{"url":"/sota/atari-games-on-atari-2600-qbert","task":{"name":"Atari Games","url":"/task/atari-games","note":null},"dataset":{"name":"Atari 2600 Q*Bert","url":"/dataset/arcade-learning-environment"},"category":"Playing Games","categories":["Playing Games"],"category_note":null,"description":"The Atari 2600 Games task (and dataset) involves training an agent to achieve high game scores.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Playing Atari with Deep Reinforcement Learning](https://arxiv.org/pdf/1312.5602v1.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Score","Best Score","Return"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Score":"higher","Best Score":"higher","Return":null}},"counts":{"rows":57,"rows_with_code":50,"rows_with_paper_page":56,"rows_dated":56,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Agent57","metrics":{"Score":"580328.14"},"uses_additional_data":false,"paper_date":"2020-03-30","paper":"/paper/agent57-outperforming-the-atari-human","paper_url":"https://arxiv.org/abs/2003.13350v1","paper_title":"Agent57: Outperforming the Atari Human Benchmark","code":"https://github.com/michaelnny/deep_rl_zoo","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":9,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"QR-DQN-1","metrics":{"Score":"572510"},"uses_additional_data":false,"paper_date":"2017-10-27","paper":"/paper/distributional-reinforcement-learning-with-1","paper_url":"http://arxiv.org/abs/1710.10044v1","paper_title":"Distributional Reinforcement Learning with Quantile Regression","code":"https://github.com/DLR-RM/stable-baselines3","n_code_links":17,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":3,"model":"R2D2","metrics":{"Score":"408850.0"},"uses_additional_data":false,"paper_date":"2019-05-01","paper":"/paper/recurrent-experience-replay-in-distributed","paper_url":"https://openreview.net/forum?id=r1lyTjAqYX","paper_title":"Recurrent Experience Replay in Distributed Reinforcement Learning","code":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/r2d2.py","n_code_links":3,"syntology":null},{"rank_in_archive_order":4,"model":"IMPALA (deep)","metrics":{"Score":"351200.12"},"uses_additional_data":false,"paper_date":"2018-02-05","paper":"/paper/impala-scalable-distributed-deep-rl-with","paper_url":"http://arxiv.org/abs/1802.01561v3","paper_title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","code":"https://github.com/ray-project/ray/tree/master/rllib","n_code_links":24,"syntology":{"n_ran":16,"n_unverified":18,"n_samples":34,"n_pointer_only_licence":3}},{"rank_in_archive_order":5,"model":"Ape-X","metrics":{"Score":"302391.3"},"uses_additional_data":false,"paper_date":"2018-03-02","paper":"/paper/distributed-prioritized-experience-replay","paper_url":"http://arxiv.org/abs/1803.00933v1","paper_title":"Distributed Prioritized Experience Replay","code":"https://github.com/ray-project/ray/tree/master/rllib","n_code_links":15,"syntology":{"n_ran":0,"n_unverified":15,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"A2C + SIL","metrics":{"Score":"104975.6"},"uses_additional_data":false,"paper_date":"2018-06-14","paper":"/paper/self-imitation-learning","paper_url":"http://arxiv.org/abs/1806.05635v1","paper_title":"Self-Imitation Learning","code":"https://github.com/junhyukoh/self-imitation-learning","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":3}},{"rank_in_archive_order":7,"model":"MuZero (Res2 Adam)","metrics":{"Score":"94906.25"},"uses_additional_data":false,"paper_date":"2021-04-13","paper":"/paper/online-and-offline-reinforcement-learning-by","paper_url":"https://arxiv.org/abs/2104.06294v1","paper_title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","code":"https://github.com/DHDev0/Muzero-unplugged","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"DreamerV2","metrics":{"Score":"94688"},"uses_additional_data":false,"paper_date":"2020-10-05","paper":"/paper/mastering-atari-with-discrete-world-models-1","paper_url":"https://arxiv.org/abs/2010.02193v4","paper_title":"Mastering Atari with Discrete World Models","code":"https://github.com/opendilab/DI-engine","n_code_links":9,"syntology":{"n_ran":3,"n_unverified":12,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"MuZero","metrics":{"Score":"72276.00"},"uses_additional_data":false,"paper_date":"2019-11-19","paper":"/paper/mastering-atari-go-chess-and-shogi-by","paper_url":"https://arxiv.org/abs/1911.08265v2","paper_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","code":"https://github.com/werner-duvaud/muzero-general","n_code_links":18,"syntology":{"n_ran":43,"n_unverified":21,"n_samples":64,"n_pointer_only_licence":62}},{"rank_in_archive_order":10,"model":"DNA","metrics":{"Score":"52398"},"uses_additional_data":false,"paper_date":"2022-06-20","paper":"/paper/dna-proximal-policy-optimization-with-a-dual","paper_url":"https://arxiv.org/abs/2206.10027v2","paper_title":"DNA: Proximal Policy Optimization with a Dual Network Architecture","code":"https://github.com/maitchison/PPO","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"GDI-H3(200M frames)","metrics":{"Score":"28657"},"uses_additional_data":false,"paper_date":"2022-06-07","paper":"/paper/generalized-data-distribution-iteration","paper_url":"https://arxiv.org/abs/2206.03192v4","paper_title":"Generalized Data Distribution Iteration","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"GDI-H3","metrics":{"Score":"28657"},"uses_additional_data":false,"paper_date":"2022-06-07","paper":"/paper/generalized-data-distribution-iteration","paper_url":"https://arxiv.org/abs/2206.03192v4","paper_title":"Generalized Data Distribution Iteration","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"GDI-I3","metrics":{"Score":"27800"},"uses_additional_data":false,"paper_date":"2022-06-07","paper":"/paper/generalized-data-distribution-iteration","paper_url":"https://arxiv.org/abs/2206.03192v4","paper_title":"Generalized Data Distribution Iteration","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"GDI-I3","metrics":{"Score":"27800"},"uses_additional_data":false,"paper_date":"2021-06-11","paper":"/paper/gdi-rethinking-what-makes-reinforcement","paper_url":"https://arxiv.org/abs/2106.06232v6","paper_title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"NoisyNet-Dueling","metrics":{"Score":"27121"},"uses_additional_data":false,"paper_date":"2017-06-30","paper":"/paper/noisy-networks-for-exploration","paper_url":"https://arxiv.org/abs/1706.10295v3","paper_title":"Noisy Networks for Exploration","code":"https://github.com/opendilab/DI-engine","n_code_links":15,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":16,"model":"IQN","metrics":{"Score":"25750"},"uses_additional_data":false,"paper_date":"2018-06-14","paper":"/paper/implicit-quantile-networks-for-distributional","paper_url":"http://arxiv.org/abs/1806.06923v1","paper_title":"Implicit Quantile Networks for Distributional Reinforcement Learning","code":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/iqn.py","n_code_links":19,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"ASL DDQN","metrics":{"Score":"24548.8"},"uses_additional_data":false,"paper_date":"2023-05-07","paper":"/paper/train-a-real-world-local-path-planner-in-one","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","code":"https://github.com/xinjinghao/color","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"C51 noop","metrics":{"Score":"23784"},"uses_additional_data":false,"paper_date":"2017-07-21","paper":"/paper/a-distributional-perspective-on-reinforcement","paper_url":"http://arxiv.org/abs/1707.06887v1","paper_title":"A Distributional Perspective on Reinforcement Learning","code":"https://github.com/facebookresearch/Horizon","n_code_links":22,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":19,"model":"A3C LSTM hs","metrics":{"Score":"21307.5"},"uses_additional_data":false,"paper_date":"2016-02-04","paper":"/paper/asynchronous-methods-for-deep-reinforcement","paper_url":"http://arxiv.org/abs/1602.01783v2","paper_title":"Asynchronous Methods for Deep Reinforcement Learning","code":"https://github.com/ray-project/ray/tree/master/rllib","n_code_links":70,"syntology":{"n_ran":38,"n_unverified":57,"n_samples":95,"n_pointer_only_licence":12}},{"rank_in_archive_order":20,"model":"Duel noop","metrics":{"Score":"19220.3"},"uses_additional_data":false,"paper_date":"2015-11-20","paper":"/paper/dueling-network-architectures-for-deep","paper_url":"http://arxiv.org/abs/1511.06581v3","paper_title":"Dueling Network Architectures for Deep Reinforcement Learning","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":73,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":6}},{"rank_in_archive_order":21,"model":"Prior+Duel noop","metrics":{"Score":"18760.3"},"uses_additional_data":false,"paper_date":"2015-11-20","paper":"/paper/dueling-network-architectures-for-deep","paper_url":"http://arxiv.org/abs/1511.06581v3","paper_title":"Dueling Network Architectures for Deep Reinforcement Learning","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":73,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":6}},{"rank_in_archive_order":22,"model":"UCT","metrics":{"Score":"17343.4"},"uses_additional_data":false,"paper_date":"2012-07-19","paper":"/paper/the-arcade-learning-environment-an-evaluation","paper_url":"http://arxiv.org/abs/1207.4708v2","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","code":"https://github.com/mgbellemare/Arcade-Learning-Environment","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":23,"model":"Prior noop","metrics":{"Score":"16256.5"},"uses_additional_data":false,"paper_date":"2015-11-18","paper":"/paper/prioritized-experience-replay","paper_url":"http://arxiv.org/abs/1511.05952v4","paper_title":"Prioritized Experience Replay","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":77,"syntology":{"n_ran":78,"n_unverified":33,"n_samples":111,"n_pointer_only_licence":43}},{"rank_in_archive_order":24,"model":"MP-EB","metrics":{"Score":"15805"},"uses_additional_data":false,"paper_date":"2015-07-03","paper":"/paper/incentivizing-exploration-in-reinforcement","paper_url":"http://arxiv.org/abs/1507.00814v3","paper_title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","code":"https://github.com/CoffeeddCat/Multiagent_chainMDP","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"POP3D","metrics":{"Score":"15396.67"},"uses_additional_data":false,"paper_date":"2018-07-02","paper":"/paper/policy-optimization-with-penalized-point","paper_url":"http://arxiv.org/abs/1807.00442v4","paper_title":"Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization","code":"https://github.com/cxxgtxy/POP3D","n_code_links":2,"syntology":null},{"rank_in_archive_order":26,"model":"A3C FF hs","metrics":{"Score":"15148.8"},"uses_additional_data":false,"paper_date":"2016-02-04","paper":"/paper/asynchronous-methods-for-deep-reinforcement","paper_url":"http://arxiv.org/abs/1602.01783v2","paper_title":"Asynchronous Methods for Deep Reinforcement Learning","code":"https://github.com/ray-project/ray/tree/master/rllib","n_code_links":70,"syntology":{"n_ran":38,"n_unverified":57,"n_samples":95,"n_pointer_only_licence":12}},{"rank_in_archive_order":27,"model":"Bootstrapped DQN","metrics":{"Score":"15092.7"},"uses_additional_data":false,"paper_date":"2016-02-15","paper":"/paper/deep-exploration-via-bootstrapped-dqn","paper_url":"http://arxiv.org/abs/1602.04621v3","paper_title":"Deep Exploration via Bootstrapped DQN","code":"https://github.com/tensorflow/models","n_code_links":6,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":28,"model":"DDQN (tuned) noop","metrics":{"Score":"15088.5"},"uses_additional_data":false,"paper_date":"2015-11-20","paper":"/paper/dueling-network-architectures-for-deep","paper_url":"http://arxiv.org/abs/1511.06581v3","paper_title":"Dueling Network Architectures for Deep Reinforcement Learning","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":73,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":6}},{"rank_in_archive_order":29,"model":"VPN","metrics":{"Score":"14517"},"uses_additional_data":false,"paper_date":"2017-07-11","paper":"/paper/value-prediction-network","paper_url":"http://arxiv.org/abs/1707.03497v2","paper_title":"Value Prediction Network","code":"https://github.com/junhyukoh/value-prediction-network","n_code_links":2,"syntology":null},{"rank_in_archive_order":30,"model":"Rational DQN Average","metrics":{"Score":"14436"},"uses_additional_data":false,"paper_date":"2021-02-18","paper":"/paper/recurrent-rational-networks","paper_url":"https://arxiv.org/abs/2102.09407v5","paper_title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","code":"https://github.com/ml-research/rational_activations","n_code_links":4,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":3}},{"rank_in_archive_order":31,"model":"Advantage Learning","metrics":{"Score":"14368.03"},"uses_additional_data":false,"paper_date":"2015-12-15","paper":"/paper/increasing-the-action-gap-new-operators-for","paper_url":"http://arxiv.org/abs/1512.04860v1","paper_title":"Increasing the Action Gap: New Operators for Reinforcement Learning","code":"https://github.com/janhuenermann/neurojs","n_code_links":2,"syntology":null},{"rank_in_archive_order":32,"model":"Duel hs","metrics":{"Score":"14175.8"},"uses_additional_data":false,"paper_date":"2015-11-20","paper":"/paper/dueling-network-architectures-for-deep","paper_url":"http://arxiv.org/abs/1511.06581v3","paper_title":"Dueling Network Architectures for Deep Reinforcement Learning","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":73,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":6}},{"rank_in_archive_order":33,"model":"MFEC","metrics":{"Best Score":"19750","Score":"14135"},"uses_additional_data":false,"paper_date":"2020-08-21","paper":"/paper/model-free-episodic-control-with-state","paper_url":"https://arxiv.org/abs/2008.09685v1","paper_title":"Model-Free Episodic Control with State Aggregation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":34,"model":"Recurrent Rational DQN Average","metrics":{"Score":"14080"},"uses_additional_data":false,"paper_date":"2021-02-18","paper":"/paper/recurrent-rational-networks","paper_url":"https://arxiv.org/abs/2102.09407v5","paper_title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","code":"https://github.com/ml-research/rational_activations","n_code_links":4,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":3}},{"rank_in_archive_order":35,"model":"Prior+Duel hs","metrics":{"Score":"14063.0"},"uses_additional_data":false,"paper_date":"2015-09-22","paper":"/paper/deep-reinforcement-learning-with-double-q","paper_url":"http://arxiv.org/abs/1509.06461v3","paper_title":"Deep Reinforcement Learning with Double Q-learning","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":97,"syntology":{"n_ran":55,"n_unverified":51,"n_samples":106,"n_pointer_only_licence":57}},{"rank_in_archive_order":36,"model":"A3C FF (1 day) hs","metrics":{"Score":"13752.3"},"uses_additional_data":false,"paper_date":"2016-02-04","paper":"/paper/asynchronous-methods-for-deep-reinforcement","paper_url":"http://arxiv.org/abs/1602.01783v2","paper_title":"Asynchronous Methods for Deep Reinforcement Learning","code":"https://github.com/ray-project/ray/tree/master/rllib","n_code_links":70,"syntology":{"n_ran":38,"n_unverified":57,"n_samples":95,"n_pointer_only_licence":12}},{"rank_in_archive_order":37,"model":"DQN noop","metrics":{"Score":"13117.3"},"uses_additional_data":false,"paper_date":"2015-09-22","paper":"/paper/deep-reinforcement-learning-with-double-q","paper_url":"http://arxiv.org/abs/1509.06461v3","paper_title":"Deep Reinforcement Learning with Double Q-learning","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":97,"syntology":{"n_ran":55,"n_unverified":51,"n_samples":106,"n_pointer_only_licence":57}},{"rank_in_archive_order":38,"model":"DDQN (tuned) hs","metrics":{"Score":"11020.8"},"uses_additional_data":false,"paper_date":"2015-09-22","paper":"/paper/deep-reinforcement-learning-with-double-q","paper_url":"http://arxiv.org/abs/1509.06461v3","paper_title":"Deep Reinforcement Learning with Double Q-learning","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":97,"syntology":{"n_ran":55,"n_unverified":51,"n_samples":106,"n_pointer_only_licence":57}},{"rank_in_archive_order":39,"model":"Nature DQN","metrics":{"Score":"10596"},"uses_additional_data":false,"paper_date":"2015-02-25","paper":"/paper/human-level-control-through-deep","paper_url":"https://www.nature.com/articles/nature14236","paper_title":"Human level control through deep reinforcement learning","code":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Deep_Reinforcement_Learning_with_Double_Q_learning","n_code_links":8,"syntology":null},{"rank_in_archive_order":40,"model":"Prior hs","metrics":{"Score":"9944"},"uses_additional_data":false,"paper_date":"2015-11-18","paper":"/paper/prioritized-experience-replay","paper_url":"http://arxiv.org/abs/1511.05952v4","paper_title":"Prioritized Experience Replay","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":77,"syntology":{"n_ran":78,"n_unverified":33,"n_samples":111,"n_pointer_only_licence":43}},{"rank_in_archive_order":41,"model":"DQN hs","metrics":{"Score":"9271.5"},"uses_additional_data":false,"paper_date":"2015-09-22","paper":"/paper/deep-reinforcement-learning-with-double-q","paper_url":"http://arxiv.org/abs/1509.06461v3","paper_title":"Deep Reinforcement Learning with Double Q-learning","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":97,"syntology":{"n_ran":55,"n_unverified":51,"n_samples":106,"n_pointer_only_licence":57}},{"rank_in_archive_order":42,"model":"Gorila","metrics":{"Score":"7089.8"},"uses_additional_data":false,"paper_date":"2015-07-15","paper":"/paper/massively-parallel-methods-for-deep","paper_url":"http://arxiv.org/abs/1507.04296v2","paper_title":"Massively Parallel Methods for Deep Reinforcement Learning","code":"https://github.com/nandomp/AICollaboratory","n_code_links":3,"syntology":null},{"rank_in_archive_order":43,"model":"DDQN+Pop-Art noop","metrics":{"Score":"5236.8"},"uses_additional_data":false,"paper_date":"2016-02-24","paper":"/paper/learning-values-across-many-orders-of","paper_url":"http://arxiv.org/abs/1602.07714v2","paper_title":"Learning values across many orders of magnitude","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":44,"model":"DQN Best","metrics":{"Score":"4500"},"uses_additional_data":false,"paper_date":"2013-12-19","paper":"/paper/playing-atari-with-deep-reinforcement","paper_url":"http://arxiv.org/abs/1312.5602v1","paper_title":"Playing Atari with Deep Reinforcement Learning","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":112,"syntology":{"n_ran":56,"n_unverified":61,"n_samples":117,"n_pointer_only_licence":56}},{"rank_in_archive_order":45,"model":"Qbert Rainbow+SEER","metrics":{"Score":"4123.5"},"uses_additional_data":false,"paper_date":"2021-03-04","paper":"/paper/improving-computational-efficiency-in-visual","paper_url":"https://arxiv.org/abs/2103.02886v2","paper_title":"Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings","code":"https://github.com/lili-chen/SEER","n_code_links":1,"syntology":null},{"rank_in_archive_order":46,"model":"Sarsa-φ-EB","metrics":{"Score":"4111.8"},"uses_additional_data":false,"paper_date":"2017-06-25","paper":"/paper/count-based-exploration-in-feature-space-for","paper_url":"http://arxiv.org/abs/1706.08090v1","paper_title":"Count-Based Exploration in Feature Space for Reinforcement Learning","code":"https://github.com/aslanides/aixijs","n_code_links":1,"syntology":null},{"rank_in_archive_order":47,"model":"Sarsa-ε","metrics":{"Score":"3895.3"},"uses_additional_data":false,"paper_date":"2017-06-25","paper":"/paper/count-based-exploration-in-feature-space-for","paper_url":"http://arxiv.org/abs/1706.08090v1","paper_title":"Count-Based Exploration in Feature Space for Reinforcement Learning","code":"https://github.com/aslanides/aixijs","n_code_links":1,"syntology":null},{"rank_in_archive_order":48,"model":"IDVQ + DRSC + XNES","metrics":{"Score":"1250"},"uses_additional_data":false,"paper_date":"2018-06-04","paper":"/paper/playing-atari-with-six-neurons","paper_url":"http://arxiv.org/abs/1806.01363v2","paper_title":"Playing Atari with Six Neurons","code":"https://github.com/giuse/DNE","n_code_links":1,"syntology":null},{"rank_in_archive_order":49,"model":"CURL","metrics":{"Score":"1225.6"},"uses_additional_data":false,"paper_date":"2020-04-08","paper":"/paper/curl-contrastive-unsupervised-representations","paper_url":"https://arxiv.org/abs/2004.04136v4","paper_title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","code":"https://github.com/opendilab/DI-engine","n_code_links":7,"syntology":{"n_ran":6,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":50,"model":"SARSA","metrics":{"Score":"960.3"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":51,"model":"CGP","metrics":{"Score":"770"},"uses_additional_data":false,"paper_date":"2018-06-14","paper":"/paper/evolving-simple-programs-for-playing-atari","paper_url":"http://arxiv.org/abs/1806.05695v1","paper_title":"Evolving simple programs for playing Atari games","code":"https://github.com/ShuhuaGao/gpFlappyBird","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":9,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":52,"model":"Best Learner","metrics":{"Score":"613.5"},"uses_additional_data":false,"paper_date":"2012-07-19","paper":"/paper/the-arcade-learning-environment-an-evaluation","paper_url":"http://arxiv.org/abs/1207.4708v2","paper_title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","code":"https://github.com/mgbellemare/Arcade-Learning-Environment","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":53,"model":"SAC","metrics":{"Score":"280.5"},"uses_additional_data":false,"paper_date":"2019-10-16","paper":"/paper/soft-actor-critic-for-discrete-action","paper_url":"https://arxiv.org/abs/1910.07207v2","paper_title":"Soft Actor-Critic for Discrete Action Settings","code":"https://github.com/p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch","n_code_links":13,"syntology":{"n_ran":4,"n_unverified":14,"n_samples":18,"n_pointer_only_licence":3}},{"rank_in_archive_order":54,"model":"MAC","metrics":{"Score":"243.4"},"uses_additional_data":false,"paper_date":"2017-09-01","paper":"/paper/mean-actor-critic","paper_url":"http://arxiv.org/abs/1709.00503v2","paper_title":"Mean Actor Critic","code":"https://github.com/kavosh8/MAC","n_code_links":2,"syntology":null},{"rank_in_archive_order":55,"model":"ES FF (1 hour) noop","metrics":{"Score":"147.5"},"uses_additional_data":false,"paper_date":"2017-03-10","paper":"/paper/evolution-strategies-as-a-scalable","paper_url":"http://arxiv.org/abs/1703.03864v2","paper_title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","code":"https://github.com/ray-project/ray/tree/master/rllib","n_code_links":23,"syntology":{"n_ran":7,"n_unverified":22,"n_samples":29,"n_pointer_only_licence":1}},{"rank_in_archive_order":56,"model":"DT","metrics":{"Score":"25.1"},"uses_additional_data":false,"paper_date":"2021-06-02","paper":"/paper/decision-transformer-reinforcement-learning","paper_url":"https://arxiv.org/abs/2106.01345v2","paper_title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","code":"https://github.com/opendilab/DI-engine","n_code_links":20,"syntology":{"n_ran":17,"n_unverified":9,"n_samples":26,"n_pointer_only_licence":6}},{"rank_in_archive_order":57,"model":"IQ-Learn","metrics":{"Return":"12940"},"uses_additional_data":false,"paper_date":"2021-06-23","paper":"/paper/iq-learn-inverse-soft-q-learning-for","paper_url":"https://arxiv.org/abs/2106.12142v4","paper_title":"IQ-Learn: Inverse soft-Q Learning for Imitation","code":"https://github.com/Div99/IQ-Learn","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":35,"rows_with_any_sample_ran":30,"distinct_papers_with_graph_line":24,"distinct_papers_with_any_sample_ran":19,"samples_over_distinct_papers":{"n_ran":343,"n_unverified":351,"n_samples":694,"n_pointer_only_licence":267,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":685,"n_unverified":669,"n_samples":1354,"n_pointer_only_licence":528,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}