{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/obstacle-tower-a-generalization-challenge-in#ran","syntology_url":"https://syntology.ai/paper/1902.01378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01378"}},"official":{"repos":["Unity-Technologies/obstacle-tower-env"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"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_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/obstacle-tower-a-generalization-challenge-in#ran","syntology_url":"https://syntology.ai/paper/1902.01378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01378"}},"official":{"repos":["Unity-Technologies/obstacle-tower-env"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"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_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/obstacle-tower-a-generalization-challenge-in#ran","syntology_url":"https://syntology.ai/paper/1902.01378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01378"}},"official":{"repos":["Unity-Technologies/obstacle-tower-env"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"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_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/obstacle-tower-a-generalization-challenge-in#ran","syntology_url":"https://syntology.ai/paper/1902.01378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01378"}},"official":{"repos":["Unity-Technologies/obstacle-tower-env"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"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_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/obstacle-tower-a-generalization-challenge-in#ran","syntology_url":"https://syntology.ai/paper/1902.01378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01378"}},"official":{"repos":["Unity-Technologies/obstacle-tower-env"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"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_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/obstacle-tower-a-generalization-challenge-in#ran","syntology_url":"https://syntology.ai/paper/1902.01378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01378"}},"official":{"repos":["Unity-Technologies/obstacle-tower-env"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}}],"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":84,"of":84,"of_with_code":40,"tagged_in_all":84,"counts":{"archive_papers_tagged":84,"with_a_code_link":40,"where_syntology_ran_a_sample":17,"not_listed_spam_title":0,"listed":84,"listed_where_code_ran":17,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":13,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":13,"listed_every_run_a_failure_of_syntologys_instrument":4,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/mastering-chess-and-shogi-by-self-play-with-a","slug":"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_constructed":0,"n_ran_checked":4,"n_instrument":9,"n_unverified":4,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":9,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mastering-chess-and-shogi-by-self-play-with-a#ran","syntology_url":"https://syntology.ai/paper/1712.01815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.01815"}},"official":null}},{"url":"/paper/openspiel-a-framework-for-reinforcement","slug":"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":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/openspiel-a-framework-for-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1908.09453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.09453"}},"official":{"repos":["deepmind/open_spiel"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/stabilizing-transformers-for-reinforcement-1","slug":"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_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/stabilizing-transformers-for-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/1910.06764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06764"}},"official":null}},{"url":"/paper/gibson-env-real-world-perception-for-embodied","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gibson-env-real-world-perception-for-embodied#ran","syntology_url":"https://syntology.ai/paper/1808.10654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.10654"}},"official":{"repos":["StanfordVL/GibsonEnv"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/action-branching-architectures-for-deep","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/recurrent-rational-networks#ran","syntology_url":"https://syntology.ai/paper/2102.09407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.09407"}},"official":{"repos":["ml-research/rational_activations","ml-research/rational_rl","ml-research/rational_sl","k4ntz/activation-functions"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sample-factory-egocentric-3d-control-from","slug":"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":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sample-factory-egocentric-3d-control-from#ran","syntology_url":"https://syntology.ai/paper/2006.11751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11751"}},"official":{"repos":["alex-petrenko/sample-factory"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/remax-a-simple-effective-and-efficient-method","slug":"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":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/remax-a-simple-effective-and-efficient-method#ran","syntology_url":"https://syntology.ai/paper/2310.10505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10505"}},"official":{"repos":["liziniu/ReMax"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/defix-detecting-and-fixing-failure-scenarios","slug":"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","slug":"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","slug":"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_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/the-loca-regret-a-consistent-metric-to#ran","syntology_url":"https://syntology.ai/paper/2007.03158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.03158"}},"official":{"repos":["chandar-lab/LoCA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-incentivize-other-learning-agents","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 10 unverified","sample_list":"/paper/learning-to-incentivize-other-learning-agents#ran","syntology_url":"https://syntology.ai/paper/2006.06051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06051"}},"official":{"repos":["011235813/lio"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":10,"ran_from_kinds":[]}}},{"url":"/paper/190600572","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rec-r1-bridging-generative-large-language#ran","syntology_url":"https://syntology.ai/paper/2503.24289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.24289"}},"official":{"repos":["linjc16/Rec-R1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hypercube-policy-regularization-framework-for","slug":"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","slug":"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_constructed":6,"n_ran_checked":15,"n_instrument":9,"n_unverified":9,"n_honours":5,"n_violates":4,"n_no_contract":6,"n_pointer_only":0,"phrase":"24 ran (of which 6 constructed an object rather than computing a result; 15 with no instrument failure: 5 honoured, 4 violated, 6 with no contract checked; 9 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/kinetix-investigating-the-training-of-general#ran","syntology_url":"https://syntology.ai/paper/2410.23208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23208"}},"official":{"repos":["michaeltmatthews/jax2d"],"state":"official (archive's flag): 24 ran","n_ran":24,"n_constructed":6,"n_ran_no_instrument_failure":15,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/discovering-general-reinforcement-learning-1","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/discovering-general-reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2310.02782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02782"}},"official":{"repos":["EmptyJackson/groove"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-backdoor-federated-learning","slug":"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":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/learning-to-backdoor-federated-learning#ran","syntology_url":"https://syntology.ai/paper/2303.03320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.03320"}},"official":{"repos":["HengerLi/RLBackdoorFL"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/intelligent-resource-allocation-in-joint","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/catastrophic-interference-in-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2109.00525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00525"}},"official":{"repos":["sweety-dm/interference-aware-deep-q-learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/qksa-quantum-knowledge-seeking-agent","slug":"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","slug":"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","slug":"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":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-to-represent-action-values-as-a-1#ran","syntology_url":"https://syntology.ai/paper/2010.14680","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.14680"}},"official":{"repos":["atavakol/action-hypergraph-networks"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/align-rudder-learning-from-few-demonstrations","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/align-rudder-learning-from-few-demonstrations#ran","syntology_url":"https://syntology.ai/paper/2009.14108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.14108"}},"official":{"repos":["ml-jku/align-rudder"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/developmental-reinforcement-learning-of","slug":"developmental-reinforcement-learning-of","title":"Developmental Reinforcement Learning of Control Policy of a Quadcopter UAV with Thrust Vectoring Rotors","date":"2020-07-15","arxiv_id":"2007.07793","repositories_listed":1,"syntology":null},{"url":"/paper/data-efficient-reinforcement-learning-with-1","slug":"data-efficient-reinforcement-learning-with-1","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","date":"2020-07-12","arxiv_id":"2007.05929","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/data-efficient-reinforcement-learning-with-1#ran","syntology_url":"https://syntology.ai/paper/2007.05929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.05929"}},"official":{"repos":["mila-iqia/spr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/counterfactual-data-augmentation-using","slug":"counterfactual-data-augmentation-using","title":"Counterfactual Data Augmentation using Locally Factored Dynamics","date":"2020-07-06","arxiv_id":"2007.02863","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/counterfactual-data-augmentation-using#ran","syntology_url":"https://syntology.ai/paper/2007.02863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.02863"}},"official":null}},{"url":"/paper/dynamic-algorithm-configuration-foundation-of","slug":"dynamic-algorithm-configuration-foundation-of","title":"Dynamic Algorithm Configuration: Foundation of a New Meta-Algorithmic Framework","date":"2020-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/local-and-global-explanations-of-agent","slug":"local-and-global-explanations-of-agent","title":"Local and Global Explanations of Agent Behavior: Integrating Strategy Summaries with Saliency Maps","date":"2020-05-18","arxiv_id":"2005.08874","repositories_listed":1,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/local-and-global-explanations-of-agent#ran","syntology_url":"https://syntology.ai/paper/2005.08874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08874"}},"official":{"repos":["HuTobias/HIGHLIGHTS-LRP"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/is-deep-reinforcement-learning-really","slug":"is-deep-reinforcement-learning-really","title":"Is Deep Reinforcement Learning Really Superhuman on Atari? Leveling the playing field","date":"2019-08-13","arxiv_id":"1908.04683","repositories_listed":1,"syntology":null},{"url":"/paper/time-limits-in-reinforcement-learning","slug":"time-limits-in-reinforcement-learning","title":"Time Limits in Reinforcement Learning","date":"2017-12-01","arxiv_id":"1712.00378","repositories_listed":1,"syntology":null},{"url":"/paper/dex-incremental-learning-for-complex","slug":"dex-incremental-learning-for-complex","title":"Dex: Incremental Learning for Complex Environments in Deep Reinforcement Learning","date":"2017-06-19","arxiv_id":"1706.05749","repositories_listed":1,"syntology":null},{"url":"/paper/aixijs-a-software-demo-for-general","slug":"aixijs-a-software-demo-for-general","title":"AIXIjs: A Software Demo for General Reinforcement Learning","date":"2017-05-22","arxiv_id":"1705.07615","repositories_listed":1,"syntology":null},{"url":"/paper/generalised-discount-functions-applied-to-a","slug":"generalised-discount-functions-applied-to-a","title":"Generalised Discount Functions applied to a Monte-Carlo AImu Implementation","date":"2017-03-03","arxiv_id":"1703.01358","repositories_listed":1,"syntology":null},{"url":null,"slug":"perl-permutation-enhanced-reinforcement","title":"PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning","date":"2025-06-17","arxiv_id":"2506.14907","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-order-regularization-for-machine","title":"High-order Regularization for Machine Learning and Learning-based Control","date":"2025-05-13","arxiv_id":"2505.08129","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-more-efficient-robust-instance","title":"Towards More Efficient, Robust, Instance-adaptive, and Generalizable Sequential Decision making","date":"2025-04-12","arxiv_id":"2504.09192","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-problem-of-social-cost-in-multi-agent","title":"The Problem of Social Cost in Multi-Agent General Reinforcement Learning: Survey and Synthesis","date":"2024-12-03","arxiv_id":"2412.02091","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-tutorial-and-survey","title":"Reinforcement Learning: Tutorial and Survey","date":"2024-07-18","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-knowledge-injection-for-aixi-agents","title":"Dynamic Knowledge Injection for AIXI Agents","date":"2023-12-18","arxiv_id":"2312.16184","repositories_listed":0,"syntology":null},{"url":null,"slug":"dropout-strategy-in-reinforcement-learning","title":"Dropout Strategy in Reinforcement Learning: Limiting the Surrogate Objective Variance in Policy Optimization Methods","date":"2023-10-31","arxiv_id":"2310.20380","repositories_listed":0,"syntology":null},{"url":null,"slug":"image-transformation-sequence-retrieval-with","title":"Image Transformation Sequence Retrieval with General Reinforcement Learning","date":"2023-07-13","arxiv_id":"2307.06630","repositories_listed":0,"syntology":null},{"url":null,"slug":"l-sa-learning-under-explored-targets-in-multi","title":"L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learning","date":"2023-05-23","arxiv_id":"2305.13741","repositories_listed":0,"syntology":null},{"url":null,"slug":"computably-continuous-reinforcement-learning","title":"Computably Continuous Reinforcement-Learning Objectives are PAC-learnable","date":"2023-03-09","arxiv_id":"2303.05518","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-mirror-descent-inherently-explores","title":"Policy Mirror Descent Inherently Explores Action Space","date":"2023-03-08","arxiv_id":"2303.04386","repositories_listed":0,"syntology":null},{"url":null,"slug":"enactivism-objectively-optimal-super","title":"Computational Dualism and Objective Superintelligence","date":"2023-02-02","arxiv_id":"2302.00843","repositories_listed":0,"syntology":null},{"url":null,"slug":"accuracy-guaranteed-collaborative-dnn","title":"Accuracy-Guaranteed Collaborative DNN Inference in Industrial IoT via Deep Reinforcement Learning","date":"2022-12-31","arxiv_id":"2301.00130","repositories_listed":0,"syntology":null},{"url":null,"slug":"accerl-policy-acceleration-framework-for-deep","title":"AcceRL: Policy Acceleration Framework for Deep Reinforcement Learning","date":"2022-11-28","arxiv_id":"2211.15023","repositories_listed":0,"syntology":null},{"url":null,"slug":"computable-artificial-general-intelligence","title":"Computable Artificial General Intelligence","date":"2022-05-21","arxiv_id":"2205.10513","repositories_listed":0,"syntology":null},{"url":null,"slug":"d3pg-dirichlet-ddpg-for-task-partitioning-and","title":"D3PG: Dirichlet DDPG for Task Partitioning and Offloading With Constrained Hybrid Action Space in Mobile-Edge Computing","date":"2022-04-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"abstractions-of-general-reinforcement","title":"Abstractions of General Reinforcement Learning","date":"2021-12-26","arxiv_id":"2112.13404","repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-planning-complexity-of-general","title":"Reducing Planning Complexity of General Reinforcement Learning with Non-Markovian Abstractions","date":"2021-12-26","arxiv_id":"2112.13386","repositories_listed":0,"syntology":null},{"url":null,"slug":"sbf-delta-2-exploration-for-reinforcement","title":"$\\sbf{\\delta^2}$-exploration for Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"superior-performance-with-diversified","title":"Superior Performance with Diversified Strategic Control in FPS Games Using General Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-policy-efficient-reduction-approach-to","title":"A Policy Efficient Reduction Approach to Convex Constrained Deep Reinforcement Learning","date":"2021-08-29","arxiv_id":"2108.12916","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-machine-translation-based-on","title":"Low-Resource Machine Translation based on Asynchronous Dynamic Programming","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-swarm-collision-avoidance-for","title":"Nearest-Neighbor-based Collision Avoidance for Quadrotors via Reinforcement Learning","date":"2021-04-30","arxiv_id":"2104.14912","repositories_listed":0,"syntology":null},{"url":null,"slug":"fair-iot-fairness-aware-human-in-the-loop","title":"FaiR-IoT: Fairness-aware Human-in-the-Loop Reinforcement Learning for Harnessing Human Variability in Personalized IoT","date":"2021-03-30","arxiv_id":"2103.16033","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-state-representation-dueling-network-for","title":"A State Representation Dueling Network for Deep Reinforcement Learning","date":"2020-12-24","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exact-reduction-of-huge-action-spaces-in","title":"Exact Reduction of Huge Action Spaces in General Reinforcement Learning","date":"2020-12-18","arxiv_id":"2012.10200","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-variables-from-reinforcement-learning","title":"Reinforcement Learning of Causal Variables Using Mediation Analysis","date":"2020-10-29","arxiv_id":"2010.15745","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-as-reinforcement-applying-principles","title":"Learning as Reinforcement: Applying Principles of Neuroscience for More General Reinforcement Learning Agents","date":"2020-04-20","arxiv_id":"2004.09043","repositories_listed":0,"syntology":null},{"url":null,"slug":"studentteacher-advising-through-reward","title":"Student/Teacher Advising through Reward Augmentation","date":"2020-02-07","arxiv_id":"2002.02938","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-free-mean-field-reinforcement-learning","title":"Model-Free Mean-Field Reinforcement Learning: Mean-Field MDP and Mean-Field Q-Learning","date":"2019-10-28","arxiv_id":"1910.12802","repositories_listed":0,"syntology":null},{"url":null,"slug":"goal-driven-sequential-data-abstraction","title":"Goal-Driven Sequential Data Abstraction","date":"2019-07-29","arxiv_id":"1907.12336","repositories_listed":0,"syntology":null},{"url":null,"slug":"regularized-hierarchical-policies-for","title":"Compositional Transfer in Hierarchical Reinforcement Learning","date":"2019-06-26","arxiv_id":"1906.11228","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-regret-bounds-for-reinforcement","title":"Variational Regret Bounds for Reinforcement Learning","date":"2019-05-14","arxiv_id":"1905.05857","repositories_listed":0,"syntology":null},{"url":null,"slug":"macro-action-reinforcement-learning-with","title":"Macro Action Reinforcement Learning with Sequence Disentanglement using Variational Autoencoder","date":"2019-03-22","arxiv_id":"1903.09366","repositories_listed":0,"syntology":null},{"url":null,"slug":"differential-temporal-difference-learning","title":"Differential Temporal Difference Learning","date":"2018-12-28","arxiv_id":"1812.11137","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-reinforcement-learning-to-self","title":"Integrating Reinforcement Learning to Self Training for Pulmonary Nodule Segmentation in Chest X-rays","date":"2018-11-21","arxiv_id":"1811.08840","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferring-agent-behaviors-from-videos-via","title":"Transferring Agent Behaviors from Videos via Motion GANs","date":"2017-11-21","arxiv_id":"1711.07676","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-of-speech-recognition","title":"Reinforcement Learning of Speech Recognition System Based on Policy Gradient and Hypothesis Selection","date":"2017-11-10","arxiv_id":"1711.03689","repositories_listed":0,"syntology":null},{"url":null,"slug":"nonparametric-general-reinforcement-learning","title":"Nonparametric General Reinforcement Learning","date":"2016-11-28","arxiv_id":"1611.08944","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-modification-of-policy-and-utility","title":"Self-Modification of Policy and Utility Function in Rational Agents","date":"2016-05-10","arxiv_id":"1605.03142","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-information-acquisition","title":"Active Information Acquisition","date":"2016-02-05","arxiv_id":"1602.02181","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-sample-complexity-of-general","title":"The Sample-Complexity of General Reinforcement Learning","date":"2013-08-22","arxiv_id":"1308.4828","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-reinforcement-of-behavioral","title":"Autonomous Reinforcement of Behavioral Sequences in Neural Dynamics","date":"2012-10-12","arxiv_id":"1210.3569","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-via-aixi-approximation","title":"Reinforcement Learning via AIXI Approximation","date":"2010-07-13","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":19,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":17,"papers_where_code_ran_first_page":"/task/general-reinforcement-learning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/general-reinforcement-learning/papers/ran/1","json":"/task/general-reinforcement-learning/papers/ran/1.json","rows":17}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"0d37e9f7e5da2999e8be7cfe1333ef807ff1afe6e74174398640084ead85eb1e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}