{"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/reinforcement-learning-2/papers/ran/3","list_of":"/task/reinforcement-learning-2","task":"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":3,"pages_in_order":12,"rows_per_page":100,"rows":[201,300],"of":1165,"counts":{"archive_papers_tagged":13427,"with_a_code_link":4119,"where_syntology_ran_a_sample":1165,"not_listed_spam_title":0,"listed":13427,"listed_where_code_ran":1165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":973,"every_run_a_failure_of_syntologys_instrument":192,"listed_with_a_run_with_no_instrument_failure":973,"listed_every_run_a_failure_of_syntologys_instrument":192,"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/reinforcement-learning-2/papers/ran/1","prev":"/task/reinforcement-learning-2/papers/ran/2","next":"/task/reinforcement-learning-2/papers/ran/4","papers":[{"url":"/paper/training-large-language-models-for-reasoning","slug":"training-large-language-models-for-reasoning","title":"Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning","date":"2024-02-08","arxiv_id":"2402.05808","repositories_listed":1,"syntology":{"n":19,"n_ran":15,"n_constructed":0,"n_ran_checked":14,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":19,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/training-large-language-models-for-reasoning#ran","syntology_url":"https://syntology.ai/paper/2402.05808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05808"}},"official":{"repos":["woooodyy/llm-reverse-curriculum-rl"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/discovering-temporally-aware-reinforcement","slug":"discovering-temporally-aware-reinforcement","title":"Discovering Temporally-Aware Reinforcement Learning Algorithms","date":"2024-02-08","arxiv_id":"2402.05828","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/discovering-temporally-aware-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2402.05828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05828"}},"official":{"repos":["EmptyJackson/groove"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-generalizability-of-multi-agent","slug":"towards-generalizability-of-multi-agent","title":"Towards Generalizability of Multi-Agent Reinforcement Learning in Graphs with Recurrent Message Passing","date":"2024-02-07","arxiv_id":"2402.05027","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/towards-generalizability-of-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2402.05027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05027"}},"official":{"repos":["jw3il/graph-marl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/compound-returns-reduce-variance-in","slug":"compound-returns-reduce-variance-in","title":"Averaging $n$-step Returns Reduces Variance in Reinforcement Learning","date":"2024-02-06","arxiv_id":"2402.03903","repositories_listed":0,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"5 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/compound-returns-reduce-variance-in#ran","syntology_url":"https://syntology.ai/paper/2402.03903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03903"}},"official":null}},{"url":"/paper/entropy-regularized-diffusion-policy-with-q","slug":"entropy-regularized-diffusion-policy-with-q","title":"Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning","date":"2024-02-06","arxiv_id":"2402.04080","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/entropy-regularized-diffusion-policy-with-q#ran","syntology_url":"https://syntology.ai/paper/2402.04080","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04080"}},"official":{"repos":["ruoqizzz/entropy-offlineRL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-with-ensemble-model","slug":"reinforcement-learning-with-ensemble-model","title":"Reinforcement Learning with Ensemble Model Predictive Safety Certification","date":"2024-02-06","arxiv_id":"2402.04182","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"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) · 0 unverified","sample_list":"/paper/reinforcement-learning-with-ensemble-model#ran","syntology_url":"https://syntology.ai/paper/2402.04182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04182"}},"official":{"repos":["svengronauer/x-mpsc"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/open-rl-benchmark-comprehensive-tracked","slug":"open-rl-benchmark-comprehensive-tracked","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","date":"2024-02-05","arxiv_id":"2402.03046","repositories_listed":1,"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/open-rl-benchmark-comprehensive-tracked#ran","syntology_url":"https://syntology.ai/paper/2402.03046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03046"}},"official":null}},{"url":"/paper/boosting-long-delayed-reinforcement-learning","slug":"boosting-long-delayed-reinforcement-learning","title":"Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays","date":"2024-02-05","arxiv_id":"2402.03141","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":11,"phrase":"10 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/boosting-long-delayed-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2402.03141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03141"}},"official":{"repos":["qingyuanwunothing/ad-rl"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dense-reward-for-free-in-reinforcement","slug":"dense-reward-for-free-in-reinforcement","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","date":"2024-02-01","arxiv_id":"2402.00782","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/dense-reward-for-free-in-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2402.00782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00782"}},"official":{"repos":["xanderjc/attention-based-credit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-reinforcement-learning-via-function","slug":"zero-shot-reinforcement-learning-via-function","title":"Zero-Shot Reinforcement Learning via Function Encoders","date":"2024-01-30","arxiv_id":"2401.17173","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/zero-shot-reinforcement-learning-via-function#ran","syntology_url":"https://syntology.ai/paper/2401.17173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17173"}},"official":{"repos":["anonymousresearcher5642/functionencoderrl","tyler-ingebrand/functionencoderrl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/off-policy-primal-dual-safe-reinforcement","slug":"off-policy-primal-dual-safe-reinforcement","title":"Off-Policy Primal-Dual Safe Reinforcement Learning","date":"2024-01-26","arxiv_id":"2401.14758","repositories_listed":2,"syntology":{"n":22,"n_ran":13,"n_constructed":1,"n_ran_checked":11,"n_instrument":2,"n_unverified":9,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":10,"phrase":"13 ran (of which 1 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/off-policy-primal-dual-safe-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2401.14758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14758"}},"official":{"repos":["pku-alignment/omnisafe","zifanwu/cal"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/fully-independent-communication-in-multi","slug":"fully-independent-communication-in-multi","title":"Fully Independent Communication in Multi-Agent Reinforcement Learning","date":"2024-01-26","arxiv_id":"2401.15059","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fully-independent-communication-in-multi#ran","syntology_url":"https://syntology.ai/paper/2401.15059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.15059"}},"official":{"repos":["rafaelmp2/marl-indep-comm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/seer-facilitating-structured-reasoning-and","slug":"seer-facilitating-structured-reasoning-and","title":"SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning","date":"2024-01-24","arxiv_id":"2401.13246","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/seer-facilitating-structured-reasoning-and#ran","syntology_url":"https://syntology.ai/paper/2401.13246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.13246"}},"official":{"repos":["chen-gx/seer"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/safe-offline-reinforcement-learning-with","slug":"safe-offline-reinforcement-learning-with","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","date":"2024-01-19","arxiv_id":"2401.10700","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":2,"n_no_contract":5,"n_pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 2 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/safe-offline-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2401.10700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10700"}},"official":{"repos":["zhengyinan-air/fisor"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/langprop-a-code-optimization-framework-using","slug":"langprop-a-code-optimization-framework-using","title":"LangProp: A code optimization framework using Large Language Models applied to driving","date":"2024-01-18","arxiv_id":"2401.10314","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":1,"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/langprop-a-code-optimization-framework-using#ran","syntology_url":"https://syntology.ai/paper/2401.10314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10314"}},"official":{"repos":["shuishida/langprop"],"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/deployable-reinforcement-learning-with","slug":"deployable-reinforcement-learning-with","title":"Deployable Reinforcement Learning with Variable Control Rate","date":"2024-01-17","arxiv_id":"2401.09286","repositories_listed":1,"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":1,"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/deployable-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2401.09286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09286"}},"official":{"repos":["alpaficia/SEAC_Pytorch_release"],"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/interpretable-concept-bottlenecks-to-align","slug":"interpretable-concept-bottlenecks-to-align","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","date":"2024-01-11","arxiv_id":"2401.05821","repositories_listed":1,"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/interpretable-concept-bottlenecks-to-align#ran","syntology_url":"https://syntology.ai/paper/2401.05821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05821"}},"official":{"repos":["k4ntz/scobots"],"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/secrets-of-rlhf-in-large-language-models-part-1","slug":"secrets-of-rlhf-in-large-language-models-part-1","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","date":"2024-01-11","arxiv_id":"2401.06080","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/secrets-of-rlhf-in-large-language-models-part-1#ran","syntology_url":"https://syntology.ai/paper/2401.06080","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06080"}},"official":{"repos":["openlmlab/moss-rlhf"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/spqr-controlling-q-ensemble-independence-with-1","slug":"spqr-controlling-q-ensemble-independence-with-1","title":"SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning","date":"2024-01-06","arxiv_id":"2401.03137","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/spqr-controlling-q-ensemble-independence-with-1#ran","syntology_url":"https://syntology.ai/paper/2401.03137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03137"}},"official":{"repos":["dohyeoklee/SPQR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/policy-regularized-offline-multi-objective","slug":"policy-regularized-offline-multi-objective","title":"Policy-regularized Offline Multi-objective Reinforcement Learning","date":"2024-01-04","arxiv_id":"2401.02244","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/policy-regularized-offline-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2401.02244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02244"}},"official":{"repos":["qianlin04/prmorl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generalizable-visual-reinforcement-learning","slug":"generalizable-visual-reinforcement-learning","title":"Generalizable Visual Reinforcement Learning with Segment Anything Model","date":"2023-12-28","arxiv_id":"2312.17116","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/generalizable-visual-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2312.17116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17116"}},"official":{"repos":["wadiuvatzy/sam-g"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/can-active-sampling-reduce-causal-confusion","slug":"can-active-sampling-reduce-causal-confusion","title":"Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?","date":"2023-12-28","arxiv_id":"2312.17168","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/can-active-sampling-reduce-causal-confusion#ran","syntology_url":"https://syntology.ai/paper/2312.17168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17168"}},"official":{"repos":["gunshi/offline_active_rl"],"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/generalizable-task-representation-learning-1","slug":"generalizable-task-representation-learning-1","title":"Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations","date":"2023-12-26","arxiv_id":"2312.15909","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/generalizable-task-representation-learning-1#ran","syntology_url":"https://syntology.ai/paper/2312.15909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15909"}},"official":{"repos":["lamda-rl/gentle"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-unlearning","slug":"reinforcement-unlearning","title":"Reinforcement Unlearning","date":"2023-12-26","arxiv_id":"2312.15910","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":1,"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/reinforcement-unlearning#ran","syntology_url":"https://syntology.ai/paper/2312.15910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15910"}},"official":{"repos":["cp-lab-uts/reinforcement-unlearning"],"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/xuance-a-comprehensive-and-unified-deep","slug":"xuance-a-comprehensive-and-unified-deep","title":"XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library","date":"2023-12-25","arxiv_id":"2312.16248","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/xuance-a-comprehensive-and-unified-deep#ran","syntology_url":"https://syntology.ai/paper/2312.16248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.16248"}},"official":{"repos":["agi-brain/xuance"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/critic-guided-decision-transformer-for","slug":"critic-guided-decision-transformer-for","title":"Critic-Guided Decision Transformer for Offline Reinforcement Learning","date":"2023-12-21","arxiv_id":"2312.13716","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"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) · 4 unverified","sample_list":"/paper/critic-guided-decision-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2312.13716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.13716"}},"official":{"repos":["sharkwyf/cgdt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/de-novo-drug-design-using-reinforcement-1","slug":"de-novo-drug-design-using-reinforcement-1","title":"De novo Drug Design using Reinforcement Learning with Multiple GPT Agents","date":"2023-12-21","arxiv_id":"2401.06155","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 2 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) · 1 unverified","sample_list":"/paper/de-novo-drug-design-using-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2401.06155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06155"}},"official":{"repos":["hxyfighter/molrl-mgpt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/in-context-reinforcement-learning-for","slug":"in-context-reinforcement-learning-for","title":"In-Context Reinforcement Learning for Variable Action Spaces","date":"2023-12-20","arxiv_id":"2312.13327","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":2,"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/in-context-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2312.13327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.13327"}},"official":{"repos":["corl-team/headless-ad"],"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/emergence-of-in-context-reinforcement","slug":"emergence-of-in-context-reinforcement","title":"Emergence of In-Context Reinforcement Learning from Noise Distillation","date":"2023-12-19","arxiv_id":"2312.12275","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 3 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; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/emergence-of-in-context-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2312.12275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12275"}},"official":{"repos":["corl-team/ad-eps"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/badrl-sparse-targeted-backdoor-attack-against","slug":"badrl-sparse-targeted-backdoor-attack-against","title":"BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning","date":"2023-12-19","arxiv_id":"2312.12585","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":2,"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/badrl-sparse-targeted-backdoor-attack-against#ran","syntology_url":"https://syntology.ai/paper/2312.12585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12585"}},"official":{"repos":["7777777cc/code"],"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/learning-a-diffusion-model-policy-from","slug":"learning-a-diffusion-model-policy-from","title":"Learning a Diffusion Model Policy from Rewards via Q-Score Matching","date":"2023-12-18","arxiv_id":"2312.11752","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-a-diffusion-model-policy-from#ran","syntology_url":"https://syntology.ai/paper/2312.11752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11752"}},"official":{"repos":["Alescontrela/score_matching_rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/no-prior-mask-eliminate-redundant-action-for","slug":"no-prior-mask-eliminate-redundant-action-for","title":"No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning","date":"2023-12-11","arxiv_id":"2312.06258","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/no-prior-mask-eliminate-redundant-action-for#ran","syntology_url":"https://syntology.ai/paper/2312.06258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06258"}},"official":{"repos":["zhongdy15/npm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reward-certification-for-policy-smoothed","slug":"reward-certification-for-policy-smoothed","title":"Reward Certification for Policy Smoothed Reinforcement Learning","date":"2023-12-11","arxiv_id":"2312.06436","repositories_listed":1,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":11,"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) · 6 unverified","sample_list":"/paper/reward-certification-for-policy-smoothed#ran","syntology_url":"https://syntology.ai/paper/2312.06436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06436"}},"official":{"repos":["trustai/receps"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/decoupling-meta-reinforcement-learning-with","slug":"decoupling-meta-reinforcement-learning-with","title":"Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills","date":"2023-12-11","arxiv_id":"2312.06518","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":3,"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/decoupling-meta-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2312.06518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06518"}},"official":{"repos":["hehongc/DCMRL"],"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/the-generalization-gap-in-offline","slug":"the-generalization-gap-in-offline","title":"The Generalization Gap in Offline Reinforcement Learning","date":"2023-12-10","arxiv_id":"2312.05742","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/the-generalization-gap-in-offline#ran","syntology_url":"https://syntology.ai/paper/2312.05742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.05742"}},"official":{"repos":["facebookresearch/gen_dgrl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/synergizing-quality-diversity-with-descriptor","slug":"synergizing-quality-diversity-with-descriptor","title":"Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learning","date":"2023-12-10","arxiv_id":"2401.08632","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/synergizing-quality-diversity-with-descriptor#ran","syntology_url":"https://syntology.ai/paper/2401.08632","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08632"}},"official":{"repos":["adaptive-intelligent-robotics/DCRL-MAP-Elites"],"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":["listed","official"]}}},{"url":"/paper/backward-learning-for-goal-conditioned","slug":"backward-learning-for-goal-conditioned","title":"Backward Learning for Goal-Conditioned Policies","date":"2023-12-08","arxiv_id":"2312.05044","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":1,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 1 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) · 4 unverified","sample_list":"/paper/backward-learning-for-goal-conditioned#ran","syntology_url":"https://syntology.ai/paper/2312.05044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.05044"}},"official":{"repos":["hauf3n/backward-learning-for-goal-conditioned-policies"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/physical-symbolic-optimization","slug":"physical-symbolic-optimization","title":"Physical Symbolic Optimization","date":"2023-12-06","arxiv_id":"2312.03612","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/physical-symbolic-optimization#ran","syntology_url":"https://syntology.ai/paper/2312.03612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03612"}},"official":{"repos":["wassimtenachi/physo"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/colour-versus-shape-goal-misgeneralization-in","slug":"colour-versus-shape-goal-misgeneralization-in","title":"Colour versus Shape Goal Misgeneralization in Reinforcement Learning: A Case Study","date":"2023-12-05","arxiv_id":"2312.03762","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/colour-versus-shape-goal-misgeneralization-in#ran","syntology_url":"https://syntology.ai/paper/2312.03762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03762"}},"official":{"repos":["KarolisRam/colour-shape-goal-misgeneralization"],"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/adsorbrl-deep-multi-objective-reinforcement","slug":"adsorbrl-deep-multi-objective-reinforcement","title":"AdsorbRL: Deep Multi-Objective Reinforcement Learning for Inverse Catalysts Design","date":"2023-12-04","arxiv_id":"2312.02308","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/adsorbrl-deep-multi-objective-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2312.02308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02308"}},"official":{"repos":["rlacombe/adsorbrl"],"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/benchmarl-benchmarking-multi-agent","slug":"benchmarl-benchmarking-multi-agent","title":"BenchMARL: Benchmarking Multi-Agent Reinforcement Learning","date":"2023-12-03","arxiv_id":"2312.01472","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchmarl-benchmarking-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2312.01472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01472"}},"official":{"repos":["facebookresearch/benchmarl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/regularity-as-intrinsic-reward-for-free-play-1","slug":"regularity-as-intrinsic-reward-for-free-play-1","title":"Regularity as Intrinsic Reward for Free Play","date":"2023-12-03","arxiv_id":"2312.01473","repositories_listed":0,"syntology":{"n":16,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":16,"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) · 7 unverified","sample_list":"/paper/regularity-as-intrinsic-reward-for-free-play-1#ran","syntology_url":"https://syntology.ai/paper/2312.01473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01473"}},"official":null}},{"url":"/paper/sample-efficient-reinforcement-learning-from","slug":"sample-efficient-reinforcement-learning-from","title":"Sample Efficient Preference Alignment in LLMs via Active Exploration","date":"2023-12-01","arxiv_id":"2312.00267","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sample-efficient-reinforcement-learning-from#ran","syntology_url":"https://syntology.ai/paper/2312.00267","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00267"}},"official":{"repos":["belakaria/active-llm-alignment"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lmrl-gym-benchmarks-for-multi-turn","slug":"lmrl-gym-benchmarks-for-multi-turn","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","date":"2023-11-30","arxiv_id":"2311.18232","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lmrl-gym-benchmarks-for-multi-turn#ran","syntology_url":"https://syntology.ai/paper/2311.18232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18232"}},"official":{"repos":["abdulhaim/lmrl-gym"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-diffusion-models-with-text-encoder","slug":"enhancing-diffusion-models-with-text-encoder","title":"Enhancing Diffusion Models with Text-Encoder Reinforcement Learning","date":"2023-11-27","arxiv_id":"2311.15657","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":1,"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/enhancing-diffusion-models-with-text-encoder#ran","syntology_url":"https://syntology.ai/paper/2311.15657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15657"}},"official":{"repos":["chaofengc/texforce"],"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/utilizing-explainability-techniques-for","slug":"utilizing-explainability-techniques-for","title":"Utilizing Explainability Techniques for Reinforcement Learning Model Assurance","date":"2023-11-27","arxiv_id":"2311.15838","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/utilizing-explainability-techniques-for#ran","syntology_url":"https://syntology.ai/paper/2311.15838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15838"}},"official":{"repos":["mitre/arlin"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-for-wildfire","slug":"reinforcement-learning-for-wildfire","title":"Reinforcement Learning for Wildfire Mitigation in Simulated Disaster Environments","date":"2023-11-27","arxiv_id":"2311.15925","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/reinforcement-learning-for-wildfire#ran","syntology_url":"https://syntology.ai/paper/2311.15925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15925"}},"official":{"repos":["mitrefireline/simfire"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-modelling-of-stochastic-actions-1","slug":"generative-modelling-of-stochastic-actions-1","title":"Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning","date":"2023-11-26","arxiv_id":"2311.15341","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generative-modelling-of-stochastic-actions-1#ran","syntology_url":"https://syntology.ai/paper/2311.15341","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15341"}},"official":{"repos":["cameron-chen/flow-iar"],"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/multi-objective-reinforcement-learning-based-2","slug":"multi-objective-reinforcement-learning-based-2","title":"Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Framework","date":"2023-11-21","arxiv_id":"2311.12495","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":3,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-objective-reinforcement-learning-based-2#ran","syntology_url":"https://syntology.ai/paper/2311.12495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.12495"}},"official":{"repos":["lucasalegre/morl-baselines"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/replay-enhanced-continual-reinforcement","slug":"replay-enhanced-continual-reinforcement","title":"Replay-enhanced Continual Reinforcement Learning","date":"2023-11-20","arxiv_id":"2311.11557","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/replay-enhanced-continual-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2311.11557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.11557"}},"official":{"repos":["Sweety-dm/RECALL"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-task-reinforcement-learning-with-1","slug":"multi-task-reinforcement-learning-with-1","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","date":"2023-11-19","arxiv_id":"2311.11385","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-task-reinforcement-learning-with-1#ran","syntology_url":"https://syntology.ai/paper/2311.11385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.11385"}},"official":{"repos":["AhmedMagdyHendawy/MOORE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/direct-preference-optimization-for-neural","slug":"direct-preference-optimization-for-neural","title":"Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding","date":"2023-11-14","arxiv_id":"2311.08380","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/direct-preference-optimization-for-neural#ran","syntology_url":"https://syntology.ai/paper/2311.08380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.08380"}},"official":{"repos":["bruceyg/dpo-mbr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-agent-quantum-reinforcement-learning","slug":"multi-agent-quantum-reinforcement-learning","title":"Multi-Agent Quantum Reinforcement Learning using Evolutionary Optimization","date":"2023-11-09","arxiv_id":"2311.05546","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-agent-quantum-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2311.05546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05546"}},"official":{"repos":["michaelkoelle/qmarl-evo"],"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/context-shift-reduction-for-offline-meta-1","slug":"context-shift-reduction-for-offline-meta-1","title":"Context Shift Reduction for Offline Meta-Reinforcement Learning","date":"2023-11-07","arxiv_id":"2311.03695","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"4 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/context-shift-reduction-for-offline-meta-1#ran","syntology_url":"https://syntology.ai/paper/2311.03695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.03695"}},"official":{"repos":["moreanp/csro"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/state-wise-safe-reinforcement-learning-with","slug":"state-wise-safe-reinforcement-learning-with","title":"State-Wise Safe Reinforcement Learning With Pixel Observations","date":"2023-11-03","arxiv_id":"2311.02227","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/state-wise-safe-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2311.02227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.02227"}},"official":{"repos":["simonzhan-code/step-wise_saferl_pixel"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/contrastive-modules-with-temporal-attention","slug":"contrastive-modules-with-temporal-attention","title":"Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning","date":"2023-11-02","arxiv_id":"2311.01075","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/contrastive-modules-with-temporal-attention#ran","syntology_url":"https://syntology.ai/paper/2311.01075","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01075"}},"official":{"repos":["niiceMing/CMTA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/selectively-sharing-experiences-improves","slug":"selectively-sharing-experiences-improves","title":"Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning","date":"2023-11-01","arxiv_id":"2311.00865","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/selectively-sharing-experiences-improves#ran","syntology_url":"https://syntology.ai/paper/2311.00865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.00865"}},"official":{"repos":["mgerstgrasser/super"],"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/variational-curriculum-reinforcement-learning","slug":"variational-curriculum-reinforcement-learning","title":"Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills","date":"2023-10-30","arxiv_id":"2310.19424","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":5,"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/variational-curriculum-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2310.19424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19424"}},"official":{"repos":["seongun-kim/vcrl"],"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/drm-mastering-visual-reinforcement-learning","slug":"drm-mastering-visual-reinforcement-learning","title":"DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization","date":"2023-10-30","arxiv_id":"2310.19668","repositories_listed":2,"syntology":{"n":14,"n_ran":10,"n_constructed":3,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":6,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/drm-mastering-visual-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2310.19668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19668"}},"official":{"repos":["XuGW-Kevin/DrM"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/robust-offline-policy-evaluation-and","slug":"robust-offline-policy-evaluation-and","title":"Robust Offline Reinforcement learning with Heavy-Tailed Rewards","date":"2023-10-28","arxiv_id":"2310.18715","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-offline-policy-evaluation-and#ran","syntology_url":"https://syntology.ai/paper/2310.18715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18715"}},"official":{"repos":["mamba413/room"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-when-dynamics-invariant-data","slug":"understanding-when-dynamics-invariant-data","title":"Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates","date":"2023-10-26","arxiv_id":"2310.17786","repositories_listed":1,"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":5,"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/understanding-when-dynamics-invariant-data#ran","syntology_url":"https://syntology.ai/paper/2310.17786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17786"}},"official":{"repos":["badger-rl/understandingdataaugmentationforrl"],"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/reward-scale-robustness-for-proximal-policy","slug":"reward-scale-robustness-for-proximal-policy","title":"Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks","date":"2023-10-26","arxiv_id":"2310.17805","repositories_listed":0,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reward-scale-robustness-for-proximal-policy#ran","syntology_url":"https://syntology.ai/paper/2310.17805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17805"}},"official":null}},{"url":"/paper/dynamics-generalisation-in-reinforcement-1","slug":"dynamics-generalisation-in-reinforcement-1","title":"Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies","date":"2023-10-25","arxiv_id":"2310.16686","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":4,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dynamics-generalisation-in-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2310.16686","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16686"}},"official":{"repos":["michael-beukman/decisionadapter"],"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":["listed","official"]}}},{"url":"/paper/recurrent-linear-transformers","slug":"recurrent-linear-transformers","title":"AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning","date":"2023-10-24","arxiv_id":"2310.15719","repositories_listed":2,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/recurrent-linear-transformers#ran","syntology_url":"https://syntology.ai/paper/2310.15719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15719"}},"official":{"repos":["subho406/Recurrent-Linear-Transformers","subho406/agalite"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/corruption-robust-offline-reinforcement-2","slug":"corruption-robust-offline-reinforcement-2","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","date":"2023-10-23","arxiv_id":"2310.14550","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"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, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/corruption-robust-offline-reinforcement-2#ran","syntology_url":"https://syntology.ai/paper/2310.14550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14550"}},"official":{"repos":["yangrui2015/uwmsg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-navigation-training-autonomous-vehicles","slug":"safe-navigation-training-autonomous-vehicles","title":"Safe Navigation: Training Autonomous Vehicles using Deep Reinforcement Learning in CARLA","date":"2023-10-23","arxiv_id":"2311.10735","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/safe-navigation-training-autonomous-vehicles#ran","syntology_url":"https://syntology.ai/paper/2311.10735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.10735"}},"official":{"repos":["tejas-deo/safe-navigation-training-autonomous-vehicles-using-deep-reinforcement-learning-in-carla"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/contrastive-prefence-learning-learning-from","slug":"contrastive-prefence-learning-learning-from","title":"Contrastive Preference Learning: Learning from Human Feedback without RL","date":"2023-10-20","arxiv_id":"2310.13639","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/contrastive-prefence-learning-learning-from#ran","syntology_url":"https://syntology.ai/paper/2310.13639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13639"}},"official":{"repos":["jhejna/cpl"],"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/safe-rlhf-safe-reinforcement-learning-from","slug":"safe-rlhf-safe-reinforcement-learning-from","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","date":"2023-10-19","arxiv_id":"2310.12773","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safe-rlhf-safe-reinforcement-learning-from#ran","syntology_url":"https://syntology.ai/paper/2310.12773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12773"}},"official":{"repos":["pku-alignment/safe-rlhf"],"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/vision-language-models-are-zero-shot-reward","slug":"vision-language-models-are-zero-shot-reward","title":"Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning","date":"2023-10-19","arxiv_id":"2310.12921","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/vision-language-models-are-zero-shot-reward#ran","syntology_url":"https://syntology.ai/paper/2310.12921","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12921"}},"official":{"repos":["alignmentresearch/vlmrm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/eureka-human-level-reward-design-via-coding","slug":"eureka-human-level-reward-design-via-coding","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","date":"2023-10-19","arxiv_id":"2310.12931","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/eureka-human-level-reward-design-via-coding#ran","syntology_url":"https://syntology.ai/paper/2310.12931","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12931"}},"official":{"repos":["eureka-research/Eureka"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"url":"/paper/towards-robust-offline-reinforcement-learning","slug":"towards-robust-offline-reinforcement-learning","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","date":"2023-10-19","arxiv_id":"2310.12955","repositories_listed":2,"syntology":{"n":9,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/towards-robust-offline-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2310.12955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12955"}},"official":{"repos":["yangrui2015/riql"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/quality-diversity-through-human-feedback","slug":"quality-diversity-through-human-feedback","title":"Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization","date":"2023-10-18","arxiv_id":"2310.12103","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/quality-diversity-through-human-feedback#ran","syntology_url":"https://syntology.ai/paper/2310.12103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12103"}},"official":{"repos":["ld-ing/qdhf"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/personalized-soups-personalized-large","slug":"personalized-soups-personalized-large","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","date":"2023-10-17","arxiv_id":"2310.11564","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":15,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/personalized-soups-personalized-large#ran","syntology_url":"https://syntology.ai/paper/2310.11564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.11564"}},"official":{"repos":["joeljang/rlphf"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"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/a-partially-supervised-reinforcement-learning","slug":"a-partially-supervised-reinforcement-learning","title":"A Partially Supervised Reinforcement Learning Framework for Visual Active Search","date":"2023-10-15","arxiv_id":"2310.09689","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/a-partially-supervised-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2310.09689","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09689"}},"official":{"repos":["anindyasarkariith/psrl_vas"],"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/amago-scalable-in-context-reinforcement","slug":"amago-scalable-in-context-reinforcement","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","date":"2023-10-15","arxiv_id":"2310.09971","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/amago-scalable-in-context-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2310.09971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09971"}},"official":{"repos":["ut-austin-rpl/amago"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/storm-efficient-stochastic-transformer-based-1","slug":"storm-efficient-stochastic-transformer-based-1","title":"STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning","date":"2023-10-14","arxiv_id":"2310.09615","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"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) · 2 unverified","sample_list":"/paper/storm-efficient-stochastic-transformer-based-1#ran","syntology_url":"https://syntology.ai/paper/2310.09615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09615"}},"official":{"repos":["weipu-zhang/storm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/transformers-as-decision-makers-provable-in","slug":"transformers-as-decision-makers-provable-in","title":"Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining","date":"2023-10-12","arxiv_id":"2310.08566","repositories_listed":1,"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":5,"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/transformers-as-decision-makers-provable-in#ran","syntology_url":"https://syntology.ai/paper/2310.08566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08566"}},"official":{"repos":["licong-lin/in-context-rl"],"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/universal-visual-decomposer-long-horizon","slug":"universal-visual-decomposer-long-horizon","title":"Universal Visual Decomposer: Long-Horizon Manipulation Made Easy","date":"2023-10-12","arxiv_id":"2310.08581","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/universal-visual-decomposer-long-horizon#ran","syntology_url":"https://syntology.ai/paper/2310.08581","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08581"}},"official":null}},{"url":"/paper/revisiting-plasticity-in-visual-reinforcement","slug":"revisiting-plasticity-in-visual-reinforcement","title":"Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages","date":"2023-10-11","arxiv_id":"2310.07418","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/revisiting-plasticity-in-visual-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2310.07418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07418"}},"official":{"repos":["Guozheng-Ma/Adaptive-Replay-Ratio"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/imitation-learning-from-observation-with","slug":"imitation-learning-from-observation-with","title":"Imitation Learning from Observation with Automatic Discount Scheduling","date":"2023-10-11","arxiv_id":"2310.07433","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/imitation-learning-from-observation-with#ran","syntology_url":"https://syntology.ai/paper/2310.07433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07433"}},"official":null}},{"url":"/paper/boosting-continuous-control-with-consistency","slug":"boosting-continuous-control-with-consistency","title":"Boosting Continuous Control with Consistency Policy","date":"2023-10-10","arxiv_id":"2310.06343","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":1,"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/boosting-continuous-control-with-consistency#ran","syntology_url":"https://syntology.ai/paper/2310.06343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06343"}},"official":{"repos":["cccedric/cpql"],"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/diffcps-diffusion-model-based-constrained","slug":"diffcps-diffusion-model-based-constrained","title":"DiffCPS: Diffusion Model based Constrained Policy Search for Offline Reinforcement Learning","date":"2023-10-09","arxiv_id":"2310.05333","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":4,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/diffcps-diffusion-model-based-constrained#ran","syntology_url":"https://syntology.ai/paper/2310.05333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05333"}},"official":{"repos":["felix-thu/DiffCPS"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-neuron-segmentation-with","slug":"self-supervised-neuron-segmentation-with","title":"Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning","date":"2023-10-06","arxiv_id":"2310.04148","repositories_listed":1,"syntology":{"n":24,"n_ran":20,"n_constructed":4,"n_ran_checked":18,"n_instrument":2,"n_unverified":4,"n_honours":2,"n_violates":1,"n_no_contract":15,"n_pointer_only":24,"phrase":"20 ran (of which 4 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 1 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/self-supervised-neuron-segmentation-with#ran","syntology_url":"https://syntology.ai/paper/2310.04148","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04148"}},"official":{"repos":["ydchen0806/dbmim"],"state":"official (archive's flag): 20 ran","n_ran":20,"n_constructed":4,"n_ran_no_instrument_failure":18,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-uniform-sampling-offline-reinforcement-1","slug":"beyond-uniform-sampling-offline-reinforcement-1","title":"Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets","date":"2023-10-06","arxiv_id":"2310.04413","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 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","sample_list":"/paper/beyond-uniform-sampling-offline-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2310.04413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04413"}},"official":{"repos":["Improbable-AI/dw-offline-rl"],"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/lesson-learning-to-integrate-exploration","slug":"lesson-learning-to-integrate-exploration","title":"LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework","date":"2023-10-05","arxiv_id":"2310.03342","repositories_listed":1,"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":1,"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/lesson-learning-to-integrate-exploration#ran","syntology_url":"https://syntology.ai/paper/2310.03342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03342"}},"official":{"repos":["beanie00/lesson"],"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/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/pre-training-with-synthetic-data-helps","slug":"pre-training-with-synthetic-data-helps","title":"Pre-training with Synthetic Data Helps Offline Reinforcement Learning","date":"2023-10-01","arxiv_id":"2310.00771","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pre-training-with-synthetic-data-helps#ran","syntology_url":"https://syntology.ai/paper/2310.00771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00771"}},"official":{"repos":["victor-wang-902/synthetic-pretrain-rl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/combining-spatial-and-temporal-abstraction-in","slug":"combining-spatial-and-temporal-abstraction-in","title":"Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning","date":"2023-09-30","arxiv_id":"2310.00229","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/combining-spatial-and-temporal-abstraction-in#ran","syntology_url":"https://syntology.ai/paper/2310.00229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00229"}},"official":{"repos":["mila-iqia/skipper"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/harmony-world-models-boosting-sample","slug":"harmony-world-models-boosting-sample","title":"HarmonyDream: Task Harmonization Inside World Models","date":"2023-09-30","arxiv_id":"2310.00344","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/harmony-world-models-boosting-sample#ran","syntology_url":"https://syntology.ai/paper/2310.00344","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00344"}},"official":{"repos":["thuml/harmonydream"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-robust-offline-to-online","slug":"towards-robust-offline-to-online","title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness","date":"2023-09-29","arxiv_id":"2309.16973","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-robust-offline-to-online#ran","syntology_url":"https://syntology.ai/paper/2309.16973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16973"}},"official":{"repos":["battlewen/ro2o"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rladapter-bridging-large-language-models-to","slug":"rladapter-bridging-large-language-models-to","title":"AdaRefiner: Refining Decisions of Language Models with Adaptive Feedback","date":"2023-09-29","arxiv_id":"2309.17176","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rladapter-bridging-large-language-models-to#ran","syntology_url":"https://syntology.ai/paper/2309.17176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17176"}},"official":{"repos":["pku-rl/adarefiner"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/estimation-and-inference-in-distributional","slug":"estimation-and-inference-in-distributional","title":"Estimation and Inference in Distributional Reinforcement Learning","date":"2023-09-29","arxiv_id":"2309.17262","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/estimation-and-inference-in-distributional#ran","syntology_url":"https://syntology.ai/paper/2309.17262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17262"}},"official":{"repos":["zhangliangyu32/estimationandinferencedistributionalrl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cleanba-a-reproducible-and-efficient","slug":"cleanba-a-reproducible-and-efficient","title":"Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform","date":"2023-09-29","arxiv_id":"2310.00036","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"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) · 4 unverified","sample_list":"/paper/cleanba-a-reproducible-and-efficient#ran","syntology_url":"https://syntology.ai/paper/2310.00036","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00036"}},"official":{"repos":["vwxyzjn/cleanba"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/rllte-long-term-evolution-project-of","slug":"rllte-long-term-evolution-project-of","title":"RLLTE: Long-Term Evolution Project of Reinforcement Learning","date":"2023-09-28","arxiv_id":"2309.16382","repositories_listed":2,"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/rllte-long-term-evolution-project-of#ran","syntology_url":"https://syntology.ai/paper/2309.16382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16382"}},"official":{"repos":["RLE-Foundation/rllte"],"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/tempo-adaptation-in-non-stationary-1","slug":"tempo-adaptation-in-non-stationary-1","title":"Tempo Adaptation in Non-stationary Reinforcement Learning","date":"2023-09-26","arxiv_id":"2309.14989","repositories_listed":1,"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":2,"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/tempo-adaptation-in-non-stationary-1#ran","syntology_url":"https://syntology.ai/paper/2309.14989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.14989"}},"official":{"repos":["hyunin-lee/TempoRL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/conservative-world-models","slug":"conservative-world-models","title":"Zero-Shot Reinforcement Learning from Low Quality Data","date":"2023-09-26","arxiv_id":"2309.15178","repositories_listed":2,"syntology":{"n":18,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/conservative-world-models#ran","syntology_url":"https://syntology.ai/paper/2309.15178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15178"}},"official":{"repos":["enjeeneer/conservative-world-models","enjeeneer/zero-shot-rl"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/counterfactual-conservative-q-learning-for-1","slug":"counterfactual-conservative-q-learning-for-1","title":"Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning","date":"2023-09-22","arxiv_id":"2309.12696","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":3,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/counterfactual-conservative-q-learning-for-1#ran","syntology_url":"https://syntology.ai/paper/2309.12696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12696"}},"official":{"repos":["thu-rllab/CFCQL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/a-bayesian-approach-to-robust-inverse","slug":"a-bayesian-approach-to-robust-inverse","title":"A Bayesian Approach to Robust Inverse Reinforcement Learning","date":"2023-09-15","arxiv_id":"2309.08571","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/a-bayesian-approach-to-robust-inverse#ran","syntology_url":"https://syntology.ai/paper/2309.08571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.08571"}},"official":{"repos":["ran-weii/bmirl_tf"],"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/offline-prompt-evaluation-and-optimization","slug":"offline-prompt-evaluation-and-optimization","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","date":"2023-09-13","arxiv_id":"2309.06553","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/offline-prompt-evaluation-and-optimization#ran","syntology_url":"https://syntology.ai/paper/2309.06553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06553"}},"official":{"repos":["holarissun/prompt-oirl","vanderschaarlab/prompt-oirl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"cf65a0f01ec6baf9f19a446cad1aefda6f21790ff4a0b08b9cf32e7138cb06bd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}