{"url":"/sota/atari-games-on-atari-2600-venture","task":{"name":"Atari Games","url":"/task/atari-games","note":null},"dataset":{"name":"Atari 2600 Venture","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"],"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"}},"counts":{"rows":55,"rows_with_code":50,"rows_with_paper_page":54,"rows_dated":54,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Agent57","metrics":{"Score":"2623.71"},"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":"Go-Explore","metrics":{"Score":"2281"},"uses_additional_data":false,"paper_date":"2020-04-27","paper":"/paper/first-return-then-explore","paper_url":"https://arxiv.org/abs/2004.12919v6","paper_title":"First return, then explore","code":"https://github.com/uber-research/go-explore","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":3,"model":"SND-VIC","metrics":{"Score":"2188"},"uses_additional_data":false,"paper_date":"2023-02-22","paper":"/paper/exploration-by-self-supervised-exploitation","paper_url":"https://arxiv.org/abs/2302.11563v4","paper_title":"Self-supervised network distillation: an effective approach to exploration in sparse reward environments","code":"https://github.com/iskandor/snd","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"SND-STD","metrics":{"Score":"2138"},"uses_additional_data":false,"paper_date":"2023-02-22","paper":"/paper/exploration-by-self-supervised-exploitation","paper_url":"https://arxiv.org/abs/2302.11563v4","paper_title":"Self-supervised network distillation: an effective approach to exploration in sparse reward environments","code":"https://github.com/iskandor/snd","n_code_links":2,"syntology":null},{"rank_in_archive_order":5,"model":"GDI-I3","metrics":{"Score":"2035"},"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":6,"model":"GDI-H3(200M frames)","metrics":{"Score":"2000"},"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":7,"model":"GDI-H3","metrics":{"Score":"2000"},"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":8,"model":"R2D2","metrics":{"Score":"1970.7"},"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":9,"model":"RND","metrics":{"Score":"1859"},"uses_additional_data":false,"paper_date":"2018-10-30","paper":"/paper/exploration-by-random-network-distillation","paper_url":"http://arxiv.org/abs/1810.12894v1","paper_title":"Exploration by Random Network Distillation","code":"https://github.com/opendilab/DI-engine/blob/main/ding/reward_model/rnd_reward_model.py","n_code_links":22,"syntology":{"n_ran":26,"n_unverified":17,"n_samples":43,"n_pointer_only_licence":15}},{"rank_in_archive_order":10,"model":"Ape-X","metrics":{"Score":"1813"},"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":11,"model":"SND-V","metrics":{"Score":"1787"},"uses_additional_data":false,"paper_date":"2023-02-22","paper":"/paper/exploration-by-self-supervised-exploitation","paper_url":"https://arxiv.org/abs/2302.11563v4","paper_title":"Self-supervised network distillation: an effective approach to exploration in sparse reward environments","code":"https://github.com/iskandor/snd","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"MuZero (Res2 Adam)","metrics":{"Score":"1731.47"},"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":13,"model":"C51 noop","metrics":{"Score":"1520.0"},"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":14,"model":"RUDDER","metrics":{"Score":"1350"},"uses_additional_data":false,"paper_date":"2018-06-20","paper":"/paper/rudder-return-decomposition-for-delayed","paper_url":"https://arxiv.org/abs/1806.07857v3","paper_title":"RUDDER: Return Decomposition for Delayed Rewards","code":"https://github.com/ml-jku/baselines-rudder","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":9}},{"rank_in_archive_order":15,"model":"IQN","metrics":{"Score":"1318"},"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":16,"model":"DQNMMCe+SR","metrics":{"Score":"1241.8"},"uses_additional_data":false,"paper_date":"2018-07-31","paper":"/paper/count-based-exploration-with-the-successor","paper_url":"https://arxiv.org/abs/1807.11622v4","paper_title":"Count-Based Exploration with the Successor Representation","code":"https://github.com/mcmachado/count_based_exploration_sr","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"DDQN+Pop-Art noop","metrics":{"Score":"1172.0"},"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":18,"model":"Sarsa-φ-EB","metrics":{"Score":"1169.2"},"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":19,"model":"NoisyNet-Dueling","metrics":{"Score":"815"},"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":20,"model":"ES FF (1 hour) noop","metrics":{"Score":"760.0"},"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":21,"model":"Gorila","metrics":{"Score":"523.4"},"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":22,"model":"Duel noop","metrics":{"Score":"497.0"},"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":23,"model":"TRPO-hash","metrics":{"Score":"445.0"},"uses_additional_data":false,"paper_date":"2016-11-15","paper":"/paper/exploration-a-study-of-count-based","paper_url":"http://arxiv.org/abs/1611.04717v3","paper_title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","code":"https://github.com/uoe-agents/derl","n_code_links":3,"syntology":null},{"rank_in_archive_order":24,"model":"Intrinsic Reward Agent","metrics":{"Score":"416"},"uses_additional_data":false,"paper_date":"2018-08-13","paper":"/paper/large-scale-study-of-curiosity-driven","paper_url":"http://arxiv.org/abs/1808.04355v1","paper_title":"Large-Scale Study of Curiosity-Driven Learning","code":"https://github.com/openai/large-scale-curiosity","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":25,"model":"Nature DQN","metrics":{"Score":"380.0"},"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":26,"model":"ASL DDQN","metrics":{"Score":"291"},"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":27,"model":"Bootstrapped DQN","metrics":{"Score":"212.5"},"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":"Duel hs","metrics":{"Score":"200.0"},"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":"Advantage Learning","metrics":{"Score":"198.69"},"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":30,"model":"DQN noop","metrics":{"Score":"163.0"},"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":31,"model":"DQN hs","metrics":{"Score":"136.0"},"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":32,"model":"DDQN (tuned) noop","metrics":{"Score":"98.0"},"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":"Prior hs","metrics":{"Score":"94.0"},"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":34,"model":"DQN-PixelCNN","metrics":{"Score":"82.2"},"uses_additional_data":false,"paper_date":"2017-03-03","paper":"/paper/count-based-exploration-with-neural-density","paper_url":"http://arxiv.org/abs/1703.01310v2","paper_title":"Count-Based Exploration with Neural Density Models","code":"https://github.com/nolisten/erl","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"Best Learner","metrics":{"Score":"66"},"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":36,"model":"Prior noop","metrics":{"Score":"54.0"},"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":37,"model":"Prior+Duel noop","metrics":{"Score":"48.0"},"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":38,"model":"DQN-CTS","metrics":{"Score":"48.0"},"uses_additional_data":false,"paper_date":"2017-03-03","paper":"/paper/count-based-exploration-with-neural-density","paper_url":"http://arxiv.org/abs/1703.01310v2","paper_title":"Count-Based Exploration with Neural Density Models","code":"https://github.com/nolisten/erl","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":39,"model":"QR-DQN-1","metrics":{"Score":"43.9"},"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":40,"model":"POP3D","metrics":{"Score":"36.33"},"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":41,"model":"Prior+Duel hs","metrics":{"Score":"29.0"},"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":42,"model":"A3C LSTM hs","metrics":{"Score":"25.0"},"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":43,"model":"A3C FF hs","metrics":{"Score":"23.0"},"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":44,"model":"DDQN (tuned) hs","metrics":{"Score":"21.0"},"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":45,"model":"A3C FF (1 day) hs","metrics":{"Score":"19.0"},"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":46,"model":"DreamerV2","metrics":{"Score":"2"},"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":47,"model":"SARSA","metrics":{"Score":"0.6"},"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":48,"model":"MuZero","metrics":{"Score":"0.40"},"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":49,"model":"MP-EB","metrics":{"Score":"0.0"},"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":50,"model":"A3C-CTS","metrics":{"Score":"0.0"},"uses_additional_data":false,"paper_date":"2016-06-06","paper":"/paper/unifying-count-based-exploration-and","paper_url":"http://arxiv.org/abs/1606.01868v2","paper_title":"Unifying Count-Based Exploration and Intrinsic Motivation","code":"https://github.com/RLAgent/state-marginal-matching","n_code_links":1,"syntology":null},{"rank_in_archive_order":51,"model":"Sarsa-ε","metrics":{"Score":"0.0"},"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":52,"model":"IMPALA (deep)","metrics":{"Score":"0.00"},"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":53,"model":"A2C + SIL","metrics":{"Score":"0"},"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":54,"model":"CGP","metrics":{"Score":"0"},"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":55,"model":"DNA","metrics":{"Score":"0"},"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}],"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":34,"rows_with_any_sample_ran":28,"distinct_papers_with_graph_line":24,"distinct_papers_with_any_sample_ran":18,"samples_over_distinct_papers":{"n_ran":287,"n_unverified":291,"n_samples":578,"n_pointer_only_licence":227,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":622,"n_unverified":609,"n_samples":1231,"n_pointer_only_licence":483,"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"}}}