{"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/papers/ran/1","list_of":"/task/general-reinforcement-learning","task":"General Reinforcement Learning","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","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.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,17],"of":17,"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"},"first_page":"/task/general-reinforcement-learning/papers/ran/1","prev":null,"next":null,"papers":[{"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/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/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":10,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 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":10,"n_unverified":2,"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/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/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/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/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/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/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/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/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/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/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":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"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) · 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/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/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}}],"record_sha256":"c625202744f8fca8a02bf51f415c60830cec1397c71713c9e3fd5b80710933e9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}