{"url":"/task/general-reinforcement-learning","name":"General Reinforcement Learning","slug":"general-reinforcement-learning","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Playing Games","url":"/area/playing-games"},{"name":"Reasoning","url":"/area/reasoning"},{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":84,"papers_with_code":40,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":2,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/general-reinforcement-learning-on-obstacle","slug":"general-reinforcement-learning-on-obstacle","dataset":"Obstacle Tower (No Gen) fixed","dataset_url":"/dataset/obstacle-tower","rows_in_archive":2,"metrics":["Score"],"first_row_in_archive_order":{"model":"RNB","paper_title":"Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning","paper_url":"/paper/obstacle-tower-a-generalization-challenge-in","paper_date":"2019-02-04","arxiv_id":"1902.01378","code_links":[{"title":"Unity-Technologies/obstacle-tower-env","url":"https://github.com/Unity-Technologies/obstacle-tower-env"},{"title":"odokumaci/rainbow-unity-obstacle-tower-challenge","url":"https://github.com/odokumaci/rainbow-unity-obstacle-tower-challenge"},{"title":"dazcona/obstacletower","url":"https://github.com/dazcona/obstacletower"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/general-reinforcement-learning-on-obstacle-1","slug":"general-reinforcement-learning-on-obstacle-1","dataset":"Obstacle Tower (No Gen) varied","dataset_url":"/dataset/obstacle-tower","rows_in_archive":2,"metrics":["Score"],"first_row_in_archive_order":{"model":"RNB","paper_title":"Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning","paper_url":"/paper/obstacle-tower-a-generalization-challenge-in","paper_date":"2019-02-04","arxiv_id":"1902.01378","code_links":[{"title":"Unity-Technologies/obstacle-tower-env","url":"https://github.com/Unity-Technologies/obstacle-tower-env"},{"title":"odokumaci/rainbow-unity-obstacle-tower-challenge","url":"https://github.com/odokumaci/rainbow-unity-obstacle-tower-challenge"},{"title":"dazcona/obstacletower","url":"https://github.com/dazcona/obstacletower"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/general-reinforcement-learning-on-obstacle-2","slug":"general-reinforcement-learning-on-obstacle-2","dataset":"Obstacle Tower (Weak Gen) fixed","dataset_url":"/dataset/obstacle-tower","rows_in_archive":2,"metrics":["Score"],"first_row_in_archive_order":{"model":"PPO","paper_title":"Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning","paper_url":"/paper/obstacle-tower-a-generalization-challenge-in","paper_date":"2019-02-04","arxiv_id":"1902.01378","code_links":[{"title":"Unity-Technologies/obstacle-tower-env","url":"https://github.com/Unity-Technologies/obstacle-tower-env"},{"title":"odokumaci/rainbow-unity-obstacle-tower-challenge","url":"https://github.com/odokumaci/rainbow-unity-obstacle-tower-challenge"},{"title":"dazcona/obstacletower","url":"https://github.com/dazcona/obstacletower"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/general-reinforcement-learning-on-obstacle-3","slug":"general-reinforcement-learning-on-obstacle-3","dataset":"Obstacle Tower (Weak Gen) varied","dataset_url":"/dataset/obstacle-tower","rows_in_archive":2,"metrics":["Score"],"first_row_in_archive_order":{"model":"RNB","paper_title":"Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning","paper_url":"/paper/obstacle-tower-a-generalization-challenge-in","paper_date":"2019-02-04","arxiv_id":"1902.01378","code_links":[{"title":"Unity-Technologies/obstacle-tower-env","url":"https://github.com/Unity-Technologies/obstacle-tower-env"},{"title":"odokumaci/rainbow-unity-obstacle-tower-challenge","url":"https://github.com/odokumaci/rainbow-unity-obstacle-tower-challenge"},{"title":"dazcona/obstacletower","url":"https://github.com/dazcona/obstacletower"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/general-reinforcement-learning-on-obstacle-4","slug":"general-reinforcement-learning-on-obstacle-4","dataset":"Obstacle Tower (Strong Gen) fixed","dataset_url":"/dataset/obstacle-tower","rows_in_archive":2,"metrics":["Score"],"first_row_in_archive_order":{"model":"PPO","paper_title":"Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning","paper_url":"/paper/obstacle-tower-a-generalization-challenge-in","paper_date":"2019-02-04","arxiv_id":"1902.01378","code_links":[{"title":"Unity-Technologies/obstacle-tower-env","url":"https://github.com/Unity-Technologies/obstacle-tower-env"},{"title":"odokumaci/rainbow-unity-obstacle-tower-challenge","url":"https://github.com/odokumaci/rainbow-unity-obstacle-tower-challenge"},{"title":"dazcona/obstacletower","url":"https://github.com/dazcona/obstacletower"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/general-reinforcement-learning-on-obstacle-5","slug":"general-reinforcement-learning-on-obstacle-5","dataset":"Obstacle Tower (Strong Gen) varied","dataset_url":"/dataset/obstacle-tower","rows_in_archive":2,"metrics":["Score"],"first_row_in_archive_order":{"model":"RNB","paper_title":"Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning","paper_url":"/paper/obstacle-tower-a-generalization-challenge-in","paper_date":"2019-02-04","arxiv_id":"1902.01378","code_links":[{"title":"Unity-Technologies/obstacle-tower-env","url":"https://github.com/Unity-Technologies/obstacle-tower-env"},{"title":"odokumaci/rainbow-unity-obstacle-tower-challenge","url":"https://github.com/odokumaci/rainbow-unity-obstacle-tower-challenge"},{"title":"dazcona/obstacletower","url":"https://github.com/dazcona/obstacletower"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/procgen","name":"ProcGen","full_name":"","num_papers_in_archive":177},{"url":"/dataset/obstacle-tower","name":"Obstacle Tower","full_name":"","num_papers_in_archive":20},{"url":"/dataset/avalon","name":"Avalon","full_name":"","num_papers_in_archive":5},{"url":"/dataset/packit","name":"PackIt","full_name":"","num_papers_in_archive":3},{"url":"/dataset/popgym","name":"POPGym","full_name":"Partially Observable Process Gym","num_papers_in_archive":3},{"url":"/dataset/wld","name":"WLD","full_name":"WildLife Documentary","num_papers_in_archive":3},{"url":"/dataset/bipedal-skills","name":"bipedal-skills","full_name":"Bipedal Skills Benchmark for Reinforcement Learning","num_papers_in_archive":2}],"subtasks":[{"url":"/task/model-based-reinforcement-learning","name":"Model-based Reinforcement Learning"},{"url":"/task/offline-rl","name":"Offline RL"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":40,"tagged_in_all":84,"items":[{"url":"/paper/mastering-chess-and-shogi-by-self-play-with-a","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","date":"2017-12-05","arxiv_id":"1712.01815","repositories_listed":62,"syntology":{"n":17,"n_ran":13,"n_unverified":4,"n_pointer_only":9}},{"url":"/paper/openspiel-a-framework-for-reinforcement","title":"OpenSpiel: A Framework for Reinforcement Learning in Games","date":"2019-08-26","arxiv_id":"1908.09453","repositories_listed":16,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/stabilizing-transformers-for-reinforcement-1","title":"Stabilizing Transformers for Reinforcement Learning","date":"2019-10-13","arxiv_id":"1910.06764","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/gibson-env-real-world-perception-for-embodied","title":"Gibson Env: Real-World Perception for Embodied Agents","date":"2018-08-31","arxiv_id":"1808.10654","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/action-branching-architectures-for-deep","title":"Action Branching Architectures for Deep Reinforcement Learning","date":"2017-11-24","arxiv_id":"1711.08946","repositories_listed":5,"syntology":null},{"url":"/paper/recurrent-rational-networks","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","date":"2021-02-18","arxiv_id":"2102.09407","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/sample-factory-egocentric-3d-control-from","title":"Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning","date":"2020-06-21","arxiv_id":"2006.11751","repositories_listed":4,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/remax-a-simple-effective-and-efficient-method","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","date":"2023-10-16","arxiv_id":"2310.10505","repositories_listed":3,"syntology":{"n":13,"n_ran":8,"n_unverified":5,"n_pointer_only":13}},{"url":"/paper/defix-detecting-and-fixing-failure-scenarios","title":"DeFIX: Detecting and Fixing Failure Scenarios with Reinforcement Learning in Imitation Learning Based Autonomous Driving","date":"2022-10-29","arxiv_id":"2210.16567","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-egospheric-spatial-memory","title":"End-to-End Egospheric Spatial Memory","date":"2021-02-15","arxiv_id":"2102.07764","repositories_listed":2,"syntology":null},{"url":"/paper/the-loca-regret-a-consistent-metric-to","title":"The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning","date":"2020-07-07","arxiv_id":"2007.03158","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/learning-to-incentivize-other-learning-agents","title":"Learning to Incentivize Other Learning Agents","date":"2020-06-10","arxiv_id":"2006.06051","repositories_listed":2,"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/190600572","title":"Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning","date":"2019-06-03","arxiv_id":"1906.00572","repositories_listed":2,"syntology":null},{"url":"/paper/learning-exploration-policies-for-navigation","title":"Learning Exploration Policies for Navigation","date":"2019-03-05","arxiv_id":"1903.01959","repositories_listed":2,"syntology":null},{"url":"/paper/a-monte-carlo-aixi-approximation","title":"A Monte Carlo AIXI Approximation","date":"2009-09-04","arxiv_id":"0909.0801","repositories_listed":2,"syntology":null},{"url":"/paper/nover-incentive-training-for-language-models","title":"NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning","date":"2025-05-21","arxiv_id":"2505.16022","repositories_listed":1,"syntology":null},{"url":"/paper/rec-r1-bridging-generative-large-language","title":"Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learning","date":"2025-03-31","arxiv_id":"2503.24289","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/hypercube-policy-regularization-framework-for","title":"Hypercube Policy Regularization Framework for Offline Reinforcement Learning","date":"2024-11-07","arxiv_id":"2411.04534","repositories_listed":1,"syntology":null},{"url":"/paper/kinetix-investigating-the-training-of-general","title":"Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks","date":"2024-10-30","arxiv_id":"2410.23208","repositories_listed":1,"syntology":{"n":33,"n_ran":24,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/discovering-general-reinforcement-learning-1","title":"Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design","date":"2023-10-04","arxiv_id":"2310.02782","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/learning-to-backdoor-federated-learning","title":"Learning to Backdoor Federated Learning","date":"2023-03-06","arxiv_id":"2303.03320","repositories_listed":1,"syntology":{"n":13,"n_ran":0,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/intelligent-resource-allocation-in-joint","title":"Intelligent Resource Allocation in Joint Radar-Communication With Graph Neural Networks","date":"2022-10-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-deformable-object-manipulation-from","title":"Learning Deformable Object Manipulation from Expert Demonstrations","date":"2022-07-20","arxiv_id":"2207.10148","repositories_listed":1,"syntology":null},{"url":"/paper/doubly-robust-estimation-for-unbiased","title":"Doubly-Robust Estimation for Correcting Position-Bias in Click Feedback for Unbiased Learning to Rank","date":"2022-03-31","arxiv_id":"2203.17118","repositories_listed":1,"syntology":null},{"url":"/paper/intelligent-trading-systems-a-sentiment-aware","title":"Intelligent Trading Systems: A Sentiment-Aware Reinforcement Learning Approach","date":"2021-11-14","arxiv_id":"2112.02095","repositories_listed":1,"syntology":null},{"url":"/paper/catastrophic-interference-in-reinforcement","title":"Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation","date":"2021-09-01","arxiv_id":"2109.00525","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/qksa-quantum-knowledge-seeking-agent","title":"QKSA: Quantum Knowledge Seeking Agent","date":"2021-07-03","arxiv_id":"2107.01429","repositories_listed":1,"syntology":null},{"url":"/paper/interactive-learning-from-activity","title":"Interactive Learning from Activity Description","date":"2021-02-13","arxiv_id":"2102.07024","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-represent-action-values-as-a-1","title":"Learning to Represent Action Values as a Hypergraph on the Action Vertices","date":"2020-10-28","arxiv_id":"2010.14680","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/align-rudder-learning-from-few-demonstrations","title":"Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution","date":"2020-09-29","arxiv_id":"2009.14108","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}}],"syntology_records":16,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}