roman-Kozachek/TradeBot","url":"https://github.com/Roman-Kozachek/TradeBot"},{"title":"gznyyb/deep_reinforcement_learning_Pong","url":"https://github.com/gznyyb/deep_reinforcement_learning_Pong"},{"title":"lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning","url":"https://github.com/lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning"},{"title":"ifestus/rl","url":"https://github.com/ifestus/rl"},{"title":"wmol4/Pytorch_DDQN_Unity_Navigation","url":"https://github.com/wmol4/Pytorch_DDQN_Unity_Navigation"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"jadag/DDQN_mario","url":"https://github.com/jadag/DDQN_mario"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"jvoynow/DQN-analysis-with-2048","url":"https://github.com/jvoynow/DQN-analysis-with-2048"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"aman-khurana/deep-q-learning","url":"https://github.com/aman-khurana/deep-q-learning"},{"title":"yaxinchen666/dce_pricingRL","url":"https://github.com/yaxinchen666/dce_pricingRL"},{"title":"puppetect/TradingBot-tensorflow","url":"https://github.com/puppetect/TradingBot-tensorflow"},{"title":"ianlimle/ItsMeMario","url":"https://github.com/ianlimle/ItsMeMario"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"NikolausBerl/Udacity_DRLN_Navigation_Project","url":"https://github.com/NikolausBerl/Udacity_DRLN_Navigation_Project"},{"title":"jeffery1236/Atari_DoubleDeepQNetwork","url":"https://github.com/jeffery1236/Atari_DoubleDeepQNetwork"},{"title":"Codernauti/Exploration-of-DQN-in-CartPole-Environment","url":"https://github.com/Codernauti/Exploration-of-DQN-in-CartPole-Environment"},{"title":"JustinStitt/acrobotDDQN","url":"https://github.com/JustinStitt/acrobotDDQN"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"},{"title":"zhengant/dqn_reversi","url":"https://github.com/zhengant/dqn_reversi"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"daviddcho/supermario","url":"https://github.com/daviddcho/supermario"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"seacevedo/ReinforcementLearningProjects","url":"https://github.com/seacevedo/ReinforcementLearningProjects"},{"title":"JonasRSV/DQNTensorflow","url":"https://github.com/JonasRSV/DQNTensorflow"},{"title":"ssainz/reinforcement_learning_algorithms","url":"https://github.com/ssainz/reinforcement_learning_algorithms"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"tkcoding/DeepRL","url":"https://github.com/tkcoding/DeepRL"},{"title":"JonasRSV/DQN","url":"https://github.com/JonasRSV/DQN"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60570,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"Go-Explore","metrics":{"Score":"197376"},"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":60571,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"MuZero","metrics":{"Score":"85932.60"},"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":60572,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"Agent57","metrics":{"Score":"61507.83"},"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":60573,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"Ape-X","metrics":{"Score":"57196.7"},"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":60574,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"R2D2","metrics":{"Score":"53318.7"},"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":60575,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"DNA","metrics":{"Score":"19789"},"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":60576,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"GDI-H3","metrics":{"Score":"14649"},"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":60577,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"FQF","metrics":{"Score":"12422.2"},"paper_url":"https://arxiv.org/abs/1911.02140v3","paper_title":"Fully Parameterized Quantile Function for Distributional Reinforcement Learning","paper_date":"2019-11-05","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"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":"microsoft/FQF","url":"https://github.com/microsoft/FQF"},{"title":"BY571/FQF-and-Extensions","url":"https://github.com/BY571/FQF-and-Extensions"},{"title":"robinzixuan/IQN_Agent","url":"https://github.com/robinzixuan/IQN_Agent"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60578,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"GDI-I3","metrics":{"Score":"7607"},"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":60579,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"GDI-I3","metrics":{"Score":"7607"},"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":60580,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"Prior+Duel noop","metrics":{"Score":"3409.0"},"paper_url":"http://arxiv.org/abs/1511.06581v3","paper_title":"Dueling Network Architectures for Deep Reinforcement Learning","paper_date":"2015-11-20","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"facebookresearch/Horizon","url":"https://github.com/facebookresearch/Horizon"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"ku2482/sac-discrete.pytorch","url":"https://github.com/ku2482/sac-discrete.pytorch"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"BY571/DQN-Atari-Agents","url":"https://github.com/BY571/DQN-Atari-Agents"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"JuliaPOMDP/DeepQLearning.jl","url":"https://github.com/JuliaPOMDP/DeepQLearning.jl"},{"title":"gouxiangchen/dueling-DQN-pytorch","url":"https://github.com/gouxiangchen/dueling-DQN-pytorch"},{"title":"R-Sweke/DeepQ-Decoding","url":"https://github.com/R-Sweke/DeepQ-Decoding"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"ethanmclark1/carla_aebs","url":"https://github.com/ethanmclark1/carla_aebs"},{"title":"clarky104/carla_aebs","url":"https://github.com/clarky104/carla_aebs"},{"title":"KDL-umass/saliency_maps","url":"https://github.com/KDL-umass/saliency_maps"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"alessandrositta/Flatland_challenge","url":"https://github.com/alessandrositta/Flatland_challenge"},{"title":"MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"nathanin/pad","url":"https://github.com/nathanin/pad"},{"title":"zynk13/dueling-dqn-Reinforcement-learning","url":"https://github.com/zynk13/dueling-dqn-Reinforcement-learning"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"prajwalgatti/DRL-Continuous-Control","url":"https://github.com/prajwalgatti/DRL-Continuous-Control"},{"title":"la3lma/chezjulia","url":"https://github.com/la3lma/chezjulia"},{"title":"la3lma/Chez","url":"https://github.com/la3lma/Chez"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"prajwalgatti/DRL-Navigation","url":"https://github.com/prajwalgatti/DRL-Navigation"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning","url":"https://github.com/manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"iDataist/Navigation-with-Deep-Q-Network","url":"https://github.com/iDataist/Navigation-with-Deep-Q-Network"},{"title":"jsztompka/DuelDQN","url":"https://github.com/jsztompka/DuelDQN"},{"title":"170928/-Review-Dueling-Deep-Q-Network","url":"https://github.com/170928/-Review-Dueling-Deep-Q-Network"},{"title":"Brandon-Rozek/DeepRL","url":"https://github.com/Brandon-Rozek/DeepRL"},{"title":"abryeemessi/Wednesday","url":"https://github.com/abryeemessi/Wednesday"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"JBGUIMBAUD/deep-reenforcement-learning","url":"https://github.com/JBGUIMBAUD/deep-reenforcement-learning"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"opplieam/Pong-Deep-RL","url":"https://github.com/opplieam/Pong-Deep-RL"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60581,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"QR-DQN-1","metrics":{"Score":"3117"},"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":60582,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"MuZero (Res2 Adam)","metrics":{"Score":"2705.82"},"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":60583,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"ASL DDQN","metrics":{"Score":"2597.2"},"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":60584,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"Reactor 500M","metrics":{"Score":"2303.1"},"paper_url":"http://arxiv.org/abs/1704.04651v2","paper_title":"The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning","paper_date":"2017-04-15","code_links":[],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60585,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"Prior+Duel hs","metrics":{"Score":"2178.6"},"paper_url":"http://arxiv.org/abs/1509.06461v3","paper_title":"Deep Reinforcement Learning with Double Q-learning","paper_date":"2015-09-22","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"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":"MaximeVandegar/Papers-in-100-Lines-of-Code","url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Deep_Reinforcement_Learning_with_Double_Q_learning"},{"title":"deepmind/rlax","url":"https://github.com/deepmind/rlax"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"yukezhu/tensorflow-reinforce","url":"https://github.com/yukezhu/tensorflow-reinforce"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"YuansongFeng/MadMario","url":"https://github.com/YuansongFeng/MadMario"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning","url":"https://github.com/jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning"},{"title":"microsoft/med-deadend","url":"https://github.com/microsoft/med-deadend"},{"title":"xtma/simple-pytorch-rl","url":"https://github.com/xtma/simple-pytorch-rl"},{"title":"moduIo/Deep-Q-network","url":"https://github.com/moduIo/Deep-Q-network"},{"title":"Denbergvanthijs/imbDRL","url":"https://github.com/Denbergvanthijs/imbDRL"},{"title":"kochlisGit/autonomous-vehicles-agent","url":"https://github.com/kochlisGit/autonomous-vehicles-agent"},{"title":"matthewsparr/Deep-Zork","url":"https://github.com/matthewsparr/Deep-Zork"},{"title":"hamishs/JAX-RL","url":"https://github.com/hamishs/JAX-RL"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"anh-nn01/Lunar-Lander-Double-Deep-Q-Networks","url":"https://github.com/anh-nn01/Lunar-Lander-Double-Deep-Q-Networks"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"PeterJochem/Double_Deep_QLearning","url":"https://github.com/PeterJochem/Double_Deep_QLearning"},{"title":"PeterJochem/Deep_RL","url":"https://github.com/PeterJochem/Deep_RL"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"pathway/alphaxos","url":"https://github.com/pathway/alphaxos"},{"title":"OscarHuangWind/Preference-Guided-DQN-Atari","url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari"},{"title":"paintception/Deep-Quality-Value-Family-","url":"https://github.com/paintception/Deep-Quality-Value-Family-"},{"title":"paintception/Deep-Quality-Value-Family","url":"https://github.com/paintception/Deep-Quality-Value-Family"},{"title":"KelvinYang0320/deepbots-panda","url":"https://github.com/KelvinYang0320/deepbots-panda"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"tkcoding/Stock_DRL","url":"https://github.com/tkcoding/Stock_DRL"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"yzheng51/rl-dino-run","url":"https://github.com/yzheng51/rl-dino-run"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"amirmirzaei79/CartPole-DQN-And-DDQN","url":"https://github.com/amirmirzaei79/CartPole-DQN-And-DDQN"},{"title":"xgfelicia/Reinforcement-Learning","url":"https://github.com/xgfelicia/Reinforcement-Learning"},{"title":"RandyDeng/gym_connect4","url":"https://github.com/RandyDeng/gym_connect4"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"Rabrg/dqn","url":"https://github.com/Rabrg/dqn"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"molomono/CartPole_Optimized_DDQN","url":"https://github.com/molomono/CartPole_Optimized_DDQN"},{"title":"Roman-Kozachek/TradeBot","url":"https://github.com/Roman-Kozachek/TradeBot"},{"title":"gznyyb/deep_reinforcement_learning_Pong","url":"https://github.com/gznyyb/deep_reinforcement_learning_Pong"},{"title":"lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning","url":"https://github.com/lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning"},{"title":"ifestus/rl","url":"https://github.com/ifestus/rl"},{"title":"wmol4/Pytorch_DDQN_Unity_Navigation","url":"https://github.com/wmol4/Pytorch_DDQN_Unity_Navigation"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"jadag/DDQN_mario","url":"https://github.com/jadag/DDQN_mario"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"jvoynow/DQN-analysis-with-2048","url":"https://github.com/jvoynow/DQN-analysis-with-2048"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"aman-khurana/deep-q-learning","url":"https://github.com/aman-khurana/deep-q-learning"},{"title":"yaxinchen666/dce_pricingRL","url":"https://github.com/yaxinchen666/dce_pricingRL"},{"title":"puppetect/TradingBot-tensorflow","url":"https://github.com/puppetect/TradingBot-tensorflow"},{"title":"ianlimle/ItsMeMario","url":"https://github.com/ianlimle/ItsMeMario"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"NikolausBerl/Udacity_DRLN_Navigation_Project","url":"https://github.com/NikolausBerl/Udacity_DRLN_Navigation_Project"},{"title":"jeffery1236/Atari_DoubleDeepQNetwork","url":"https://github.com/jeffery1236/Atari_DoubleDeepQNetwork"},{"title":"Codernauti/Exploration-of-DQN-in-CartPole-Environment","url":"https://github.com/Codernauti/Exploration-of-DQN-in-CartPole-Environment"},{"title":"JustinStitt/acrobotDDQN","url":"https://github.com/JustinStitt/acrobotDDQN"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"},{"title":"zhengant/dqn_reversi","url":"https://github.com/zhengant/dqn_reversi"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"daviddcho/supermario","url":"https://github.com/daviddcho/supermario"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"seacevedo/ReinforcementLearningProjects","url":"https://github.com/seacevedo/ReinforcementLearningProjects"},{"title":"JonasRSV/DQNTensorflow","url":"https://github.com/JonasRSV/DQNTensorflow"},{"title":"ssainz/reinforcement_learning_algorithms","url":"https://github.com/ssainz/reinforcement_learning_algorithms"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"tkcoding/DeepRL","url":"https://github.com/tkcoding/DeepRL"},{"title":"JonasRSV/DQN","url":"https://github.com/JonasRSV/DQN"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60586,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"NoisyNet-Dueling","metrics":{"Score":"1896"},"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":60587,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"IMPALA (deep)","metrics":{"Score":"1852.70"},"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":60588,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"C51 noop","metrics":{"Score":"1645.0"},"paper_url":"http://arxiv.org/abs/1707.06887v1","paper_title":"A Distributional Perspective on Reinforcement Learning","paper_date":"2017-07-21","code_links":[{"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/c51.py"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"Stable-Baselines-Team/stable-baselines3-contrib","url":"https://github.com/Stable-Baselines-Team/stable-baselines3-contrib"},{"title":"Kchu/DeepRL_CK","url":"https://github.com/Kchu/DeepRL_CK"},{"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":"marload/dist-rl-tf2","url":"https://github.com/marload/dist-rl-tf2"},{"title":"marload/DistRL-TensorFlow2","url":"https://github.com/marload/DistRL-TensorFlow2"},{"title":"kochlisGit/autonomous-vehicles-agent","url":"https://github.com/kochlisGit/autonomous-vehicles-agent"},{"title":"qgallouedec/deep_rl","url":"https://github.com/qgallouedec/deep_rl"},{"title":"Abdelhamid-bouzid/Distributional-RL","url":"https://github.com/Abdelhamid-bouzid/Distributional-RL"},{"title":"pihey1995/DistributionalRL","url":"https://github.com/pihey1995/DistributionalRL"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment"},{"title":"parilo/gym_bipedal_walker_v2_solution","url":"https://github.com/parilo/gym_bipedal_walker_v2_solution"},{"title":"eric-yim/fin_map","url":"https://github.com/eric-yim/fin_map"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"shuli0808/DQN","url":"https://github.com/shuli0808/DQN"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60589,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"Duel noop","metrics":{"Score":"1472.6"},"paper_url":"http://arxiv.org/abs/1511.06581v3","paper_title":"Dueling Network Architectures for Deep Reinforcement Learning","paper_date":"2015-11-20","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"facebookresearch/Horizon","url":"https://github.com/facebookresearch/Horizon"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"ku2482/sac-discrete.pytorch","url":"https://github.com/ku2482/sac-discrete.pytorch"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"BY571/DQN-Atari-Agents","url":"https://github.com/BY571/DQN-Atari-Agents"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"JuliaPOMDP/DeepQLearning.jl","url":"https://github.com/JuliaPOMDP/DeepQLearning.jl"},{"title":"gouxiangchen/dueling-DQN-pytorch","url":"https://github.com/gouxiangchen/dueling-DQN-pytorch"},{"title":"R-Sweke/DeepQ-Decoding","url":"https://github.com/R-Sweke/DeepQ-Decoding"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"ethanmclark1/carla_aebs","url":"https://github.com/ethanmclark1/carla_aebs"},{"title":"clarky104/carla_aebs","url":"https://github.com/clarky104/carla_aebs"},{"title":"KDL-umass/saliency_maps","url":"https://github.com/KDL-umass/saliency_maps"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"alessandrositta/Flatland_challenge","url":"https://github.com/alessandrositta/Flatland_challenge"},{"title":"MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"nathanin/pad","url":"https://github.com/nathanin/pad"},{"title":"zynk13/dueling-dqn-Reinforcement-learning","url":"https://github.com/zynk13/dueling-dqn-Reinforcement-learning"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"prajwalgatti/DRL-Continuous-Control","url":"https://github.com/prajwalgatti/DRL-Continuous-Control"},{"title":"la3lma/chezjulia","url":"https://github.com/la3lma/chezjulia"},{"title":"la3lma/Chez","url":"https://github.com/la3lma/Chez"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"prajwalgatti/DRL-Navigation","url":"https://github.com/prajwalgatti/DRL-Navigation"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning","url":"https://github.com/manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"iDataist/Navigation-with-Deep-Q-Network","url":"https://github.com/iDataist/Navigation-with-Deep-Q-Network"},{"title":"jsztompka/DuelDQN","url":"https://github.com/jsztompka/DuelDQN"},{"title":"170928/-Review-Dueling-Deep-Q-Network","url":"https://github.com/170928/-Review-Dueling-Deep-Q-Network"},{"title":"Brandon-Rozek/DeepRL","url":"https://github.com/Brandon-Rozek/DeepRL"},{"title":"abryeemessi/Wednesday","url":"https://github.com/abryeemessi/Wednesday"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"JBGUIMBAUD/deep-reenforcement-learning","url":"https://github.com/JBGUIMBAUD/deep-reenforcement-learning"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"opplieam/Pong-Deep-RL","url":"https://github.com/opplieam/Pong-Deep-RL"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60590,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"A3C FF (1 day) hs","metrics":{"Score":"1433.4"},"paper_url":"http://arxiv.org/abs/1602.01783v2","paper_title":"Asynchronous Methods for Deep Reinforcement Learning","paper_date":"2016-02-04","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"DLR-RM/stable-baselines3","url":"https://github.com/DLR-RM/stable-baselines3"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/A3C-Gym"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"pytorch/rl","url":"https://github.com/pytorch/rl/tree/main/examples/a2c"},{"title":"ikostrikov/pytorch-a3c","url":"https://github.com/ikostrikov/pytorch-a3c"},{"title":"Khrylx/PyTorch-RL","url":"https://github.com/Khrylx/PyTorch-RL"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"openai/universe-starter-agent","url":"https://github.com/openai/universe-starter-agent"},{"title":"uvipen/Super-mario-bros-A3C-pytorch","url":"https://github.com/uvipen/Super-mario-bros-A3C-pytorch"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"dickreuter/neuron_poker","url":"https://github.com/dickreuter/neuron_poker"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"marload/deep-rl-tf2","url":"https://github.com/marload/deep-rl-tf2"},{"title":"miyosuda/async_deep_reinforce","url":"https://github.com/miyosuda/async_deep_reinforce"},{"title":"yukezhu/tensorflow-reinforce","url":"https://github.com/yukezhu/tensorflow-reinforce"},{"title":"muupan/async-rl","url":"https://github.com/muupan/async-rl"},{"title":"bentrevett/pytorch-rl","url":"https://github.com/bentrevett/pytorch-rl"},{"title":"Kaixhin/ACER","url":"https://github.com/Kaixhin/ACER"},{"title":"lcswillems/torch-ac","url":"https://github.com/lcswillems/torch-ac"},{"title":"Nasdin/ReinforcementLearning-AtariGame","url":"https://github.com/Nasdin/ReinforcementLearning-AtariGame"},{"title":"Kaixhin/NoisyNet-A3C","url":"https://github.com/Kaixhin/NoisyNet-A3C"},{"title":"khanhptnk/bandit-nmt","url":"https://github.com/khanhptnk/bandit-nmt"},{"title":"arnomoonens/yarll","url":"https://github.com/arnomoonens/yarll"},{"title":"traai/async-deep-rl","url":"https://github.com/traai/async-deep-rl"},{"title":"deepsense-ai/Distributed-BA3C","url":"https://github.com/deepsense-ai/Distributed-BA3C"},{"title":"ikostrikov/pytorch-rl","url":"https://github.com/ikostrikov/pytorch-rl"},{"title":"nvlabs/gbrl_sb3","url":"https://github.com/nvlabs/gbrl_sb3"},{"title":"ShibiHe/Q-Optimality-Tightening","url":"https://github.com/ShibiHe/Q-Optimality-Tightening"},{"title":"qihongl/dlstm-demo","url":"https://github.com/qihongl/dlstm-demo"},{"title":"MatheusMRFM/A3C-LSTM-with-Tensorflow","url":"https://github.com/MatheusMRFM/A3C-LSTM-with-Tensorflow"},{"title":"roop-pal/Meta-Learning-for-StarCraft-II-Minigames","url":"https://github.com/roop-pal/Meta-Learning-for-StarCraft-II-Minigames"},{"title":"4rChon/NL-FuN","url":"https://github.com/4rChon/NL-FuN"},{"title":"braemt/attentive-multi-task-deep-reinforcement-learning","url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning"},{"title":"Sheepsody/Batched-Impala-PyTorch","url":"https://github.com/Sheepsody/Batched-Impala-PyTorch"},{"title":"avillemin/Minecraft-AI","url":"https://github.com/avillemin/Minecraft-AI"},{"title":"bkhmsi/meta-rl-harlow","url":"https://github.com/bkhmsi/meta-rl-harlow"},{"title":"mavischer/DRRL","url":"https://github.com/mavischer/DRRL"},{"title":"grananqvist/reinforcement-learning-super-mario-A3C","url":"https://github.com/grananqvist/reinforcement-learning-super-mario-A3C"},{"title":"brett-daley/fast-dqn","url":"https://github.com/brett-daley/fast-dqn"},{"title":"vladfi1/universe-starter-agent","url":"https://github.com/vladfi1/universe-starter-agent"},{"title":"qihongl/demo-advantage-actor-critic","url":"https://github.com/qihongl/demo-advantage-actor-critic"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"dsinghnegi/atari_RL_agent","url":"https://github.com/dsinghnegi/atari_RL_agent"},{"title":"Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment"},{"title":"gungui98/deeprl-a3c-ai2thor","url":"https://github.com/gungui98/deeprl-a3c-ai2thor"},{"title":"amanda-lambda/hack-flappy-bird-drl","url":"https://github.com/amanda-lambda/hack-flappy-bird-drl"},{"title":"amanda-lambda/drl-experiments","url":"https://github.com/amanda-lambda/drl-experiments"},{"title":"Zartris/TD3_continuous_control","url":"https://github.com/Zartris/TD3_continuous_control"},{"title":"liuyuezhang/pyrl","url":"https://github.com/liuyuezhang/pyrl"},{"title":"InSpaceAI/RL-Zoo","url":"https://github.com/InSpaceAI/RL-Zoo"},{"title":"N0r9st/a2c-jax","url":"https://github.com/N0r9st/a2c-jax"},{"title":"amaudruz/RL_openaigym","url":"https://github.com/amaudruz/RL_openaigym"},{"title":"cdesilv1/sc2_ai_cdes","url":"https://github.com/cdesilv1/sc2_ai_cdes"},{"title":"wxj77/TransferReinforcementLearning","url":"https://github.com/wxj77/TransferReinforcementLearning"},{"title":"joshiatul/game_playing","url":"https://github.com/joshiatul/game_playing"},{"title":"sainijagjit/A3C-Pytorch","url":"https://github.com/sainijagjit/A3C-Pytorch"},{"title":"alexmlamb/blocks_rl_gru_setup","url":"https://github.com/alexmlamb/blocks_rl_gru_setup"},{"title":"PaulCharnay/Projet_AIF","url":"https://github.com/PaulCharnay/Projet_AIF"},{"title":"sharan-dce/A3C","url":"https://github.com/sharan-dce/A3C"},{"title":"danielpolimac/Ispit_Inteligentni_Agenti","url":"https://github.com/danielpolimac/Ispit_Inteligentni_Agenti"},{"title":"AI-RG/rl-experiments","url":"https://github.com/AI-RG/rl-experiments"},{"title":"natsumeS/analysis","url":"https://github.com/natsumeS/analysis"},{"title":"aabbeell/reinforcementLearning.a2c.gym","url":"https://github.com/aabbeell/reinforcementLearning.a2c.gym"},{"title":"Jzar/Space-Invaders-DQN","url":"https://github.com/Jzar/Space-Invaders-DQN"},{"title":"JulT1/RL_SS19","url":"https://github.com/JulT1/RL_SS19"},{"title":"ofekluis/sonic_project_ss19","url":"https://github.com/ofekluis/sonic_project_ss19"},{"title":"hulanwin/A3C-DRL","url":"https://github.com/hulanwin/A3C-DRL"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60591,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"Persistent AL","metrics":{"Score":"1328.25"},"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":60592,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"Prior noop","metrics":{"Score":"1305.6"},"paper_url":"http://arxiv.org/abs/1511.05952v4","paper_title":"Prioritized Experience Replay","paper_date":"2015-11-18","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"ku2482/sac-discrete.pytorch","url":"https://github.com/ku2482/sac-discrete.pytorch"},{"title":"instadeepai/flashbax","url":"https://github.com/instadeepai/flashbax"},{"title":"SimonRamstedt/ddpg","url":"https://github.com/SimonRamstedt/ddpg"},{"title":"Damcy/prioritized-experience-replay","url":"https://github.com/Damcy/prioritized-experience-replay"},{"title":"backgom2357/Recommender_system_via_deep_RL","url":"https://github.com/backgom2357/Recommender_system_via_deep_RL"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"toshikwa/soft-actor-critic.pytorch","url":"https://github.com/toshikwa/soft-actor-critic.pytorch"},{"title":"ku2482/soft-actor-critic.pytorch","url":"https://github.com/ku2482/soft-actor-critic.pytorch"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"Howuhh/prioritized_experience_replay","url":"https://github.com/Howuhh/prioritized_experience_replay"},{"title":"JuliaPOMDP/DeepQLearning.jl","url":"https://github.com/JuliaPOMDP/DeepQLearning.jl"},{"title":"dtak/hip-mdp-public","url":"https://github.com/dtak/hip-mdp-public"},{"title":"xinjinghao/sparrow-v1","url":"https://github.com/xinjinghao/sparrow-v1"},{"title":"atavakol/action-hypergraph-networks","url":"https://github.com/atavakol/action-hypergraph-networks"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"Guillaume-Cr/lunar_lander_per","url":"https://github.com/Guillaume-Cr/lunar_lander_per"},{"title":"kayuksel/pytorch-ars","url":"https://github.com/kayuksel/pytorch-ars"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"Suryavf/SelfDrivingCar","url":"https://github.com/Suryavf/SelfDrivingCar"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"Arrabonae/openai_DDDQN","url":"https://github.com/Arrabonae/openai_DDDQN"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"MathPhysSim/PER-NAF","url":"https://github.com/MathPhysSim/PER-NAF"},{"title":"KAIST-AILab/deeprl_practice_colab","url":"https://github.com/KAIST-AILab/deeprl_practice_colab"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"VictorZuanazzi/Project_RL","url":"https://github.com/VictorZuanazzi/Project_RL"},{"title":"Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"yzheng51/rl-dino-run","url":"https://github.com/yzheng51/rl-dino-run"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"emiled16/Beyond_prioritized_experience_replay","url":"https://github.com/emiled16/Beyond_prioritized_experience_replay"},{"title":"7starsea/Prioritized-Experience-Replay","url":"https://github.com/7starsea/Prioritized-Experience-Replay"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"justinmaojones/starr","url":"https://github.com/justinmaojones/starr"},{"title":"CharlotteMorrison/Baxter-VREP","url":"https://github.com/CharlotteMorrison/Baxter-VREP"},{"title":"iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient","url":"https://github.com/iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"iDataist/Tennis-With-Multi-Agent-Reinforcement","url":"https://github.com/iDataist/Tennis-With-Multi-Agent-Reinforcement"},{"title":"ACampero/dopamine","url":"https://github.com/ACampero/dopamine"},{"title":"iDataist/Navigation-with-Deep-Q-Network","url":"https://github.com/iDataist/Navigation-with-Deep-Q-Network"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"KatyNTsachi/Hierarchical-RL","url":"https://github.com/KatyNTsachi/Hierarchical-RL"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"CharlotteMorrison/Baxter-Research","url":"https://github.com/CharlotteMorrison/Baxter-Research"},{"title":"ameet-1997/Prioritized_Experience_Replay","url":"https://github.com/ameet-1997/Prioritized_Experience_Replay"},{"title":"CSCI4850/S20-team3-project","url":"https://github.com/CSCI4850/S20-team3-project"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"Clement-Hui/Q-Learning","url":"https://github.com/Clement-Hui/Q-Learning"},{"title":"tphanson/xupr-drl","url":"https://github.com/tphanson/xupr-drl"},{"title":"snhwang/p3_collab-compet","url":"https://github.com/snhwang/p3_collab-compet"},{"title":"CharlotteMorrison/Baxter-VREP-Version-2","url":"https://github.com/CharlotteMorrison/Baxter-VREP-Version-2"},{"title":"snhwang/p2-continuous-control-SNH","url":"https://github.com/snhwang/p2-continuous-control-SNH"},{"title":"snhwang/p1_navigation_SNH","url":"https://github.com/snhwang/p1_navigation_SNH"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"},{"title":"VasaKiDD/TD3-deep-rl-research","url":"https://github.com/VasaKiDD/TD3-deep-rl-research"},{"title":"V0LsTeR/dopamine_prioritized_buffer","url":"https://github.com/V0LsTeR/dopamine_prioritized_buffer"},{"title":"sunfex/weighted-sac","url":"https://github.com/sunfex/weighted-sac"},{"title":"anhtu293/NeurIPS-2019-Challenge","url":"https://github.com/anhtu293/NeurIPS-2019-Challenge"},{"title":"Brandon-Rozek/DeepRL","url":"https://github.com/Brandon-Rozek/DeepRL"},{"title":"V0LsTeR/DQN_heap","url":"https://github.com/V0LsTeR/DQN_heap"},{"title":"olonok69/Udacity_Banana_Unity","url":"https://github.com/olonok69/Udacity_Banana_Unity"},{"title":"seacevedo/ReinforcementLearningProjects","url":"https://github.com/seacevedo/ReinforcementLearningProjects"},{"title":"MrDaubinet/collaboration-and-competition","url":"https://github.com/MrDaubinet/collaboration-and-competition"},{"title":"yusme/DDPG","url":"https://github.com/yusme/DDPG"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"GoingMyWay/dopamine_reward_decomposition","url":"https://github.com/GoingMyWay/dopamine_reward_decomposition"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60593,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"DDQN (tuned) noop","metrics":{"Score":"1225.4"},"paper_url":"http://arxiv.org/abs/1511.06581v3","paper_title":"Dueling Network Architectures for Deep Reinforcement Learning","paper_date":"2015-11-20","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"facebookresearch/Horizon","url":"https://github.com/facebookresearch/Horizon"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"ku2482/sac-discrete.pytorch","url":"https://github.com/ku2482/sac-discrete.pytorch"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"BY571/DQN-Atari-Agents","url":"https://github.com/BY571/DQN-Atari-Agents"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"JuliaPOMDP/DeepQLearning.jl","url":"https://github.com/JuliaPOMDP/DeepQLearning.jl"},{"title":"gouxiangchen/dueling-DQN-pytorch","url":"https://github.com/gouxiangchen/dueling-DQN-pytorch"},{"title":"R-Sweke/DeepQ-Decoding","url":"https://github.com/R-Sweke/DeepQ-Decoding"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"ethanmclark1/carla_aebs","url":"https://github.com/ethanmclark1/carla_aebs"},{"title":"clarky104/carla_aebs","url":"https://github.com/clarky104/carla_aebs"},{"title":"KDL-umass/saliency_maps","url":"https://github.com/KDL-umass/saliency_maps"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"alessandrositta/Flatland_challenge","url":"https://github.com/alessandrositta/Flatland_challenge"},{"title":"MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"nathanin/pad","url":"https://github.com/nathanin/pad"},{"title":"zynk13/dueling-dqn-Reinforcement-learning","url":"https://github.com/zynk13/dueling-dqn-Reinforcement-learning"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"prajwalgatti/DRL-Continuous-Control","url":"https://github.com/prajwalgatti/DRL-Continuous-Control"},{"title":"la3lma/chezjulia","url":"https://github.com/la3lma/chezjulia"},{"title":"la3lma/Chez","url":"https://github.com/la3lma/Chez"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"prajwalgatti/DRL-Navigation","url":"https://github.com/prajwalgatti/DRL-Navigation"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning","url":"https://github.com/manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"iDataist/Navigation-with-Deep-Q-Network","url":"https://github.com/iDataist/Navigation-with-Deep-Q-Network"},{"title":"jsztompka/DuelDQN","url":"https://github.com/jsztompka/DuelDQN"},{"title":"170928/-Review-Dueling-Deep-Q-Network","url":"https://github.com/170928/-Review-Dueling-Deep-Q-Network"},{"title":"Brandon-Rozek/DeepRL","url":"https://github.com/Brandon-Rozek/DeepRL"},{"title":"abryeemessi/Wednesday","url":"https://github.com/abryeemessi/Wednesday"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"JBGUIMBAUD/deep-reenforcement-learning","url":"https://github.com/JBGUIMBAUD/deep-reenforcement-learning"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"opplieam/Pong-Deep-RL","url":"https://github.com/opplieam/Pong-Deep-RL"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60594,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"DDQN+Pop-Art noop","metrics":{"Score":"1199.6"},"paper_url":"http://arxiv.org/abs/1602.07714v2","paper_title":"Learning values across many orders of magnitude","paper_date":"2016-02-24","code_links":[],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60595,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"CGP","metrics":{"Score":"1138"},"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":60596,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"IQN","metrics":{"Score":"1053"},"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":60597,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"DDQN (tuned) hs","metrics":{"Score":"1011.1"},"paper_url":"http://arxiv.org/abs/1509.06461v3","paper_title":"Deep Reinforcement Learning with Double Q-learning","paper_date":"2015-09-22","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"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":"MaximeVandegar/Papers-in-100-Lines-of-Code","url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Deep_Reinforcement_Learning_with_Double_Q_learning"},{"title":"deepmind/rlax","url":"https://github.com/deepmind/rlax"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"yukezhu/tensorflow-reinforce","url":"https://github.com/yukezhu/tensorflow-reinforce"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"YuansongFeng/MadMario","url":"https://github.com/YuansongFeng/MadMario"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning","url":"https://github.com/jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning"},{"title":"microsoft/med-deadend","url":"https://github.com/microsoft/med-deadend"},{"title":"xtma/simple-pytorch-rl","url":"https://github.com/xtma/simple-pytorch-rl"},{"title":"moduIo/Deep-Q-network","url":"https://github.com/moduIo/Deep-Q-network"},{"title":"Denbergvanthijs/imbDRL","url":"https://github.com/Denbergvanthijs/imbDRL"},{"title":"kochlisGit/autonomous-vehicles-agent","url":"https://github.com/kochlisGit/autonomous-vehicles-agent"},{"title":"matthewsparr/Deep-Zork","url":"https://github.com/matthewsparr/Deep-Zork"},{"title":"hamishs/JAX-RL","url":"https://github.com/hamishs/JAX-RL"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"anh-nn01/Lunar-Lander-Double-Deep-Q-Networks","url":"https://github.com/anh-nn01/Lunar-Lander-Double-Deep-Q-Networks"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"PeterJochem/Double_Deep_QLearning","url":"https://github.com/PeterJochem/Double_Deep_QLearning"},{"title":"PeterJochem/Deep_RL","url":"https://github.com/PeterJochem/Deep_RL"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"pathway/alphaxos","url":"https://github.com/pathway/alphaxos"},{"title":"OscarHuangWind/Preference-Guided-DQN-Atari","url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari"},{"title":"paintception/Deep-Quality-Value-Family-","url":"https://github.com/paintception/Deep-Quality-Value-Family-"},{"title":"paintception/Deep-Quality-Value-Family","url":"https://github.com/paintception/Deep-Quality-Value-Family"},{"title":"KelvinYang0320/deepbots-panda","url":"https://github.com/KelvinYang0320/deepbots-panda"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"tkcoding/Stock_DRL","url":"https://github.com/tkcoding/Stock_DRL"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"yzheng51/rl-dino-run","url":"https://github.com/yzheng51/rl-dino-run"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"amirmirzaei79/CartPole-DQN-And-DDQN","url":"https://github.com/amirmirzaei79/CartPole-DQN-And-DDQN"},{"title":"xgfelicia/Reinforcement-Learning","url":"https://github.com/xgfelicia/Reinforcement-Learning"},{"title":"RandyDeng/gym_connect4","url":"https://github.com/RandyDeng/gym_connect4"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"Rabrg/dqn","url":"https://github.com/Rabrg/dqn"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"molomono/CartPole_Optimized_DDQN","url":"https://github.com/molomono/CartPole_Optimized_DDQN"},{"title":"Roman-Kozachek/TradeBot","url":"https://github.com/Roman-Kozachek/TradeBot"},{"title":"gznyyb/deep_reinforcement_learning_Pong","url":"https://github.com/gznyyb/deep_reinforcement_learning_Pong"},{"title":"lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning","url":"https://github.com/lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning"},{"title":"ifestus/rl","url":"https://github.com/ifestus/rl"},{"title":"wmol4/Pytorch_DDQN_Unity_Navigation","url":"https://github.com/wmol4/Pytorch_DDQN_Unity_Navigation"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"jadag/DDQN_mario","url":"https://github.com/jadag/DDQN_mario"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"jvoynow/DQN-analysis-with-2048","url":"https://github.com/jvoynow/DQN-analysis-with-2048"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"aman-khurana/deep-q-learning","url":"https://github.com/aman-khurana/deep-q-learning"},{"title":"yaxinchen666/dce_pricingRL","url":"https://github.com/yaxinchen666/dce_pricingRL"},{"title":"puppetect/TradingBot-tensorflow","url":"https://github.com/puppetect/TradingBot-tensorflow"},{"title":"ianlimle/ItsMeMario","url":"https://github.com/ianlimle/ItsMeMario"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"NikolausBerl/Udacity_DRLN_Navigation_Project","url":"https://github.com/NikolausBerl/Udacity_DRLN_Navigation_Project"},{"title":"jeffery1236/Atari_DoubleDeepQNetwork","url":"https://github.com/jeffery1236/Atari_DoubleDeepQNetwork"},{"title":"Codernauti/Exploration-of-DQN-in-CartPole-Environment","url":"https://github.com/Codernauti/Exploration-of-DQN-in-CartPole-Environment"},{"title":"JustinStitt/acrobotDDQN","url":"https://github.com/JustinStitt/acrobotDDQN"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"},{"title":"zhengant/dqn_reversi","url":"https://github.com/zhengant/dqn_reversi"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"daviddcho/supermario","url":"https://github.com/daviddcho/supermario"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"seacevedo/ReinforcementLearningProjects","url":"https://github.com/seacevedo/ReinforcementLearningProjects"},{"title":"JonasRSV/DQNTensorflow","url":"https://github.com/JonasRSV/DQNTensorflow"},{"title":"ssainz/reinforcement_learning_algorithms","url":"https://github.com/ssainz/reinforcement_learning_algorithms"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"tkcoding/DeepRL","url":"https://github.com/tkcoding/DeepRL"},{"title":"JonasRSV/DQN","url":"https://github.com/JonasRSV/DQN"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60598,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"Duel hs","metrics":{"Score":"910.6"},"paper_url":"http://arxiv.org/abs/1511.06581v3","paper_title":"Dueling Network Architectures for Deep Reinforcement Learning","paper_date":"2015-11-20","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"facebookresearch/Horizon","url":"https://github.com/facebookresearch/Horizon"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"ku2482/sac-discrete.pytorch","url":"https://github.com/ku2482/sac-discrete.pytorch"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"BY571/DQN-Atari-Agents","url":"https://github.com/BY571/DQN-Atari-Agents"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"JuliaPOMDP/DeepQLearning.jl","url":"https://github.com/JuliaPOMDP/DeepQLearning.jl"},{"title":"gouxiangchen/dueling-DQN-pytorch","url":"https://github.com/gouxiangchen/dueling-DQN-pytorch"},{"title":"R-Sweke/DeepQ-Decoding","url":"https://github.com/R-Sweke/DeepQ-Decoding"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"ethanmclark1/carla_aebs","url":"https://github.com/ethanmclark1/carla_aebs"},{"title":"clarky104/carla_aebs","url":"https://github.com/clarky104/carla_aebs"},{"title":"KDL-umass/saliency_maps","url":"https://github.com/KDL-umass/saliency_maps"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"alessandrositta/Flatland_challenge","url":"https://github.com/alessandrositta/Flatland_challenge"},{"title":"MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/Dueling_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"nathanin/pad","url":"https://github.com/nathanin/pad"},{"title":"zynk13/dueling-dqn-Reinforcement-learning","url":"https://github.com/zynk13/dueling-dqn-Reinforcement-learning"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"prajwalgatti/DRL-Continuous-Control","url":"https://github.com/prajwalgatti/DRL-Continuous-Control"},{"title":"la3lma/chezjulia","url":"https://github.com/la3lma/chezjulia"},{"title":"la3lma/Chez","url":"https://github.com/la3lma/Chez"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"prajwalgatti/DRL-Navigation","url":"https://github.com/prajwalgatti/DRL-Navigation"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning","url":"https://github.com/manvibharat/Stock-price-pridiction-using-Deep-reienforcement-learning"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"iDataist/Navigation-with-Deep-Q-Network","url":"https://github.com/iDataist/Navigation-with-Deep-Q-Network"},{"title":"jsztompka/DuelDQN","url":"https://github.com/jsztompka/DuelDQN"},{"title":"170928/-Review-Dueling-Deep-Q-Network","url":"https://github.com/170928/-Review-Dueling-Deep-Q-Network"},{"title":"Brandon-Rozek/DeepRL","url":"https://github.com/Brandon-Rozek/DeepRL"},{"title":"abryeemessi/Wednesday","url":"https://github.com/abryeemessi/Wednesday"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"JBGUIMBAUD/deep-reenforcement-learning","url":"https://github.com/JBGUIMBAUD/deep-reenforcement-learning"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"opplieam/Pong-Deep-RL","url":"https://github.com/opplieam/Pong-Deep-RL"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60599,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"Prior hs","metrics":{"Score":"865.9"},"paper_url":"http://arxiv.org/abs/1511.05952v4","paper_title":"Prioritized Experience Replay","paper_date":"2015-11-18","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"Curt-Park/rainbow-is-all-you-need","url":"https://github.com/Curt-Park/rainbow-is-all-you-need"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"ku2482/sac-discrete.pytorch","url":"https://github.com/ku2482/sac-discrete.pytorch"},{"title":"instadeepai/flashbax","url":"https://github.com/instadeepai/flashbax"},{"title":"SimonRamstedt/ddpg","url":"https://github.com/SimonRamstedt/ddpg"},{"title":"Damcy/prioritized-experience-replay","url":"https://github.com/Damcy/prioritized-experience-replay"},{"title":"backgom2357/Recommender_system_via_deep_RL","url":"https://github.com/backgom2357/Recommender_system_via_deep_RL"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"toshikwa/soft-actor-critic.pytorch","url":"https://github.com/toshikwa/soft-actor-critic.pytorch"},{"title":"ku2482/soft-actor-critic.pytorch","url":"https://github.com/ku2482/soft-actor-critic.pytorch"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"Howuhh/prioritized_experience_replay","url":"https://github.com/Howuhh/prioritized_experience_replay"},{"title":"JuliaPOMDP/DeepQLearning.jl","url":"https://github.com/JuliaPOMDP/DeepQLearning.jl"},{"title":"dtak/hip-mdp-public","url":"https://github.com/dtak/hip-mdp-public"},{"title":"xinjinghao/sparrow-v1","url":"https://github.com/xinjinghao/sparrow-v1"},{"title":"atavakol/action-hypergraph-networks","url":"https://github.com/atavakol/action-hypergraph-networks"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"Guillaume-Cr/lunar_lander_per","url":"https://github.com/Guillaume-Cr/lunar_lander_per"},{"title":"kayuksel/pytorch-ars","url":"https://github.com/kayuksel/pytorch-ars"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"Suryavf/SelfDrivingCar","url":"https://github.com/Suryavf/SelfDrivingCar"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"Arrabonae/openai_DDDQN","url":"https://github.com/Arrabonae/openai_DDDQN"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"MathPhysSim/PER-NAF","url":"https://github.com/MathPhysSim/PER-NAF"},{"title":"KAIST-AILab/deeprl_practice_colab","url":"https://github.com/KAIST-AILab/deeprl_practice_colab"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"VictorZuanazzi/Project_RL","url":"https://github.com/VictorZuanazzi/Project_RL"},{"title":"Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"yzheng51/rl-dino-run","url":"https://github.com/yzheng51/rl-dino-run"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"emiled16/Beyond_prioritized_experience_replay","url":"https://github.com/emiled16/Beyond_prioritized_experience_replay"},{"title":"7starsea/Prioritized-Experience-Replay","url":"https://github.com/7starsea/Prioritized-Experience-Replay"},{"title":"xusophia/DataSciFinalProj","url":"https://github.com/xusophia/DataSciFinalProj"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"justinmaojones/starr","url":"https://github.com/justinmaojones/starr"},{"title":"CharlotteMorrison/Baxter-VREP","url":"https://github.com/CharlotteMorrison/Baxter-VREP"},{"title":"iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient","url":"https://github.com/iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"iDataist/Tennis-With-Multi-Agent-Reinforcement","url":"https://github.com/iDataist/Tennis-With-Multi-Agent-Reinforcement"},{"title":"ACampero/dopamine","url":"https://github.com/ACampero/dopamine"},{"title":"iDataist/Navigation-with-Deep-Q-Network","url":"https://github.com/iDataist/Navigation-with-Deep-Q-Network"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"KatyNTsachi/Hierarchical-RL","url":"https://github.com/KatyNTsachi/Hierarchical-RL"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"CharlotteMorrison/Baxter-Research","url":"https://github.com/CharlotteMorrison/Baxter-Research"},{"title":"ameet-1997/Prioritized_Experience_Replay","url":"https://github.com/ameet-1997/Prioritized_Experience_Replay"},{"title":"CSCI4850/S20-team3-project","url":"https://github.com/CSCI4850/S20-team3-project"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"Clement-Hui/Q-Learning","url":"https://github.com/Clement-Hui/Q-Learning"},{"title":"tphanson/xupr-drl","url":"https://github.com/tphanson/xupr-drl"},{"title":"snhwang/p3_collab-compet","url":"https://github.com/snhwang/p3_collab-compet"},{"title":"CharlotteMorrison/Baxter-VREP-Version-2","url":"https://github.com/CharlotteMorrison/Baxter-VREP-Version-2"},{"title":"snhwang/p2-continuous-control-SNH","url":"https://github.com/snhwang/p2-continuous-control-SNH"},{"title":"snhwang/p1_navigation_SNH","url":"https://github.com/snhwang/p1_navigation_SNH"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"eddynelson/dqn","url":"https://github.com/eddynelson/dqn"},{"title":"VasaKiDD/TD3-deep-rl-research","url":"https://github.com/VasaKiDD/TD3-deep-rl-research"},{"title":"V0LsTeR/dopamine_prioritized_buffer","url":"https://github.com/V0LsTeR/dopamine_prioritized_buffer"},{"title":"sunfex/weighted-sac","url":"https://github.com/sunfex/weighted-sac"},{"title":"anhtu293/NeurIPS-2019-Challenge","url":"https://github.com/anhtu293/NeurIPS-2019-Challenge"},{"title":"Brandon-Rozek/DeepRL","url":"https://github.com/Brandon-Rozek/DeepRL"},{"title":"V0LsTeR/DQN_heap","url":"https://github.com/V0LsTeR/DQN_heap"},{"title":"olonok69/Udacity_Banana_Unity","url":"https://github.com/olonok69/Udacity_Banana_Unity"},{"title":"seacevedo/ReinforcementLearningProjects","url":"https://github.com/seacevedo/ReinforcementLearningProjects"},{"title":"MrDaubinet/collaboration-and-competition","url":"https://github.com/MrDaubinet/collaboration-and-competition"},{"title":"yusme/DDPG","url":"https://github.com/yusme/DDPG"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"GoingMyWay/dopamine_reward_decomposition","url":"https://github.com/GoingMyWay/dopamine_reward_decomposition"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60600,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"A3C LSTM hs","metrics":{"Score":"862.2"},"paper_url":"http://arxiv.org/abs/1602.01783v2","paper_title":"Asynchronous Methods for Deep Reinforcement Learning","paper_date":"2016-02-04","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"DLR-RM/stable-baselines3","url":"https://github.com/DLR-RM/stable-baselines3"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/A3C-Gym"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"pytorch/rl","url":"https://github.com/pytorch/rl/tree/main/examples/a2c"},{"title":"ikostrikov/pytorch-a3c","url":"https://github.com/ikostrikov/pytorch-a3c"},{"title":"Khrylx/PyTorch-RL","url":"https://github.com/Khrylx/PyTorch-RL"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"openai/universe-starter-agent","url":"https://github.com/openai/universe-starter-agent"},{"title":"uvipen/Super-mario-bros-A3C-pytorch","url":"https://github.com/uvipen/Super-mario-bros-A3C-pytorch"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"dickreuter/neuron_poker","url":"https://github.com/dickreuter/neuron_poker"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"marload/deep-rl-tf2","url":"https://github.com/marload/deep-rl-tf2"},{"title":"miyosuda/async_deep_reinforce","url":"https://github.com/miyosuda/async_deep_reinforce"},{"title":"yukezhu/tensorflow-reinforce","url":"https://github.com/yukezhu/tensorflow-reinforce"},{"title":"muupan/async-rl","url":"https://github.com/muupan/async-rl"},{"title":"bentrevett/pytorch-rl","url":"https://github.com/bentrevett/pytorch-rl"},{"title":"Kaixhin/ACER","url":"https://github.com/Kaixhin/ACER"},{"title":"lcswillems/torch-ac","url":"https://github.com/lcswillems/torch-ac"},{"title":"Nasdin/ReinforcementLearning-AtariGame","url":"https://github.com/Nasdin/ReinforcementLearning-AtariGame"},{"title":"Kaixhin/NoisyNet-A3C","url":"https://github.com/Kaixhin/NoisyNet-A3C"},{"title":"khanhptnk/bandit-nmt","url":"https://github.com/khanhptnk/bandit-nmt"},{"title":"arnomoonens/yarll","url":"https://github.com/arnomoonens/yarll"},{"title":"traai/async-deep-rl","url":"https://github.com/traai/async-deep-rl"},{"title":"deepsense-ai/Distributed-BA3C","url":"https://github.com/deepsense-ai/Distributed-BA3C"},{"title":"ikostrikov/pytorch-rl","url":"https://github.com/ikostrikov/pytorch-rl"},{"title":"nvlabs/gbrl_sb3","url":"https://github.com/nvlabs/gbrl_sb3"},{"title":"ShibiHe/Q-Optimality-Tightening","url":"https://github.com/ShibiHe/Q-Optimality-Tightening"},{"title":"qihongl/dlstm-demo","url":"https://github.com/qihongl/dlstm-demo"},{"title":"MatheusMRFM/A3C-LSTM-with-Tensorflow","url":"https://github.com/MatheusMRFM/A3C-LSTM-with-Tensorflow"},{"title":"roop-pal/Meta-Learning-for-StarCraft-II-Minigames","url":"https://github.com/roop-pal/Meta-Learning-for-StarCraft-II-Minigames"},{"title":"4rChon/NL-FuN","url":"https://github.com/4rChon/NL-FuN"},{"title":"braemt/attentive-multi-task-deep-reinforcement-learning","url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning"},{"title":"Sheepsody/Batched-Impala-PyTorch","url":"https://github.com/Sheepsody/Batched-Impala-PyTorch"},{"title":"avillemin/Minecraft-AI","url":"https://github.com/avillemin/Minecraft-AI"},{"title":"bkhmsi/meta-rl-harlow","url":"https://github.com/bkhmsi/meta-rl-harlow"},{"title":"mavischer/DRRL","url":"https://github.com/mavischer/DRRL"},{"title":"grananqvist/reinforcement-learning-super-mario-A3C","url":"https://github.com/grananqvist/reinforcement-learning-super-mario-A3C"},{"title":"brett-daley/fast-dqn","url":"https://github.com/brett-daley/fast-dqn"},{"title":"vladfi1/universe-starter-agent","url":"https://github.com/vladfi1/universe-starter-agent"},{"title":"qihongl/demo-advantage-actor-critic","url":"https://github.com/qihongl/demo-advantage-actor-critic"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"dsinghnegi/atari_RL_agent","url":"https://github.com/dsinghnegi/atari_RL_agent"},{"title":"Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment"},{"title":"gungui98/deeprl-a3c-ai2thor","url":"https://github.com/gungui98/deeprl-a3c-ai2thor"},{"title":"amanda-lambda/hack-flappy-bird-drl","url":"https://github.com/amanda-lambda/hack-flappy-bird-drl"},{"title":"amanda-lambda/drl-experiments","url":"https://github.com/amanda-lambda/drl-experiments"},{"title":"Zartris/TD3_continuous_control","url":"https://github.com/Zartris/TD3_continuous_control"},{"title":"liuyuezhang/pyrl","url":"https://github.com/liuyuezhang/pyrl"},{"title":"InSpaceAI/RL-Zoo","url":"https://github.com/InSpaceAI/RL-Zoo"},{"title":"N0r9st/a2c-jax","url":"https://github.com/N0r9st/a2c-jax"},{"title":"amaudruz/RL_openaigym","url":"https://github.com/amaudruz/RL_openaigym"},{"title":"cdesilv1/sc2_ai_cdes","url":"https://github.com/cdesilv1/sc2_ai_cdes"},{"title":"wxj77/TransferReinforcementLearning","url":"https://github.com/wxj77/TransferReinforcementLearning"},{"title":"joshiatul/game_playing","url":"https://github.com/joshiatul/game_playing"},{"title":"sainijagjit/A3C-Pytorch","url":"https://github.com/sainijagjit/A3C-Pytorch"},{"title":"alexmlamb/blocks_rl_gru_setup","url":"https://github.com/alexmlamb/blocks_rl_gru_setup"},{"title":"PaulCharnay/Projet_AIF","url":"https://github.com/PaulCharnay/Projet_AIF"},{"title":"sharan-dce/A3C","url":"https://github.com/sharan-dce/A3C"},{"title":"danielpolimac/Ispit_Inteligentni_Agenti","url":"https://github.com/danielpolimac/Ispit_Inteligentni_Agenti"},{"title":"AI-RG/rl-experiments","url":"https://github.com/AI-RG/rl-experiments"},{"title":"natsumeS/analysis","url":"https://github.com/natsumeS/analysis"},{"title":"aabbeell/reinforcementLearning.a2c.gym","url":"https://github.com/aabbeell/reinforcementLearning.a2c.gym"},{"title":"Jzar/Space-Invaders-DQN","url":"https://github.com/Jzar/Space-Invaders-DQN"},{"title":"JulT1/RL_SS19","url":"https://github.com/JulT1/RL_SS19"},{"title":"ofekluis/sonic_project_ss19","url":"https://github.com/ofekluis/sonic_project_ss19"},{"title":"hulanwin/A3C-DRL","url":"https://github.com/hulanwin/A3C-DRL"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60601,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"A3C FF hs","metrics":{"Score":"817.9"},"paper_url":"http://arxiv.org/abs/1602.01783v2","paper_title":"Asynchronous Methods for Deep Reinforcement Learning","paper_date":"2016-02-04","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"DLR-RM/stable-baselines3","url":"https://github.com/DLR-RM/stable-baselines3"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/A3C-Gym"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"NervanaSystems/coach","url":"https://github.com/NervanaSystems/coach"},{"title":"pytorch/rl","url":"https://github.com/pytorch/rl/tree/main/examples/a2c"},{"title":"ikostrikov/pytorch-a3c","url":"https://github.com/ikostrikov/pytorch-a3c"},{"title":"Khrylx/PyTorch-RL","url":"https://github.com/Khrylx/PyTorch-RL"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"openai/universe-starter-agent","url":"https://github.com/openai/universe-starter-agent"},{"title":"uvipen/Super-mario-bros-A3C-pytorch","url":"https://github.com/uvipen/Super-mario-bros-A3C-pytorch"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"dickreuter/neuron_poker","url":"https://github.com/dickreuter/neuron_poker"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"marload/deep-rl-tf2","url":"https://github.com/marload/deep-rl-tf2"},{"title":"miyosuda/async_deep_reinforce","url":"https://github.com/miyosuda/async_deep_reinforce"},{"title":"yukezhu/tensorflow-reinforce","url":"https://github.com/yukezhu/tensorflow-reinforce"},{"title":"muupan/async-rl","url":"https://github.com/muupan/async-rl"},{"title":"bentrevett/pytorch-rl","url":"https://github.com/bentrevett/pytorch-rl"},{"title":"Kaixhin/ACER","url":"https://github.com/Kaixhin/ACER"},{"title":"lcswillems/torch-ac","url":"https://github.com/lcswillems/torch-ac"},{"title":"Nasdin/ReinforcementLearning-AtariGame","url":"https://github.com/Nasdin/ReinforcementLearning-AtariGame"},{"title":"Kaixhin/NoisyNet-A3C","url":"https://github.com/Kaixhin/NoisyNet-A3C"},{"title":"khanhptnk/bandit-nmt","url":"https://github.com/khanhptnk/bandit-nmt"},{"title":"arnomoonens/yarll","url":"https://github.com/arnomoonens/yarll"},{"title":"traai/async-deep-rl","url":"https://github.com/traai/async-deep-rl"},{"title":"deepsense-ai/Distributed-BA3C","url":"https://github.com/deepsense-ai/Distributed-BA3C"},{"title":"ikostrikov/pytorch-rl","url":"https://github.com/ikostrikov/pytorch-rl"},{"title":"nvlabs/gbrl_sb3","url":"https://github.com/nvlabs/gbrl_sb3"},{"title":"ShibiHe/Q-Optimality-Tightening","url":"https://github.com/ShibiHe/Q-Optimality-Tightening"},{"title":"qihongl/dlstm-demo","url":"https://github.com/qihongl/dlstm-demo"},{"title":"MatheusMRFM/A3C-LSTM-with-Tensorflow","url":"https://github.com/MatheusMRFM/A3C-LSTM-with-Tensorflow"},{"title":"roop-pal/Meta-Learning-for-StarCraft-II-Minigames","url":"https://github.com/roop-pal/Meta-Learning-for-StarCraft-II-Minigames"},{"title":"4rChon/NL-FuN","url":"https://github.com/4rChon/NL-FuN"},{"title":"braemt/attentive-multi-task-deep-reinforcement-learning","url":"https://github.com/braemt/attentive-multi-task-deep-reinforcement-learning"},{"title":"Sheepsody/Batched-Impala-PyTorch","url":"https://github.com/Sheepsody/Batched-Impala-PyTorch"},{"title":"avillemin/Minecraft-AI","url":"https://github.com/avillemin/Minecraft-AI"},{"title":"bkhmsi/meta-rl-harlow","url":"https://github.com/bkhmsi/meta-rl-harlow"},{"title":"mavischer/DRRL","url":"https://github.com/mavischer/DRRL"},{"title":"grananqvist/reinforcement-learning-super-mario-A3C","url":"https://github.com/grananqvist/reinforcement-learning-super-mario-A3C"},{"title":"brett-daley/fast-dqn","url":"https://github.com/brett-daley/fast-dqn"},{"title":"vladfi1/universe-starter-agent","url":"https://github.com/vladfi1/universe-starter-agent"},{"title":"qihongl/demo-advantage-actor-critic","url":"https://github.com/qihongl/demo-advantage-actor-critic"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"dsinghnegi/atari_RL_agent","url":"https://github.com/dsinghnegi/atari_RL_agent"},{"title":"Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment"},{"title":"gungui98/deeprl-a3c-ai2thor","url":"https://github.com/gungui98/deeprl-a3c-ai2thor"},{"title":"amanda-lambda/hack-flappy-bird-drl","url":"https://github.com/amanda-lambda/hack-flappy-bird-drl"},{"title":"amanda-lambda/drl-experiments","url":"https://github.com/amanda-lambda/drl-experiments"},{"title":"Zartris/TD3_continuous_control","url":"https://github.com/Zartris/TD3_continuous_control"},{"title":"liuyuezhang/pyrl","url":"https://github.com/liuyuezhang/pyrl"},{"title":"InSpaceAI/RL-Zoo","url":"https://github.com/InSpaceAI/RL-Zoo"},{"title":"N0r9st/a2c-jax","url":"https://github.com/N0r9st/a2c-jax"},{"title":"amaudruz/RL_openaigym","url":"https://github.com/amaudruz/RL_openaigym"},{"title":"cdesilv1/sc2_ai_cdes","url":"https://github.com/cdesilv1/sc2_ai_cdes"},{"title":"wxj77/TransferReinforcementLearning","url":"https://github.com/wxj77/TransferReinforcementLearning"},{"title":"joshiatul/game_playing","url":"https://github.com/joshiatul/game_playing"},{"title":"sainijagjit/A3C-Pytorch","url":"https://github.com/sainijagjit/A3C-Pytorch"},{"title":"alexmlamb/blocks_rl_gru_setup","url":"https://github.com/alexmlamb/blocks_rl_gru_setup"},{"title":"PaulCharnay/Projet_AIF","url":"https://github.com/PaulCharnay/Projet_AIF"},{"title":"sharan-dce/A3C","url":"https://github.com/sharan-dce/A3C"},{"title":"danielpolimac/Ispit_Inteligentni_Agenti","url":"https://github.com/danielpolimac/Ispit_Inteligentni_Agenti"},{"title":"AI-RG/rl-experiments","url":"https://github.com/AI-RG/rl-experiments"},{"title":"natsumeS/analysis","url":"https://github.com/natsumeS/analysis"},{"title":"aabbeell/reinforcementLearning.a2c.gym","url":"https://github.com/aabbeell/reinforcementLearning.a2c.gym"},{"title":"Jzar/Space-Invaders-DQN","url":"https://github.com/Jzar/Space-Invaders-DQN"},{"title":"JulT1/RL_SS19","url":"https://github.com/JulT1/RL_SS19"},{"title":"ofekluis/sonic_project_ss19","url":"https://github.com/ofekluis/sonic_project_ss19"},{"title":"hulanwin/A3C-DRL","url":"https://github.com/hulanwin/A3C-DRL"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60602,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"DreamerV2","metrics":{"Score":"810"},"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":60603,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"Advantage Learning","metrics":{"Score":"747.26"},"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":60604,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"ES FF (1 hour) noop","metrics":{"Score":"686.0"},"paper_url":"http://arxiv.org/abs/1703.03864v2","paper_title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","paper_date":"2017-03-10","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"openai/evolution-strategies-starter","url":"https://github.com/openai/evolution-strategies-starter"},{"title":"atgambardella/pytorch-es","url":"https://github.com/atgambardella/pytorch-es"},{"title":"rasmusbergpalm/evostrat","url":"https://github.com/rasmusbergpalm/evostrat"},{"title":"nnaisense/pgpelib","url":"https://github.com/nnaisense/pgpelib"},{"title":"ShangtongZhang/DistributedES","url":"https://github.com/ShangtongZhang/DistributedES"},{"title":"evaboost/evaboost","url":"https://github.com/evaboost/evaboost"},{"title":"enajx/ES","url":"https://github.com/enajx/ES"},{"title":"fiberleif/evolution-strategies","url":"https://github.com/fiberleif/evolution-strategies"},{"title":"neuro-soup/es-torch","url":"https://github.com/neuro-soup/es-torch"},{"title":"stavrosgreece/MultiAgentLearning","url":"https://github.com/stavrosgreece/MultiAgentLearning"},{"title":"FlixCoder/rust-es-optimizer","url":"https://github.com/FlixCoder/rust-es-optimizer"},{"title":"MohammadAsadolahi/Gradient-Free-Reinforcement-Learning-solving-Openai-gym-LunarLanderV2-by-Evolution-Strategy-python","url":"https://github.com/MohammadAsadolahi/Gradient-Free-Reinforcement-Learning-solving-Openai-gym-LunarLanderV2-by-Evolution-Strategy-python/blob/main/README.md"},{"title":"silvialuu/DRL-2018","url":"https://github.com/silvialuu/DRL-2018"},{"title":"susanwe/ope_worldmodels","url":"https://github.com/susanwe/ope_worldmodels"},{"title":"czen88/qtrader","url":"https://github.com/czen88/qtrader"},{"title":"aspk/space_battle","url":"https://github.com/aspk/space_battle"},{"title":"shakti365/nes","url":"https://github.com/shakti365/nes"},{"title":"cesch97/NeuroEvolution","url":"https://github.com/cesch97/NeuroEvolution"},{"title":"alisidd/Evolution-Strategies","url":"https://github.com/alisidd/Evolution-Strategies"},{"title":"AnshMittal1811/AugmentedRandomSearch","url":"https://github.com/AnshMittal1811/AugmentedRandomSearch"},{"title":"patniemeyer/ga-autoencoder","url":"https://github.com/patniemeyer/ga-autoencoder"},{"title":"neilsgp/RL-Algorithms","url":"https://github.com/neilsgp/RL-Algorithms"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60605,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"Best Baseline","metrics":{"Score":"670"},"paper_url":"http://arxiv.org/abs/1207.4708v2","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","paper_date":"2012-07-19","code_links":[{"title":"mgbellemare/Arcade-Learning-Environment","url":"https://github.com/mgbellemare/Arcade-Learning-Environment"},{"title":"kenjyoung/MinAtar","url":"https://github.com/kenjyoung/MinAtar"},{"title":"nandomp/AICollaboratory","url":"https://github.com/nandomp/AICollaboratory"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60606,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"DQN noop","metrics":{"Score":"585.6"},"paper_url":"http://arxiv.org/abs/1509.06461v3","paper_title":"Deep Reinforcement Learning with Double Q-learning","paper_date":"2015-09-22","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"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":"MaximeVandegar/Papers-in-100-Lines-of-Code","url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Deep_Reinforcement_Learning_with_Double_Q_learning"},{"title":"deepmind/rlax","url":"https://github.com/deepmind/rlax"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"yukezhu/tensorflow-reinforce","url":"https://github.com/yukezhu/tensorflow-reinforce"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"YuansongFeng/MadMario","url":"https://github.com/YuansongFeng/MadMario"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning","url":"https://github.com/jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning"},{"title":"microsoft/med-deadend","url":"https://github.com/microsoft/med-deadend"},{"title":"xtma/simple-pytorch-rl","url":"https://github.com/xtma/simple-pytorch-rl"},{"title":"moduIo/Deep-Q-network","url":"https://github.com/moduIo/Deep-Q-network"},{"title":"Denbergvanthijs/imbDRL","url":"https://github.com/Denbergvanthijs/imbDRL"},{"title":"kochlisGit/autonomous-vehicles-agent","url":"https://github.com/kochlisGit/autonomous-vehicles-agent"},{"title":"matthewsparr/Deep-Zork","url":"https://github.com/matthewsparr/Deep-Zork"},{"title":"hamishs/JAX-RL","url":"https://github.com/hamishs/JAX-RL"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"anh-nn01/Lunar-Lander-Double-Deep-Q-Networks","url":"https://github.com/anh-nn01/Lunar-Lander-Double-Deep-Q-Networks"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"PeterJochem/Double_Deep_QLearning","url":"https://github.com/PeterJochem/Double_Deep_QLearning"},{"title":"PeterJochem/Deep_RL","url":"https://github.com/PeterJochem/Deep_RL"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"pathway/alphaxos","url":"https://github.com/pathway/alphaxos"},{"title":"OscarHuangWind/Preference-Guided-DQN-Atari","url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari"},{"title":"paintception/Deep-Quality-Value-Family-","url":"https://github.com/paintception/Deep-Quality-Value-Family-"},{"title":"paintception/Deep-Quality-Value-Family","url":"https://github.com/paintception/Deep-Quality-Value-Family"},{"title":"KelvinYang0320/deepbots-panda","url":"https://github.com/KelvinYang0320/deepbots-panda"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"tkcoding/Stock_DRL","url":"https://github.com/tkcoding/Stock_DRL"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"yzheng51/rl-dino-run","url":"https://github.com/yzheng51/rl-dino-run"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"amirmirzaei79/CartPole-DQN-And-DDQN","url":"https://github.com/amirmirzaei79/CartPole-DQN-And-DDQN"},{"title":"xgfelicia/Reinforcement-Learning","url":"https://github.com/xgfelicia/Reinforcement-Learning"},{"title":"RandyDeng/gym_connect4","url":"https://github.com/RandyDeng/gym_connect4"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"Rabrg/dqn","url":"https://github.com/Rabrg/dqn"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"molomono/CartPole_Optimized_DDQN","url":"https://github.com/molomono/CartPole_Optimized_DDQN"},{"title":"Roman-Kozachek/TradeBot","url":"https://github.com/Roman-Kozachek/TradeBot"},{"title":"gznyyb/deep_reinforcement_learning_Pong","url":"https://github.com/gznyyb/deep_reinforcement_learning_Pong"},{"title":"lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning","url":"https://github.com/lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning"},{"title":"ifestus/rl","url":"https://github.com/ifestus/rl"},{"title":"wmol4/Pytorch_DDQN_Unity_Navigation","url":"https://github.com/wmol4/Pytorch_DDQN_Unity_Navigation"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"jadag/DDQN_mario","url":"https://github.com/jadag/DDQN_mario"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"jvoynow/DQN-analysis-with-2048","url":"https://github.com/jvoynow/DQN-analysis-with-2048"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"aman-khurana/deep-q-learning","url":"https://github.com/aman-khurana/deep-q-learning"},{"title":"yaxinchen666/dce_pricingRL","url":"https://github.com/yaxinchen666/dce_pricingRL"},{"title":"puppetect/TradingBot-tensorflow","url":"https://github.com/puppetect/TradingBot-tensorflow"},{"title":"ianlimle/ItsMeMario","url":"https://github.com/ianlimle/ItsMeMario"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"NikolausBerl/Udacity_DRLN_Navigation_Project","url":"https://github.com/NikolausBerl/Udacity_DRLN_Navigation_Project"},{"title":"jeffery1236/Atari_DoubleDeepQNetwork","url":"https://github.com/jeffery1236/Atari_DoubleDeepQNetwork"},{"title":"Codernauti/Exploration-of-DQN-in-CartPole-Environment","url":"https://github.com/Codernauti/Exploration-of-DQN-in-CartPole-Environment"},{"title":"JustinStitt/acrobotDDQN","url":"https://github.com/JustinStitt/acrobotDDQN"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"},{"title":"zhengant/dqn_reversi","url":"https://github.com/zhengant/dqn_reversi"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"daviddcho/supermario","url":"https://github.com/daviddcho/supermario"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"seacevedo/ReinforcementLearningProjects","url":"https://github.com/seacevedo/ReinforcementLearningProjects"},{"title":"JonasRSV/DQNTensorflow","url":"https://github.com/JonasRSV/DQNTensorflow"},{"title":"ssainz/reinforcement_learning_algorithms","url":"https://github.com/ssainz/reinforcement_learning_algorithms"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"tkcoding/DeepRL","url":"https://github.com/tkcoding/DeepRL"},{"title":"JonasRSV/DQN","url":"https://github.com/JonasRSV/DQN"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60607,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"Best Learner","metrics":{"Score":"501.3"},"paper_url":"http://arxiv.org/abs/1207.4708v2","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","paper_date":"2012-07-19","code_links":[{"title":"mgbellemare/Arcade-Learning-Environment","url":"https://github.com/mgbellemare/Arcade-Learning-Environment"},{"title":"kenjyoung/MinAtar","url":"https://github.com/kenjyoung/MinAtar"},{"title":"nandomp/AICollaboratory","url":"https://github.com/nandomp/AICollaboratory"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":60608,"task":"Atari Games","parent_task":"Video Games","dataset":"Atari 2600 Berzerk","model_name":"DQN hs","metrics":{"Score":"493.4"},"paper_url":"http://arxiv.org/abs/1509.06461v3","paper_title":"Deep Reinforcement Learning with Double Q-learning","paper_date":"2015-09-22","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/DeepQNetwork"},{"title":"hill-a/stable-baselines","url":"https://github.com/hill-a/stable-baselines"},{"title":"facebookresearch/ReAgent","url":"https://github.com/facebookresearch/ReAgent"},{"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":"MaximeVandegar/Papers-in-100-Lines-of-Code","url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Deep_Reinforcement_Learning_with_Double_Q_learning"},{"title":"deepmind/rlax","url":"https://github.com/deepmind/rlax"},{"title":"chainer/chainerrl","url":"https://github.com/chainer/chainerrl"},{"title":"toni-sm/skrl","url":"https://github.com/toni-sm/skrl"},{"title":"tensorlayer/RLzoo","url":"https://github.com/tensorlayer/RLzoo"},{"title":"marload/DeepRL-TensorFlow2","url":"https://github.com/marload/DeepRL-TensorFlow2"},{"title":"dxyang/DQN_pytorch","url":"https://github.com/dxyang/DQN_pytorch"},{"title":"yukezhu/tensorflow-reinforce","url":"https://github.com/yukezhu/tensorflow-reinforce"},{"title":"philtabor/Deep-Q-Learning-Paper-To-Code","url":"https://github.com/philtabor/Deep-Q-Learning-Paper-To-Code"},{"title":"YuansongFeng/MadMario","url":"https://github.com/YuansongFeng/MadMario"},{"title":"cove9988/TradingGym","url":"https://github.com/cove9988/TradingGym"},{"title":"atavakol/action-branching-agents","url":"https://github.com/atavakol/action-branching-agents"},{"title":"chandar-lab/RLHive","url":"https://github.com/chandar-lab/RLHive"},{"title":"jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning","url":"https://github.com/jihoonerd/Deep-Reinforcement-Learning-with-Double-Q-learning"},{"title":"microsoft/med-deadend","url":"https://github.com/microsoft/med-deadend"},{"title":"xtma/simple-pytorch-rl","url":"https://github.com/xtma/simple-pytorch-rl"},{"title":"moduIo/Deep-Q-network","url":"https://github.com/moduIo/Deep-Q-network"},{"title":"Denbergvanthijs/imbDRL","url":"https://github.com/Denbergvanthijs/imbDRL"},{"title":"kochlisGit/autonomous-vehicles-agent","url":"https://github.com/kochlisGit/autonomous-vehicles-agent"},{"title":"matthewsparr/Deep-Zork","url":"https://github.com/matthewsparr/Deep-Zork"},{"title":"hamishs/JAX-RL","url":"https://github.com/hamishs/JAX-RL"},{"title":"cocolico14/N-step-Dueling-DDQN-PER-Pacman","url":"https://github.com/cocolico14/N-step-Dueling-DDQN-PER-Pacman"},{"title":"anh-nn01/Lunar-Lander-Double-Deep-Q-Networks","url":"https://github.com/anh-nn01/Lunar-Lander-Double-Deep-Q-Networks"},{"title":"Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification"},{"title":"mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore","url":"https://github.com/mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore"},{"title":"PeterJochem/Double_Deep_QLearning","url":"https://github.com/PeterJochem/Double_Deep_QLearning"},{"title":"PeterJochem/Deep_RL","url":"https://github.com/PeterJochem/Deep_RL"},{"title":"kmdanielduan/DQN_Family_PyTorch","url":"https://github.com/kmdanielduan/DQN_Family_PyTorch"},{"title":"pathway/alphaxos","url":"https://github.com/pathway/alphaxos"},{"title":"OscarHuangWind/Preference-Guided-DQN-Atari","url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari"},{"title":"paintception/Deep-Quality-Value-Family-","url":"https://github.com/paintception/Deep-Quality-Value-Family-"},{"title":"paintception/Deep-Quality-Value-Family","url":"https://github.com/paintception/Deep-Quality-Value-Family"},{"title":"KelvinYang0320/deepbots-panda","url":"https://github.com/KelvinYang0320/deepbots-panda"},{"title":"hemilpanchiwala/Dueling-Network-Architectures","url":"https://github.com/hemilpanchiwala/Dueling-Network-Architectures"},{"title":"hemilpanchiwala/Dueling_Network_Architectures","url":"https://github.com/hemilpanchiwala/Dueling_Network_Architectures"},{"title":"utarumo/RL_implementation","url":"https://github.com/utarumo/RL_implementation"},{"title":"tkcoding/Stock_DRL","url":"https://github.com/tkcoding/Stock_DRL"},{"title":"mindspore-courses/Rainbow-MindSpore","url":"https://github.com/mindspore-courses/Rainbow-MindSpore"},{"title":"wtingda/DeepRLBreakout","url":"https://github.com/wtingda/DeepRLBreakout"},{"title":"yzheng51/rl-dino-run","url":"https://github.com/yzheng51/rl-dino-run"},{"title":"rybread1/deep-rl-trex","url":"https://github.com/rybread1/deep-rl-trex"},{"title":"OMS1996/Carla_The_RL_Self-Driving-Car","url":"https://github.com/OMS1996/Carla_The_RL_Self-Driving-Car"},{"title":"rybread1/DeepRlTrex","url":"https://github.com/rybread1/DeepRlTrex"},{"title":"amirmirzaei79/CartPole-DQN-And-DDQN","url":"https://github.com/amirmirzaei79/CartPole-DQN-And-DDQN"},{"title":"xgfelicia/Reinforcement-Learning","url":"https://github.com/xgfelicia/Reinforcement-Learning"},{"title":"RandyDeng/gym_connect4","url":"https://github.com/RandyDeng/gym_connect4"},{"title":"SayhoKim/tetrisRL","url":"https://github.com/SayhoKim/tetrisRL"},{"title":"MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python","url":"https://github.com/MohammadAsadolahi/DDQN_Deep-Double_Q-Learning-for-solving-OpenAi-Gym-LunarLander-v2-in-python"},{"title":"Rabrg/dqn","url":"https://github.com/Rabrg/dqn"},{"title":"near32/regym","url":"https://github.com/near32/regym"},{"title":"1jsingh/rl_navigation","url":"https://github.com/1jsingh/rl_navigation"},{"title":"molomono/CartPole_Optimized_DDQN","url":"https://github.com/molomono/CartPole_Optimized_DDQN"},{"title":"Roman-Kozachek/TradeBot","url":"https://github.com/Roman-Kozachek/TradeBot"},{"title":"gznyyb/deep_reinforcement_learning_Pong","url":"https://github.com/gznyyb/deep_reinforcement_learning_Pong"},{"title":"lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning","url":"https://github.com/lbenbaccar/Deep-Reinforcement-Learning-with-Double-Q-Learning"},{"title":"ifestus/rl","url":"https://github.com/ifestus/rl"},{"title":"wmol4/Pytorch_DDQN_Unity_Navigation","url":"https://github.com/wmol4/Pytorch_DDQN_Unity_Navigation"},{"title":"botforge/simplementation","url":"https://github.com/botforge/simplementation"},{"title":"fengsterooni/dql","url":"https://github.com/fengsterooni/dql"},{"title":"mohit8935/Deep-Q-Learning-Paper","url":"https://github.com/mohit8935/Deep-Q-Learning-Paper"},{"title":"jadag/DDQN_mario","url":"https://github.com/jadag/DDQN_mario"},{"title":"kshitij-ingale/Reinforcement-Learning","url":"https://github.com/kshitij-ingale/Reinforcement-Learning"},{"title":"MEOWMEOW114/nd893-p1-navigation-banana","url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana"},{"title":"Adrelf/DRL-navigation","url":"https://github.com/Adrelf/DRL-navigation"},{"title":"HussonnoisMaxence/RL_Algorithms","url":"https://github.com/HussonnoisMaxence/RL_Algorithms"},{"title":"jvoynow/DQN-analysis-with-2048","url":"https://github.com/jvoynow/DQN-analysis-with-2048"},{"title":"shehrum/RL_Navigation","url":"https://github.com/shehrum/RL_Navigation"},{"title":"aman-khurana/deep-q-learning","url":"https://github.com/aman-khurana/deep-q-learning"},{"title":"yaxinchen666/dce_pricingRL","url":"https://github.com/yaxinchen666/dce_pricingRL"},{"title":"puppetect/TradingBot-tensorflow","url":"https://github.com/puppetect/TradingBot-tensorflow"},{"title":"ianlimle/ItsMeMario","url":"https://github.com/ianlimle/ItsMeMario"},{"title":"FaboNo/DRLND","url":"https://github.com/FaboNo/DRLND"},{"title":"NikolausBerl/Udacity_DRLN_Navigation_Project","url":"https://github.com/NikolausBerl/Udacity_DRLN_Navigation_Project"},{"title":"jeffery1236/Atari_DoubleDeepQNetwork","url":"https://github.com/jeffery1236/Atari_DoubleDeepQNetwork"},{"title":"Codernauti/Exploration-of-DQN-in-CartPole-Environment","url":"https://github.com/Codernauti/Exploration-of-DQN-in-CartPole-Environment"},{"title":"JustinStitt/acrobotDDQN","url":"https://github.com/JustinStitt/acrobotDDQN"},{"title":"shashwatsaxena571/DRL-navigation","url":"https://github.com/shashwatsaxena571/DRL-navigation"},{"title":"jezzarax/drlnd_p1_navigation","url":"https://github.com/jezzarax/drlnd_p1_navigation"},{"title":"zhengant/dqn_reversi","url":"https://github.com/zhengant/dqn_reversi"},{"title":"nbopardi/smb","url":"https://github.com/nbopardi/smb"},{"title":"ZainRaza14/deepRL","url":"https://github.com/ZainRaza14/deepRL"},{"title":"guillaumeboniface/bananaland","url":"https://github.com/guillaumeboniface/bananaland"},{"title":"daviddcho/supermario","url":"https://github.com/daviddcho/supermario"},{"title":"austinsilveria/Banana-Collection-DQN","url":"https://github.com/austinsilveria/Banana-Collection-DQN"},{"title":"mightypirate1/DRL-Tetris","url":"https://github.com/mightypirate1/DRL-Tetris"},{"title":"seacevedo/ReinforcementLearningProjects","url":"https://github.com/seacevedo/ReinforcementLearningProjects"},{"title":"JonasRSV/DQNTensorflow","url":"https://github.com/JonasRSV/DQNTensorflow"},{"title":"ssainz/reinforcement_learning_algorithms","url":"https://github.com/ssainz/reinforcement_learning_algorithms"},{"title":"MOVzeroOne/DQN","url":"https://github.com/MOVzeroOne/DQN"},{"title":"tkcoding/DeepRL","url":"https://github.com/tkcoding/DeepRL"},{"title":"JonasRSV/DQN","url":"https://github.com/JonasRSV/DQN"}],"metrics_order":"[\"Score\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]}]}