{"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-1/papers/ran/4","list_of":"/task/reinforcement-learning-1","task":"Reinforcement Learning (RL)","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":4,"pages_in_order":15,"rows_per_page":100,"rows":[301,400],"of":1416,"counts":{"archive_papers_tagged":15113,"with_a_code_link":4749,"where_syntology_ran_a_sample":1416,"not_listed_spam_title":0,"listed":15113,"listed_where_code_ran":1416,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1186,"every_run_a_failure_of_syntologys_instrument":230,"listed_with_a_run_with_no_instrument_failure":1186,"listed_every_run_a_failure_of_syntologys_instrument":230,"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-1/papers/ran/1","prev":"/task/reinforcement-learning-1/papers/ran/3","next":"/task/reinforcement-learning-1/papers/ran/5","papers":[{"url":"/paper/craftax-a-lightning-fast-benchmark-for-open","slug":"craftax-a-lightning-fast-benchmark-for-open","title":"Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning","date":"2024-02-26","arxiv_id":"2402.16801","repositories_listed":1,"syntology":{"n":16,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":14,"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) · 14 unverified","sample_list":"/paper/craftax-a-lightning-fast-benchmark-for-open#ran","syntology_url":"https://syntology.ai/paper/2402.16801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16801"}},"official":{"repos":["michaeltmatthews/craftax"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/how-can-llm-guide-rl-a-value-based-approach","slug":"how-can-llm-guide-rl-a-value-based-approach","title":"How Can LLM Guide RL? A Value-Based Approach","date":"2024-02-25","arxiv_id":"2402.16181","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/how-can-llm-guide-rl-a-value-based-approach#ran","syntology_url":"https://syntology.ai/paper/2402.16181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16181"}},"official":{"repos":["agentification/language-integrated-vi"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/himap-learning-heuristics-informed-policies","slug":"himap-learning-heuristics-informed-policies","title":"HiMAP: Learning Heuristics-Informed Policies for Large-Scale Multi-Agent Pathfinding","date":"2024-02-23","arxiv_id":"2402.15546","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/himap-learning-heuristics-informed-policies#ran","syntology_url":"https://syntology.ai/paper/2402.15546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15546"}},"official":{"repos":["kaist-silab/himap"],"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/foundation-policies-with-hilbert","slug":"foundation-policies-with-hilbert","title":"Foundation Policies with Hilbert Representations","date":"2024-02-23","arxiv_id":"2402.15567","repositories_listed":2,"syntology":{"n":16,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":16,"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) · 9 unverified","sample_list":"/paper/foundation-policies-with-hilbert#ran","syntology_url":"https://syntology.ai/paper/2402.15567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15567"}},"official":{"repos":["seohongpark/hilp"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/reflect-rl-two-player-online-rl-fine-tuning","slug":"reflect-rl-two-player-online-rl-fine-tuning","title":"Reflect-RL: Two-Player Online RL Fine-Tuning for LMs","date":"2024-02-20","arxiv_id":"2402.12621","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/reflect-rl-two-player-online-rl-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2402.12621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12621"}},"official":{"repos":["zhourunlong/reflect-rl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-critical-evaluation-of-ai-feedback-for","slug":"a-critical-evaluation-of-ai-feedback-for","title":"A Critical Evaluation of AI Feedback for Aligning Large Language Models","date":"2024-02-19","arxiv_id":"2402.12366","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"9 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-critical-evaluation-of-ai-feedback-for#ran","syntology_url":"https://syntology.ai/paper/2402.12366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12366"}},"official":{"repos":["architsharma97/dpo-rlaif"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/policy-learning-for-off-dynamics-rl-with","slug":"policy-learning-for-off-dynamics-rl-with","title":"Policy Learning for Off-Dynamics RL with Deficient Support","date":"2024-02-16","arxiv_id":"2402.10765","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":2,"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/policy-learning-for-off-dynamics-rl-with#ran","syntology_url":"https://syntology.ai/paper/2402.10765","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10765"}},"official":{"repos":["linhlpv/DADS"],"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/performative-reinforcement-learning-in","slug":"performative-reinforcement-learning-in","title":"Performative Reinforcement Learning in Gradually Shifting Environments","date":"2024-02-15","arxiv_id":"2402.09838","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":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/performative-reinforcement-learning-in#ran","syntology_url":"https://syntology.ai/paper/2402.09838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09838"}},"official":{"repos":["bsen/performative-rl-gradually-shifting-envs","rank-and-files/performative-rl-gradually-shifting-envs"],"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/jack-of-all-trades-master-of-some-a-multi","slug":"jack-of-all-trades-master-of-some-a-multi","title":"Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent","date":"2024-02-15","arxiv_id":"2402.09844","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"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) · 5 unverified","sample_list":"/paper/jack-of-all-trades-master-of-some-a-multi#ran","syntology_url":"https://syntology.ai/paper/2402.09844","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09844"}},"official":{"repos":["huggingface/jat"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/rewards-in-context-multi-objective-alignment","slug":"rewards-in-context-multi-objective-alignment","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","date":"2024-02-15","arxiv_id":"2402.10207","repositories_listed":2,"syntology":{"n":10,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/rewards-in-context-multi-objective-alignment#ran","syntology_url":"https://syntology.ai/paper/2402.10207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10207"}},"official":{"repos":["yangrui2015/ric"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/conservative-and-risk-aware-offline-multi","slug":"conservative-and-risk-aware-offline-multi","title":"Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning","date":"2024-02-13","arxiv_id":"2402.08421","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/conservative-and-risk-aware-offline-multi#ran","syntology_url":"https://syntology.ai/paper/2402.08421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08421"}},"official":{"repos":["eslam211/conservative-and-distributional-marl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/entropy-regularized-token-level-policy","slug":"entropy-regularized-token-level-policy","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement","date":"2024-02-09","arxiv_id":"2402.06700","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/entropy-regularized-token-level-policy#ran","syntology_url":"https://syntology.ai/paper/2402.06700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06700"}},"official":{"repos":["morning9393/etpo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/monitored-markov-decision-processes","slug":"monitored-markov-decision-processes","title":"Monitored Markov Decision Processes","date":"2024-02-09","arxiv_id":"2402.06819","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/monitored-markov-decision-processes#ran","syntology_url":"https://syntology.ai/paper/2402.06819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06819"}},"official":{"repos":["amiithinks/mon_mdp_aamas24"],"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/model-based-rl-for-mean-field-games-is-not","slug":"model-based-rl-for-mean-field-games-is-not","title":"Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL","date":"2024-02-08","arxiv_id":"2402.05724","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/model-based-rl-for-mean-field-games-is-not#ran","syntology_url":"https://syntology.ai/paper/2402.05724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05724"}},"official":{"repos":["jiaweihhuang/heuristic_mebp"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/qgfn-controllable-greediness-with-action","slug":"qgfn-controllable-greediness-with-action","title":"QGFN: Controllable Greediness with Action Values","date":"2024-02-07","arxiv_id":"2402.05234","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/qgfn-controllable-greediness-with-action#ran","syntology_url":"https://syntology.ai/paper/2402.05234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05234"}},"official":{"repos":["yunglau/QGFN"],"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/seabo-a-simple-search-based-method-for","slug":"seabo-a-simple-search-based-method-for","title":"SEABO: A Simple Search-Based Method for Offline Imitation Learning","date":"2024-02-06","arxiv_id":"2402.03807","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/seabo-a-simple-search-based-method-for#ran","syntology_url":"https://syntology.ai/paper/2402.03807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03807"}},"official":{"repos":["dmksjfl/seabo"],"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/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/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/hyperagent-a-simple-scalable-efficient-and","slug":"hyperagent-a-simple-scalable-efficient-and","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","date":"2024-02-05","arxiv_id":"2402.10228","repositories_listed":3,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/hyperagent-a-simple-scalable-efficient-and#ran","syntology_url":"https://syntology.ai/paper/2402.10228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10228"}},"official":{"repos":["szrlee/hyperagent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/value-aided-conditional-supervised-learning","slug":"value-aided-conditional-supervised-learning","title":"Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning","date":"2024-02-03","arxiv_id":"2402.02017","repositories_listed":0,"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/value-aided-conditional-supervised-learning#ran","syntology_url":"https://syntology.ai/paper/2402.02017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02017"}},"official":null}},{"url":"/paper/odice-revealing-the-mystery-of-distribution","slug":"odice-revealing-the-mystery-of-distribution","title":"ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update","date":"2024-02-01","arxiv_id":"2402.00348","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":1,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"8 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/odice-revealing-the-mystery-of-distribution#ran","syntology_url":"https://syntology.ai/paper/2402.00348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00348"}},"official":{"repos":["maoliyuan/odice-pytorch"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-efficient-and-exact-optimization-of","slug":"towards-efficient-and-exact-optimization-of","title":"Towards Efficient Exact Optimization of Language Model Alignment","date":"2024-02-01","arxiv_id":"2402.00856","repositories_listed":2,"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/towards-efficient-and-exact-optimization-of#ran","syntology_url":"https://syntology.ai/paper/2402.00856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00856"}},"official":{"repos":["haozheji/exact-optimization"],"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/expert-proximity-as-surrogate-rewards-for","slug":"expert-proximity-as-surrogate-rewards-for","title":"Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning","date":"2024-02-01","arxiv_id":"2402.01057","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/expert-proximity-as-surrogate-rewards-for#ran","syntology_url":"https://syntology.ai/paper/2402.01057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01057"}},"official":{"repos":["stanl1y/tdil"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/true-knowledge-comes-from-practice-aligning","slug":"true-knowledge-comes-from-practice-aligning","title":"True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning","date":"2024-01-25","arxiv_id":"2401.14151","repositories_listed":1,"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":3,"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/true-knowledge-comes-from-practice-aligning#ran","syntology_url":"https://syntology.ai/paper/2401.14151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14151"}},"official":{"repos":["weihaotan/twosome"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dittogym-learning-to-control-soft-shape","slug":"dittogym-learning-to-control-soft-shape","title":"DittoGym: Learning to Control Soft Shape-Shifting Robots","date":"2024-01-24","arxiv_id":"2401.13231","repositories_listed":2,"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/dittogym-learning-to-control-soft-shape#ran","syntology_url":"https://syntology.ai/paper/2401.13231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.13231"}},"official":{"repos":["suninghuang19/cfp","suninghuang19/dittogym"],"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/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/hazard-challenge-embodied-decision-making-in","slug":"hazard-challenge-embodied-decision-making-in","title":"HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments","date":"2024-01-23","arxiv_id":"2401.12975","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":0,"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/hazard-challenge-embodied-decision-making-in#ran","syntology_url":"https://syntology.ai/paper/2401.12975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12975"}},"official":{"repos":["umass-foundation-model/hazard"],"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/open-the-black-box-step-based-policy-updates","slug":"open-the-black-box-step-based-policy-updates","title":"Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning","date":"2024-01-21","arxiv_id":"2401.11437","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"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) · 2 unverified","sample_list":"/paper/open-the-black-box-step-based-policy-updates#ran","syntology_url":"https://syntology.ai/paper/2401.11437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11437"}},"official":{"repos":["brucegeli/tce_rl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/closing-the-gap-between-td-learning-and","slug":"closing-the-gap-between-td-learning-and","title":"Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View","date":"2024-01-20","arxiv_id":"2401.11237","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/closing-the-gap-between-td-learning-and#ran","syntology_url":"https://syntology.ai/paper/2401.11237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11237"}},"official":{"repos":["rajghugare19/stitching-is-combinatorial-generalisation"],"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/freed-improving-rl-agents-for-fragment-based","slug":"freed-improving-rl-agents-for-fragment-based","title":"FREED++: Improving RL Agents for Fragment-Based Molecule Generation by Thorough Reproduction","date":"2024-01-18","arxiv_id":"2401.09840","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/freed-improving-rl-agents-for-fragment-based#ran","syntology_url":"https://syntology.ai/paper/2401.09840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09840"}},"official":{"repos":["airi-institute/ffreed"],"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":["official"]}}},{"url":"/paper/bridging-state-and-history-representations","slug":"bridging-state-and-history-representations","title":"Bridging State and History Representations: Understanding Self-Predictive RL","date":"2024-01-17","arxiv_id":"2401.08898","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"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) · 1 unverified","sample_list":"/paper/bridging-state-and-history-representations#ran","syntology_url":"https://syntology.ai/paper/2401.08898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08898"}},"official":{"repos":["twni2016/self-predictive-rl"],"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":["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/learning-from-sparse-offline-datasets-via","slug":"learning-from-sparse-offline-datasets-via","title":"Learning from Sparse Offline Datasets via Conservative Density Estimation","date":"2024-01-16","arxiv_id":"2401.08819","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-from-sparse-offline-datasets-via#ran","syntology_url":"https://syntology.ai/paper/2401.08819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08819"}},"official":{"repos":["czp16/cde-offline-rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"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/improving-large-language-models-via-fine","slug":"improving-large-language-models-via-fine","title":"Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint","date":"2024-01-11","arxiv_id":"2401.06081","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":10,"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) · 1 unverified","sample_list":"/paper/improving-large-language-models-via-fine#ran","syntology_url":"https://syntology.ai/paper/2401.06081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06081"}},"official":{"repos":["rucaibox/rlmec"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"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/large-language-models-as-traffic-signal","slug":"large-language-models-as-traffic-signal","title":"LLMLight: Large Language Models as Traffic Signal Control Agents","date":"2023-12-26","arxiv_id":"2312.16044","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":1,"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/large-language-models-as-traffic-signal#ran","syntology_url":"https://syntology.ai/paper/2312.16044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.16044"}},"official":{"repos":["usail-hkust/llmtscs"],"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/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/diffusion-reward-learning-rewards-via","slug":"diffusion-reward-learning-rewards-via","title":"Diffusion Reward: Learning Rewards via Conditional Video Diffusion","date":"2023-12-21","arxiv_id":"2312.14134","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/diffusion-reward-learning-rewards-via#ran","syntology_url":"https://syntology.ai/paper/2312.14134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14134"}},"official":{"repos":["TEA-Lab/diffusion_reward"],"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/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-to-act-without-actions","slug":"learning-to-act-without-actions","title":"Learning to Act without Actions","date":"2023-12-17","arxiv_id":"2312.10812","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"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) · 4 unverified","sample_list":"/paper/learning-to-act-without-actions#ran","syntology_url":"https://syntology.ai/paper/2312.10812","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10812"}},"official":{"repos":["schmidtdominik/lapo"],"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/world-models-via-policy-guided-trajectory","slug":"world-models-via-policy-guided-trajectory","title":"World Models via Policy-Guided Trajectory Diffusion","date":"2023-12-13","arxiv_id":"2312.08533","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":2,"n_no_contract":2,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/world-models-via-policy-guided-trajectory#ran","syntology_url":"https://syntology.ai/paper/2312.08533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08533"}},"official":{"repos":["marc-rigter/polygrad-world-models"],"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/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/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/mocha-multi-objective-reinforcement","slug":"mocha-multi-objective-reinforcement","title":"Mitigating Open-Vocabulary Caption Hallucinations","date":"2023-12-06","arxiv_id":"2312.03631","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":15,"phrase":"10 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; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mocha-multi-objective-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2312.03631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03631"}},"official":{"repos":["assafbk/mocha_code"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/language-model-alignment-with-elastic-reset-1","slug":"language-model-alignment-with-elastic-reset-1","title":"Language Model Alignment with Elastic Reset","date":"2023-12-06","arxiv_id":"2312.07551","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/language-model-alignment-with-elastic-reset-1#ran","syntology_url":"https://syntology.ai/paper/2312.07551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07551"}},"official":{"repos":["mnoukhov/elastic-reset"],"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/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/learning-curricula-in-open-ended-worlds","slug":"learning-curricula-in-open-ended-worlds","title":"Learning Curricula in Open-Ended Worlds","date":"2023-12-03","arxiv_id":"2312.03126","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/learning-curricula-in-open-ended-worlds#ran","syntology_url":"https://syntology.ai/paper/2312.03126","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03126"}},"official":{"repos":["facebookresearch/dcd"],"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/ddxt-deep-generative-transformer-models-for","slug":"ddxt-deep-generative-transformer-models-for","title":"DDxT: Deep Generative Transformer Models for Differential Diagnosis","date":"2023-12-02","arxiv_id":"2312.01242","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":5,"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 5 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/ddxt-deep-generative-transformer-models-for#ran","syntology_url":"https://syntology.ai/paper/2312.01242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01242"}},"official":{"repos":["MahmudulAlam/Differential-Diagnosis-Using-Transformers"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":5,"n_ran_no_instrument_failure":7,"n_unverified":0,"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/jaxmarl-multi-agent-rl-environments-in-jax","slug":"jaxmarl-multi-agent-rl-environments-in-jax","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","date":"2023-11-16","arxiv_id":"2311.10090","repositories_listed":3,"syntology":{"n":23,"n_ran":22,"n_constructed":0,"n_ran_checked":22,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":22,"n_pointer_only":0,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/jaxmarl-multi-agent-rl-environments-in-jax#ran","syntology_url":"https://syntology.ai/paper/2311.10090","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.10090"}},"official":{"repos":["flairox/jaxmarl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/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/combinatorial-optimization-with-policy","slug":"combinatorial-optimization-with-policy","title":"Combinatorial Optimization with Policy Adaptation using Latent Space Search","date":"2023-11-13","arxiv_id":"2311.13569","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":7,"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/combinatorial-optimization-with-policy#ran","syntology_url":"https://syntology.ai/paper/2311.13569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13569"}},"official":{"repos":["instadeepai/compass"],"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/accelerating-exploration-with-unlabeled-prior-1","slug":"accelerating-exploration-with-unlabeled-prior-1","title":"Accelerating Exploration with Unlabeled Prior Data","date":"2023-11-09","arxiv_id":"2311.05067","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":2,"n_ran_checked":9,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":14,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/accelerating-exploration-with-unlabeled-prior-1#ran","syntology_url":"https://syntology.ai/paper/2311.05067","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05067"}},"official":{"repos":["facebookresearch/explore"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/uni-o4-unifying-online-and-offline-deep","slug":"uni-o4-unifying-online-and-offline-deep","title":"Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization","date":"2023-11-06","arxiv_id":"2311.03351","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uni-o4-unifying-online-and-offline-deep#ran","syntology_url":"https://syntology.ai/paper/2311.03351","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.03351"}},"official":{"repos":["Lei-Kun/Uni-O4"],"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/alberdice-addressing-out-of-distribution-1","slug":"alberdice-addressing-out-of-distribution-1","title":"AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation","date":"2023-11-03","arxiv_id":"2311.02194","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":2,"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 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/alberdice-addressing-out-of-distribution-1#ran","syntology_url":"https://syntology.ai/paper/2311.02194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.02194"}},"official":{"repos":["dematsunaga/alberdice"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"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/unleashing-the-power-of-pre-trained-language","slug":"unleashing-the-power-of-pre-trained-language","title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning","date":"2023-10-31","arxiv_id":"2310.20587","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/unleashing-the-power-of-pre-trained-language#ran","syntology_url":"https://syntology.ai/paper/2310.20587","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.20587"}},"official":{"repos":["srzer/LaMo-2023"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"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/train-once-get-a-family-state-adaptive-1","slug":"train-once-get-a-family-state-adaptive-1","title":"Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning","date":"2023-10-27","arxiv_id":"2310.17966","repositories_listed":1,"syntology":{"n":25,"n_ran":17,"n_constructed":5,"n_ran_checked":12,"n_instrument":5,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"17 ran (of which 5 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/train-once-get-a-family-state-adaptive-1#ran","syntology_url":"https://syntology.ai/paper/2310.17966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17966"}},"official":{"repos":["leaplabthu/famo2o"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":5,"n_ran_no_instrument_failure":12,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/counterfactual-augmented-importance-sampling-1","slug":"counterfactual-augmented-importance-sampling-1","title":"Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation","date":"2023-10-26","arxiv_id":"2310.17146","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/counterfactual-augmented-importance-sampling-1#ran","syntology_url":"https://syntology.ai/paper/2310.17146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17146"}},"official":{"repos":["mld3/counterfactualannot-semiope"],"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/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/td-mpc2-scalable-robust-world-models-for","slug":"td-mpc2-scalable-robust-world-models-for","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","date":"2023-10-25","arxiv_id":"2310.16828","repositories_listed":3,"syntology":{"n":16,"n_ran":12,"n_constructed":4,"n_ran_checked":6,"n_instrument":6,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"12 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/td-mpc2-scalable-robust-world-models-for#ran","syntology_url":"https://syntology.ai/paper/2310.16828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16828"}},"official":null}},{"url":"/paper/diversify-question-generation-with-retrieval","slug":"diversify-question-generation-with-retrieval","title":"Diversify Question Generation with Retrieval-Augmented Style Transfer","date":"2023-10-23","arxiv_id":"2310.14503","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"phrase":"9 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/diversify-question-generation-with-retrieval#ran","syntology_url":"https://syntology.ai/paper/2310.14503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14503"}},"official":{"repos":["gouqi666/rast"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"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/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/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/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/metra-scalable-unsupervised-rl-with-metric","slug":"metra-scalable-unsupervised-rl-with-metric","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","date":"2023-10-13","arxiv_id":"2310.08887","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/metra-scalable-unsupervised-rl-with-metric#ran","syntology_url":"https://syntology.ai/paper/2310.08887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08887"}},"official":{"repos":["seohongpark/metra"],"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-retraining-for-online-rl-decoupled","slug":"offline-retraining-for-online-rl-decoupled","title":"Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias","date":"2023-10-12","arxiv_id":"2310.08558","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"7 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/offline-retraining-for-online-rl-decoupled#ran","syntology_url":"https://syntology.ai/paper/2310.08558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08558"}},"official":{"repos":["MaxSobolMark/OOO"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/aligning-language-models-with-human-1","slug":"aligning-language-models-with-human-1","title":"Aligning Language Models with Human Preferences via a Bayesian Approach","date":"2023-10-09","arxiv_id":"2310.05782","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":2,"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/aligning-language-models-with-human-1#ran","syntology_url":"https://syntology.ai/paper/2310.05782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05782"}},"official":{"repos":["wangjs9/aligned-dpm"],"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/dsac-t-distributional-soft-actor-critic-with","slug":"dsac-t-distributional-soft-actor-critic-with","title":"Distributional Soft Actor-Critic with Three Refinements","date":"2023-10-09","arxiv_id":"2310.05858","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/dsac-t-distributional-soft-actor-critic-with#ran","syntology_url":"https://syntology.ai/paper/2310.05858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05858"}},"official":{"repos":["jingliang-duan/dsac-t","jingliang-duan/dsac-v2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"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/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/consistency-models-as-a-rich-and-efficient","slug":"consistency-models-as-a-rich-and-efficient","title":"Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning","date":"2023-09-29","arxiv_id":"2309.16984","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":1,"n_ran_checked":6,"n_instrument":3,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/consistency-models-as-a-rich-and-efficient#ran","syntology_url":"https://syntology.ai/paper/2309.16984","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16984"}},"official":{"repos":["quantumiracle/consistency_model_for_reinforcement_learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["community","official","unlocated"]}}},{"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/motif-intrinsic-motivation-from-artificial","slug":"motif-intrinsic-motivation-from-artificial","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","date":"2023-09-29","arxiv_id":"2310.00166","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":5,"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/motif-intrinsic-motivation-from-artificial#ran","syntology_url":"https://syntology.ai/paper/2310.00166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00166"}},"official":{"repos":["facebookresearch/motif"],"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/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/kuaisim-a-comprehensive-simulator-for","slug":"kuaisim-a-comprehensive-simulator-for","title":"KuaiSim: A Comprehensive Simulator for Recommender Systems","date":"2023-09-22","arxiv_id":"2309.12645","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kuaisim-a-comprehensive-simulator-for#ran","syntology_url":"https://syntology.ai/paper/2309.12645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12645"}},"official":{"repos":["applied-machine-learning-lab/kuaisim"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reasoning-with-latent-diffusion-in-offline","slug":"reasoning-with-latent-diffusion-in-offline","title":"Reasoning with Latent Diffusion in Offline Reinforcement Learning","date":"2023-09-12","arxiv_id":"2309.06599","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"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) · 2 unverified","sample_list":"/paper/reasoning-with-latent-diffusion-in-offline#ran","syntology_url":"https://syntology.ai/paper/2309.06599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.06599"}},"official":{"repos":["ldcq/ldcq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-reinforcement-learning-training","slug":"improving-reinforcement-learning-training","title":"Improving Generalization in Reinforcement Learning Training Regimes for Social Robot Navigation","date":"2023-08-29","arxiv_id":"2308.14947","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/improving-reinforcement-learning-training#ran","syntology_url":"https://syntology.ai/paper/2308.14947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14947"}},"official":{"repos":["raise-lab/soc-nav-training"],"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/language-reward-modulation-for-pretraining","slug":"language-reward-modulation-for-pretraining","title":"Language Reward Modulation for Pretraining Reinforcement Learning","date":"2023-08-23","arxiv_id":"2308.12270","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":1,"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/language-reward-modulation-for-pretraining#ran","syntology_url":"https://syntology.ai/paper/2308.12270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12270"}},"official":{"repos":["ademiadeniji/lamp"],"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/dialogue-for-prompting-a-policy-gradient","slug":"dialogue-for-prompting-a-policy-gradient","title":"Dialogue for Prompting: a Policy-Gradient-Based Discrete Prompt Generation for Few-shot Learning","date":"2023-08-14","arxiv_id":"2308.07272","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":1,"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/dialogue-for-prompting-a-policy-gradient#ran","syntology_url":"https://syntology.ai/paper/2308.07272","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07272"}},"official":{"repos":["czx-li/DP2O"],"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/esrl-efficient-sampling-based-reinforcement","slug":"esrl-efficient-sampling-based-reinforcement","title":"ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation","date":"2023-08-04","arxiv_id":"2308.02223","repositories_listed":2,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/esrl-efficient-sampling-based-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2308.02223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.02223"}},"official":{"repos":["wangclnlp/DeepSpeed-Chat-Extension"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-based-non","slug":"reinforcement-learning-based-non","title":"Reinforcement Learning-based Non-Autoregressive Solver for Traveling Salesman Problems","date":"2023-08-01","arxiv_id":"2308.00560","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/reinforcement-learning-based-non#ran","syntology_url":"https://syntology.ai/paper/2308.00560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.00560"}},"official":{"repos":["xybfight/nar4tsp"],"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/submodular-reinforcement-learning","slug":"submodular-reinforcement-learning","title":"Submodular Reinforcement Learning","date":"2023-07-25","arxiv_id":"2307.13372","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/submodular-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2307.13372","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.13372"}},"official":{"repos":["manish-pra/non-additive-rl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"6dd1f800cf2e573da7f84f91a43e9712465364d22f06a69a4c83ca638e0a362c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}