{"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/offline-rl","name":"Offline RL","slug":"offline-rl","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Playing Games","url":"/area/playing-games"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":755,"papers_with_code":310,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/offline-rl-on-d4rl","slug":"offline-rl-on-d4rl","dataset":"D4RL","dataset_url":"/dataset/d4rl","rows_in_archive":3,"metrics":["Average Reward"],"first_row_in_archive_order":{"model":"KFC","paper_title":"Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics","paper_url":"/paper/koopman-q-learning-offline-reinforcement-1","paper_date":"2021-11-02","arxiv_id":"2111.01365","code_links":[],"syntology":null}},{"leaderboard":"/sota/offline-rl-on-walker2d","slug":"offline-rl-on-walker2d","dataset":"Walker2d","dataset_url":null,"rows_in_archive":1,"metrics":["D4RL Normalized Score"],"first_row_in_archive_order":{"model":"ParPI","paper_title":"Particle Based Stochastic Policy Optimization","paper_url":"/paper/particle-based-stochastic-policy-optimization","paper_date":"2021-09-29","arxiv_id":null,"code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/d4rl","name":"D4RL","full_name":"D4RL","num_papers_in_archive":538},{"url":"/dataset/robonet","name":"RoboNet","full_name":"","num_papers_in_archive":28},{"url":"/dataset/neorl","name":"NeoRL","full_name":"","num_papers_in_archive":10},{"url":"/dataset/rl-unplugged","name":"RL Unplugged","full_name":"RL Unplugged","num_papers_in_archive":7},{"url":"/dataset/caglar","name":"RLU","full_name":"RL Unplugged","num_papers_in_archive":2},{"url":"/dataset/visuomotor-affordance-learning-val-robot","name":"Visuomotor affordance learning (VAL) robot interaction dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/neorl2","name":"NeoRL-2","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/dqn-replay-dataset","name":"DQN Replay Dataset"}],"parent_tasks":[{"url":"/task/general-reinforcement-learning","name":"General Reinforcement Learning"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":8,"rows_per_page":100,"shown":100,"of":755,"of_with_code":310,"tagged_in_all":755,"counts":{"archive_papers_tagged":755,"with_a_code_link":310,"where_syntology_ran_a_sample":164,"not_listed_spam_title":0,"listed":755,"listed_where_code_ran":164,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":135,"every_run_a_failure_of_syntologys_instrument":29,"listed_with_a_run_with_no_instrument_failure":135,"listed_every_run_a_failure_of_syntologys_instrument":29,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/decision-transformer-reinforcement-learning","slug":"decision-transformer-reinforcement-learning","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","date":"2021-06-02","arxiv_id":"2106.01345","repositories_listed":20,"syntology":{"n":26,"n_ran":17,"n_constructed":10,"n_ran_checked":12,"n_instrument":5,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":8,"phrase":"17 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/decision-transformer-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2106.01345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01345"}},"official":{"repos":["kzl/decision-transformer"],"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/conservative-q-learning-for-offline","slug":"conservative-q-learning-for-offline","title":"Conservative Q-Learning for Offline Reinforcement Learning","date":"2020-06-08","arxiv_id":"2006.04779","repositories_listed":18,"syntology":{"n":34,"n_ran":31,"n_constructed":5,"n_ran_checked":22,"n_instrument":9,"n_unverified":3,"n_honours":5,"n_violates":2,"n_no_contract":15,"n_pointer_only":19,"phrase":"31 ran (of which 5 constructed an object rather than computing a result; 22 with no instrument failure: 5 honoured, 2 violated, 15 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/conservative-q-learning-for-offline#ran","syntology_url":"https://syntology.ai/paper/2006.04779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04779"}},"official":{"repos":["aviralkumar2907/CQL"],"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/offline-reinforcement-learning-with-implicit","slug":"offline-reinforcement-learning-with-implicit","title":"Offline Reinforcement Learning with Implicit Q-Learning","date":"2021-10-12","arxiv_id":"2110.06169","repositories_listed":17,"syntology":{"n":58,"n_ran":45,"n_constructed":23,"n_ran_checked":36,"n_instrument":9,"n_unverified":13,"n_honours":0,"n_violates":0,"n_no_contract":36,"n_pointer_only":23,"phrase":"45 ran (of which 23 constructed an object rather than computing a result; 36 with no instrument failure: 0 honoured, 0 violated, 36 with no contract checked; 9 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/offline-reinforcement-learning-with-implicit#ran","syntology_url":"https://syntology.ai/paper/2110.06169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06169"}},"official":{"repos":["rail-berkeley/rlkit","ikostrikov/implicit_q_learning"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/reformer-the-efficient-transformer-1","slug":"reformer-the-efficient-transformer-1","title":"Reformer: The Efficient Transformer","date":"2020-01-13","arxiv_id":"2001.04451","repositories_listed":10,"syntology":{"n":8,"n_ran":6,"n_constructed":1,"n_ran_checked":1,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 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; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/reformer-the-efficient-transformer-1#ran","syntology_url":"https://syntology.ai/paper/2001.04451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.04451"}},"official":{"repos":["google/trax"],"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/a-minimalist-approach-to-offline","slug":"a-minimalist-approach-to-offline","title":"A Minimalist Approach to Offline Reinforcement Learning","date":"2021-06-12","arxiv_id":"2106.06860","repositories_listed":8,"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/a-minimalist-approach-to-offline#ran","syntology_url":"https://syntology.ai/paper/2106.06860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06860"}},"official":{"repos":["sfujim/TD3_BC"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/transformers-are-rnns-fast-autoregressive","slug":"transformers-are-rnns-fast-autoregressive","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","date":"2020-06-29","arxiv_id":"2006.16236","repositories_listed":8,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/transformers-are-rnns-fast-autoregressive#ran","syntology_url":"https://syntology.ai/paper/2006.16236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.16236"}},"official":{"repos":["idiap/fast-transformers"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/rethinking-attention-with-performers","slug":"rethinking-attention-with-performers","title":"Rethinking Attention with Performers","date":"2020-09-30","arxiv_id":"2009.14794","repositories_listed":7,"syntology":{"n":16,"n_ran":11,"n_constructed":3,"n_ran_checked":7,"n_instrument":4,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"11 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/rethinking-attention-with-performers#ran","syntology_url":"https://syntology.ai/paper/2009.14794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.14794"}},"official":{"repos":["google-research/google-research"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/datasets-for-data-driven-reinforcement","slug":"datasets-for-data-driven-reinforcement","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","date":"2020-04-15","arxiv_id":"2004.07219","repositories_listed":7,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":6,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/datasets-for-data-driven-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2004.07219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07219"}},"official":{"repos":["rail-berkeley/d4rl","rail-berkeley/offline_rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mopo-model-based-offline-policy-optimization","slug":"mopo-model-based-offline-policy-optimization","title":"MOPO: Model-based Offline Policy Optimization","date":"2020-05-27","arxiv_id":"2005.13239","repositories_listed":6,"syntology":{"n":8,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 1 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) · 5 unverified","sample_list":"/paper/mopo-model-based-offline-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/2005.13239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.13239"}},"official":{"repos":["tianheyu927/mopo"],"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/uncertainty-based-offline-reinforcement","slug":"uncertainty-based-offline-reinforcement","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","date":"2021-10-04","arxiv_id":"2110.01548","repositories_listed":5,"syntology":{"n":21,"n_ran":13,"n_constructed":11,"n_ran_checked":12,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":6,"phrase":"13 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/uncertainty-based-offline-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2110.01548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01548"}},"official":null}},{"url":"/paper/critic-regularized-regression","slug":"critic-regularized-regression","title":"Critic Regularized Regression","date":"2020-06-26","arxiv_id":"2006.15134","repositories_listed":5,"syntology":null},{"url":"/paper/acme-a-research-framework-for-distributed","slug":"acme-a-research-framework-for-distributed","title":"Acme: A Research Framework for Distributed Reinforcement Learning","date":"2020-06-01","arxiv_id":"2006.00979","repositories_listed":5,"syntology":null},{"url":"/paper/offline-rl-with-no-ood-actions-in-sample","slug":"offline-rl-with-no-ood-actions-in-sample","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","date":"2023-03-28","arxiv_id":"2303.15810","repositories_listed":4,"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/offline-rl-with-no-ood-actions-in-sample#ran","syntology_url":"https://syntology.ai/paper/2303.15810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15810"}},"official":{"repos":["ryanxhr/ivr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-in-sample-softmax-for-offline","slug":"the-in-sample-softmax-for-offline","title":"The In-Sample Softmax for Offline Reinforcement Learning","date":"2023-02-28","arxiv_id":"2302.14372","repositories_listed":4,"syntology":null},{"url":"/paper/extreme-q-learning-maxent-rl-without-entropy","slug":"extreme-q-learning-maxent-rl-without-entropy","title":"Extreme Q-Learning: MaxEnt RL without Entropy","date":"2023-01-05","arxiv_id":"2301.02328","repositories_listed":4,"syntology":{"n":13,"n_ran":8,"n_constructed":5,"n_ran_checked":5,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"8 ran (of which 5 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) · 5 unverified","sample_list":"/paper/extreme-q-learning-maxent-rl-without-entropy#ran","syntology_url":"https://syntology.ai/paper/2301.02328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02328"}},"official":null}},{"url":"/paper/combo-conservative-offline-model-based-policy","slug":"combo-conservative-offline-model-based-policy","title":"COMBO: Conservative Offline Model-Based Policy Optimization","date":"2021-02-16","arxiv_id":"2102.08363","repositories_listed":4,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/combo-conservative-offline-model-based-policy#ran","syntology_url":"https://syntology.ai/paper/2102.08363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.08363"}},"official":null}},{"url":"/paper/deployment-efficient-reinforcement-learning","slug":"deployment-efficient-reinforcement-learning","title":"Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization","date":"2020-06-05","arxiv_id":"2006.03647","repositories_listed":4,"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/deployment-efficient-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2006.03647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03647"}},"official":{"repos":["matsuolab/BREMEN"],"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/revisiting-the-minimalist-approach-to-offline","slug":"revisiting-the-minimalist-approach-to-offline","title":"Revisiting the Minimalist Approach to Offline Reinforcement Learning","date":"2023-05-16","arxiv_id":"2305.09836","repositories_listed":3,"syntology":{"n":16,"n_ran":15,"n_constructed":0,"n_ran_checked":9,"n_instrument":6,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/revisiting-the-minimalist-approach-to-offline#ran","syntology_url":"https://syntology.ai/paper/2305.09836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.09836"}},"official":{"repos":["dt6a/rebrac"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/cal-ql-calibrated-offline-rl-pre-training-for-1","slug":"cal-ql-calibrated-offline-rl-pre-training-for-1","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","date":"2023-03-09","arxiv_id":"2303.05479","repositories_listed":3,"syntology":null},{"url":"/paper/model-based-offline-reinforcement-learning","slug":"model-based-offline-reinforcement-learning","title":"Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief","date":"2022-10-13","arxiv_id":"2210.06692","repositories_listed":3,"syntology":null},{"url":"/paper/diffusion-policies-as-an-expressive-policy","slug":"diffusion-policies-as-an-expressive-policy","title":"Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning","date":"2022-08-12","arxiv_id":"2208.06193","repositories_listed":3,"syntology":{"n":18,"n_ran":11,"n_constructed":5,"n_ran_checked":11,"n_instrument":0,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":10,"phrase":"11 ran (of which 5 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/diffusion-policies-as-an-expressive-policy#ran","syntology_url":"https://syntology.ai/paper/2208.06193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.06193"}},"official":{"repos":["zhendong-wang/diffusion-policies-for-offline-rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/cosformer-rethinking-softmax-in-attention-1","slug":"cosformer-rethinking-softmax-in-attention-1","title":"cosFormer: Rethinking Softmax in Attention","date":"2022-02-17","arxiv_id":"2202.08791","repositories_listed":3,"syntology":null},{"url":"/paper/supported-policy-optimization-for-offline","slug":"supported-policy-optimization-for-offline","title":"Supported Policy Optimization for Offline Reinforcement Learning","date":"2022-02-13","arxiv_id":"2202.06239","repositories_listed":3,"syntology":null},{"url":"/paper/adversarially-trained-actor-critic-for","slug":"adversarially-trained-actor-critic-for","title":"Adversarially Trained Actor Critic for Offline Reinforcement Learning","date":"2022-02-05","arxiv_id":"2202.02446","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarially-trained-actor-critic-for#ran","syntology_url":"https://syntology.ai/paper/2202.02446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.02446"}},"official":{"repos":["microsoft/atac"],"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":["listed","official"]}}},{"url":"/paper/near-real-world-benchmarks-for-offline","slug":"near-real-world-benchmarks-for-offline","title":"NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning","date":"2021-02-01","arxiv_id":"2102.00714","repositories_listed":3,"syntology":null},{"url":"/paper/training-frankensteins-creature-to-stack","slug":"training-frankensteins-creature-to-stack","title":"The CoSTAR Block Stacking Dataset: Learning with Workspace Constraints","date":"2018-10-27","arxiv_id":"1810.11714","repositories_listed":3,"syntology":null},{"url":"/paper/a-clean-slate-for-offline-reinforcement","slug":"a-clean-slate-for-offline-reinforcement","title":"A Clean Slate for Offline Reinforcement Learning","date":"2025-04-15","arxiv_id":"2504.11453","repositories_listed":2,"syntology":null},{"url":"/paper/flow-q-learning","slug":"flow-q-learning","title":"Flow Q-Learning","date":"2025-02-04","arxiv_id":"2502.02538","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/flow-q-learning#ran","syntology_url":"https://syntology.ai/paper/2502.02538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02538"}},"official":{"repos":["seohongpark/fql"],"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":["listed","official"]}}},{"url":"/paper/offline-reinforcement-learning-for-llm-multi","slug":"offline-reinforcement-learning-for-llm-multi","title":"Offline Reinforcement Learning for LLM Multi-Step Reasoning","date":"2024-12-20","arxiv_id":"2412.16145","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/offline-reinforcement-learning-for-llm-multi#ran","syntology_url":"https://syntology.ai/paper/2412.16145","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.16145"}},"official":{"repos":["jwhj/oreo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/q-value-regularized-transformer-for-offline","slug":"q-value-regularized-transformer-for-offline","title":"Q-value Regularized Transformer for Offline Reinforcement Learning","date":"2024-05-27","arxiv_id":"2405.17098","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/q-value-regularized-transformer-for-offline#ran","syntology_url":"https://syntology.ai/paper/2405.17098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17098"}},"official":null}},{"url":"/paper/pdit-interleaving-perception-and-decision","slug":"pdit-interleaving-perception-and-decision","title":"PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learning","date":"2023-12-26","arxiv_id":"2312.15863","repositories_listed":2,"syntology":null},{"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/understanding-predicting-and-better-resolving-1","slug":"understanding-predicting-and-better-resolving-1","title":"Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL","date":"2023-10-06","arxiv_id":"2310.04411","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":4,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/understanding-predicting-and-better-resolving-1#ran","syntology_url":"https://syntology.ai/paper/2310.04411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04411"}},"official":{"repos":["yueyang130/seem"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/alleviating-matthew-effect-of-offline","slug":"alleviating-matthew-effect-of-offline","title":"Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendation","date":"2023-07-10","arxiv_id":"2307.04571","repositories_listed":2,"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":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) · 2 unverified","sample_list":"/paper/alleviating-matthew-effect-of-offline#ran","syntology_url":"https://syntology.ai/paper/2307.04571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.04571"}},"official":{"repos":["chongminggao/dorl-codes"],"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":["listed","official"]}}},{"url":"/paper/model-bellman-inconsistency-for-model-based","slug":"model-bellman-inconsistency-for-model-based","title":"Model-Bellman Inconsistency for Model-based Offline Reinforcement Learning","date":"2023-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/unified-off-policy-learning-to-rank-a","slug":"unified-off-policy-learning-to-rank-a","title":"Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective","date":"2023-06-13","arxiv_id":"2306.07528","repositories_listed":2,"syntology":null},{"url":"/paper/policy-regularization-with-dataset-constraint","slug":"policy-regularization-with-dataset-constraint","title":"Policy Regularization with Dataset Constraint for Offline Reinforcement Learning","date":"2023-06-11","arxiv_id":"2306.06569","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 6 samples that ran constructed an object rather than computing a result","sample_list":"/paper/policy-regularization-with-dataset-constraint#ran","syntology_url":"https://syntology.ai/paper/2306.06569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.06569"}},"official":{"repos":["lamda-rl/prdc"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/offline-prioritized-experience-replay","slug":"offline-prioritized-experience-replay","title":"Decoupled Prioritized Resampling for Offline RL","date":"2023-06-08","arxiv_id":"2306.05412","repositories_listed":2,"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/offline-prioritized-experience-replay#ran","syntology_url":"https://syntology.ai/paper/2306.05412","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05412"}},"official":{"repos":["sail-sg/oper","yueyang130/odpr"],"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/explaining-rl-decisions-with-trajectories","slug":"explaining-rl-decisions-with-trajectories","title":"Explaining RL Decisions with Trajectories","date":"2023-05-06","arxiv_id":"2305.04073","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 1 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/explaining-rl-decisions-with-trajectories#ran","syntology_url":"https://syntology.ai/paper/2305.04073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.04073"}},"official":{"repos":["shripaddeshmukh/xrl_with_trajectories"],"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/leveraging-factored-action-spaces-for","slug":"leveraging-factored-action-spaces-for","title":"Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare","date":"2023-05-02","arxiv_id":"2305.01738","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/leveraging-factored-action-spaces-for#ran","syntology_url":"https://syntology.ai/paper/2305.01738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.01738"}},"official":{"repos":["mld3/offlinerl_factoredactions"],"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":["listed","official"]}}},{"url":"/paper/learning-to-control-autonomous-fleets-from","slug":"learning-to-control-autonomous-fleets-from","title":"Learning to Control Autonomous Fleets from Observation via Offline Reinforcement Learning","date":"2023-02-28","arxiv_id":"2302.14833","repositories_listed":2,"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/learning-to-control-autonomous-fleets-from#ran","syntology_url":"https://syntology.ai/paper/2302.14833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.14833"}},"official":{"repos":["carolinssc/offline-rl-amod","carolinssc/offline-rl-for-amod"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/neural-laplace-control-for-continuous-time","slug":"neural-laplace-control-for-continuous-time","title":"Neural Laplace Control for Continuous-time Delayed Systems","date":"2023-02-24","arxiv_id":"2302.12604","repositories_listed":2,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/neural-laplace-control-for-continuous-time#ran","syntology_url":"https://syntology.ai/paper/2302.12604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.12604"}},"official":{"repos":["samholt/neurallaplacecontrol","vanderschaarlab/neurallaplacecontrol"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/behavior-proximal-policy-optimization","slug":"behavior-proximal-policy-optimization","title":"Behavior Proximal Policy Optimization","date":"2023-02-22","arxiv_id":"2302.11312","repositories_listed":2,"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":0,"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/behavior-proximal-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/2302.11312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11312"}},"official":{"repos":["dragon-zhuang/bppo"],"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/direct-preference-based-policy-optimization-1","slug":"direct-preference-based-policy-optimization-1","title":"Direct Preference-based Policy Optimization without Reward Modeling","date":"2023-01-30","arxiv_id":"2301.12842","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/direct-preference-based-policy-optimization-1#ran","syntology_url":"https://syntology.ai/paper/2301.12842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12842"}},"official":{"repos":["snu-mllab/dppo"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/let-offline-rl-flow-training-conservative","slug":"let-offline-rl-flow-training-conservative","title":"Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows","date":"2022-11-20","arxiv_id":"2211.11096","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":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) · 2 unverified","sample_list":"/paper/let-offline-rl-flow-training-conservative#ran","syntology_url":"https://syntology.ai/paper/2211.11096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11096"}},"official":{"repos":["tinkoff-ai/cnf"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/q-ensemble-for-offline-rl-don-t-scale-the","slug":"q-ensemble-for-offline-rl-don-t-scale-the","title":"Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size","date":"2022-11-20","arxiv_id":"2211.11092","repositories_listed":2,"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/q-ensemble-for-offline-rl-don-t-scale-the#ran","syntology_url":"https://syntology.ai/paper/2211.11092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11092"}},"official":{"repos":["corl-team/CORL"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper"]}}},{"url":"/paper/agent-controller-representations-principled","slug":"agent-controller-representations-principled","title":"Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information","date":"2022-10-31","arxiv_id":"2211.00164","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 6 samples that ran constructed an object rather than computing a result","sample_list":"/paper/agent-controller-representations-principled#ran","syntology_url":"https://syntology.ai/paper/2211.00164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.00164"}},"official":{"repos":["manantomar/agent-centric-representations"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-behavior-cloning-regularization-for-1","slug":"adaptive-behavior-cloning-regularization-for-1","title":"Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning","date":"2022-10-25","arxiv_id":"2210.13846","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":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/adaptive-behavior-cloning-regularization-for-1#ran","syntology_url":"https://syntology.ai/paper/2210.13846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13846"}},"official":{"repos":["zhaoyi11/adaptive_bc"],"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/discriminator-weighted-offline-imitation-1","slug":"discriminator-weighted-offline-imitation-1","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","date":"2022-07-20","arxiv_id":"2207.10050","repositories_listed":2,"syntology":{"n":13,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/discriminator-weighted-offline-imitation-1#ran","syntology_url":"https://syntology.ai/paper/2207.10050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10050"}},"official":{"repos":["ryanxhr/dwbc"],"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/behavior-transformers-cloning-k-modes-with","slug":"behavior-transformers-cloning-k-modes-with","title":"Behavior Transformers: Cloning $k$ modes with one stone","date":"2022-06-22","arxiv_id":"2206.11251","repositories_listed":2,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/behavior-transformers-cloning-k-modes-with#ran","syntology_url":"https://syntology.ai/paper/2206.11251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.11251"}},"official":{"repos":["notmahi/bet"],"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":["listed","official"]}}},{"url":"/paper/challenges-and-opportunities-in-offline","slug":"challenges-and-opportunities-in-offline","title":"Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations","date":"2022-06-09","arxiv_id":"2206.04779","repositories_listed":2,"syntology":null},{"url":"/paper/offline-rl-for-natural-language-generation","slug":"offline-rl-for-natural-language-generation","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","date":"2022-06-05","arxiv_id":"2206.11871","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/offline-rl-for-natural-language-generation#ran","syntology_url":"https://syntology.ai/paper/2206.11871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.11871"}},"official":null}},{"url":"/paper/why-so-pessimistic-estimating-uncertainties-1","slug":"why-so-pessimistic-estimating-uncertainties-1","title":"Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters","date":"2022-05-27","arxiv_id":"2205.13703","repositories_listed":2,"syntology":null},{"url":"/paper/distance-sensitive-offline-reinforcement","slug":"distance-sensitive-offline-reinforcement","title":"When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning","date":"2022-05-23","arxiv_id":"2205.11027","repositories_listed":2,"syntology":null},{"url":"/paper/rambo-rl-robust-adversarial-model-based","slug":"rambo-rl-robust-adversarial-model-based","title":"RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning","date":"2022-04-26","arxiv_id":"2204.12581","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rambo-rl-robust-adversarial-model-based#ran","syntology_url":"https://syntology.ai/paper/2204.12581","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.12581"}},"official":{"repos":["marc-rigter/rambo"],"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/chai-a-chatbot-ai-for-task-oriented-dialogue","slug":"chai-a-chatbot-ai-for-task-oriented-dialogue","title":"CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning","date":"2022-04-18","arxiv_id":"2204.08426","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/chai-a-chatbot-ai-for-task-oriented-dialogue#ran","syntology_url":"https://syntology.ai/paper/2204.08426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08426"}},"official":{"repos":["siddharthverma314/chai-naacl-2022"],"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/understanding-the-effects-of-dataset","slug":"understanding-the-effects-of-dataset","title":"A Dataset Perspective on Offline Reinforcement Learning","date":"2021-11-08","arxiv_id":"2111.04714","repositories_listed":2,"syntology":null},{"url":"/paper/d3rlpy-an-offline-deep-reinforcement-learning","slug":"d3rlpy-an-offline-deep-reinforcement-learning","title":"d3rlpy: An Offline Deep Reinforcement Learning Library","date":"2021-11-06","arxiv_id":"2111.03788","repositories_listed":2,"syntology":null},{"url":"/paper/planning-from-pixels-in-environments-with","slug":"planning-from-pixels-in-environments-with","title":"Planning from Pixels in Environments with Combinatorially Hard Search Spaces","date":"2021-10-12","arxiv_id":"2110.06149","repositories_listed":2,"syntology":null},{"url":"/paper/reinforcement-learning-as-one-big-sequence","slug":"reinforcement-learning-as-one-big-sequence","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","date":"2021-06-03","arxiv_id":"2106.02039","repositories_listed":2,"syntology":{"n":28,"n_ran":23,"n_constructed":0,"n_ran_checked":21,"n_instrument":2,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":20,"n_pointer_only":1,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/reinforcement-learning-as-one-big-sequence#ran","syntology_url":"https://syntology.ai/paper/2106.02039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02039"}},"official":{"repos":["JannerM/trajectory-transformer"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/uncertainty-weighted-actor-critic-for-offline","slug":"uncertainty-weighted-actor-critic-for-offline","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning","date":"2021-05-17","arxiv_id":"2105.08140","repositories_listed":2,"syntology":null},{"url":"/paper/online-and-offline-reinforcement-learning-by","slug":"online-and-offline-reinforcement-learning-by","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","date":"2021-04-13","arxiv_id":"2104.06294","repositories_listed":2,"syntology":null},{"url":"/paper/offline-reinforcement-learning-with-fisher","slug":"offline-reinforcement-learning-with-fisher","title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization","date":"2021-03-14","arxiv_id":"2103.08050","repositories_listed":2,"syntology":null},{"url":"/paper/deepaveragers-offline-reinforcement-learning-1","slug":"deepaveragers-offline-reinforcement-learning-1","title":"DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs","date":"2020-10-18","arxiv_id":"2010.08891","repositories_listed":2,"syntology":null},{"url":"/paper/offline-meta-reinforcement-learning-with","slug":"offline-meta-reinforcement-learning-with","title":"Offline Meta-Reinforcement Learning with Advantage Weighting","date":"2020-08-13","arxiv_id":"2008.06043","repositories_listed":2,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"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) · 3 unverified","sample_list":"/paper/offline-meta-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2008.06043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.06043"}},"official":{"repos":["eric-mitchell/macaw"],"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/rl-unplugged-benchmarks-for-offline","slug":"rl-unplugged-benchmarks-for-offline","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","date":"2020-06-24","arxiv_id":"2006.13888","repositories_listed":2,"syntology":null},{"url":"/paper/morel-model-based-offline-reinforcement","slug":"morel-model-based-offline-reinforcement","title":"MOReL : Model-Based Offline Reinforcement Learning","date":"2020-05-12","arxiv_id":"2005.05951","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"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) · 4 unverified","sample_list":"/paper/morel-model-based-offline-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2005.05951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05951"}},"official":null}},{"url":"/paper/step-wise-policy-for-rare-tool-knowledge","slug":"step-wise-policy-for-rare-tool-knowledge","title":"Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs","date":"2025-07-15","arxiv_id":"2507.11371","repositories_listed":1,"syntology":null},{"url":"/paper/sparse-reg-improving-sample-complexity-in","slug":"sparse-reg-improving-sample-complexity-in","title":"Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity","date":"2025-06-20","arxiv_id":"2506.17155","repositories_listed":1,"syntology":null},{"url":"/paper/cawr-corruption-averse-advantage-weighted","slug":"cawr-corruption-averse-advantage-weighted","title":"CAWR: Corruption-Averse Advantage-Weighted Regression for Robust Policy Optimization","date":"2025-06-18","arxiv_id":"2506.15654","repositories_listed":1,"syntology":null},{"url":"/paper/dr-sac-distributionally-robust-soft-actor","slug":"dr-sac-distributionally-robust-soft-actor","title":"DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty","date":"2025-06-14","arxiv_id":"2506.12622","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 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; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/dr-sac-distributionally-robust-soft-actor#ran","syntology_url":"https://syntology.ai/paper/2506.12622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.12622"}},"official":{"repos":["lemutisme/dr-sac"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/2506-08460","slug":"2506-08460","title":"MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning","date":"2025-06-10","arxiv_id":"2506.08460","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2506-08460#ran","syntology_url":"https://syntology.ai/paper/2506.08460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08460"}},"official":{"repos":["guoyihonggyh/mobody-model-based-off-dynamics-offline-reinforcement-learning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/offline-rl-with-smooth-ood-generalization-in","slug":"offline-rl-with-smooth-ood-generalization-in","title":"Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood","date":"2025-06-10","arxiv_id":"2506.08417","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":3,"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/offline-rl-with-smooth-ood-generalization-in#ran","syntology_url":"https://syntology.ai/paper/2506.08417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08417"}},"official":{"repos":["yqpqry/sqog"],"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/diffusion-guidance-is-a-controllable-policy","slug":"diffusion-guidance-is-a-controllable-policy","title":"Diffusion Guidance Is a Controllable Policy Improvement Operator","date":"2025-05-29","arxiv_id":"2505.23458","repositories_listed":1,"syntology":null},{"url":"/paper/sorel-and-torel-two-methods-for-fully-offline","slug":"sorel-and-torel-two-methods-for-fully-offline","title":"SOReL and TOReL: Two Methods for Fully Offline Reinforcement Learning","date":"2025-05-28","arxiv_id":"2505.22442","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-trust-bellman-updates-selective","slug":"learning-to-trust-bellman-updates-selective","title":"Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL","date":"2025-05-26","arxiv_id":"2505.19923","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":2,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-to-trust-bellman-updates-selective#ran","syntology_url":"https://syntology.ai/paper/2505.19923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19923"}},"official":{"repos":["qinwenluo/ssar"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/pytupli-a-scalable-infrastructure-for","slug":"pytupli-a-scalable-infrastructure-for","title":"PyTupli: A Scalable Infrastructure for Collaborative Offline Reinforcement Learning Projects","date":"2025-05-22","arxiv_id":"2505.16754","repositories_listed":1,"syntology":null},{"url":"/paper/think-j-learning-to-think-for-generative-llm","slug":"think-j-learning-to-think-for-generative-llm","title":"Think-J: Learning to Think for Generative LLM-as-a-Judge","date":"2025-05-20","arxiv_id":"2505.14268","repositories_listed":1,"syntology":null},{"url":"/paper/imaginebench-evaluating-reinforcement","slug":"imaginebench-evaluating-reinforcement","title":"ImagineBench: Evaluating Reinforcement Learning with Large Language Model Rollouts","date":"2025-05-15","arxiv_id":"2505.10010","repositories_listed":1,"syntology":null},{"url":"/paper/neorl-2-near-real-world-benchmarks-for","slug":"neorl-2-near-real-world-benchmarks-for","title":"NeoRL-2: Near Real-World Benchmarks for Offline Reinforcement Learning with Extended Realistic Scenarios","date":"2025-03-25","arxiv_id":"2503.19267","repositories_listed":1,"syntology":null},{"url":"/paper/policy-constraint-by-only-support-constraint","slug":"policy-constraint-by-only-support-constraint","title":"Policy Constraint by Only Support Constraint for Offline Reinforcement Learning","date":"2025-03-07","arxiv_id":"2503.05207","repositories_listed":1,"syntology":null},{"url":"/paper/what-makes-a-good-diffusion-planner-for","slug":"what-makes-a-good-diffusion-planner-for","title":"What Makes a Good Diffusion Planner for Decision Making?","date":"2025-03-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/scalable-decision-making-in-stochastic","slug":"scalable-decision-making-in-stochastic","title":"Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction","date":"2025-02-28","arxiv_id":"2502.21186","repositories_listed":1,"syntology":null},{"url":"/paper/active-advantage-aligned-online-reinforcement","slug":"active-advantage-aligned-online-reinforcement","title":"Active Advantage-Aligned Online Reinforcement Learning with Offline Data","date":"2025-02-11","arxiv_id":"2502.07937","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/active-advantage-aligned-online-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2502.07937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07937"}},"official":{"repos":["xuefeng-cs/a3rl"],"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/gnn-dt-graph-neural-network-enhanced-decision","slug":"gnn-dt-graph-neural-network-enhanced-decision","title":"GNN-DT: Graph Neural Network Enhanced Decision Transformer for Efficient Optimization in Dynamic Environments","date":"2025-02-03","arxiv_id":"2502.01778","repositories_listed":1,"syntology":null},{"url":"/paper/fat-to-thin-policy-optimization-offline-rl","slug":"fat-to-thin-policy-optimization-offline-rl","title":"Fat-to-Thin Policy Optimization: Offline RL with Sparse Policies","date":"2025-01-24","arxiv_id":"2501.14373","repositories_listed":1,"syntology":null},{"url":"/paper/constraint-adaptive-policy-switching-for","slug":"constraint-adaptive-policy-switching-for","title":"Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning","date":"2024-12-25","arxiv_id":"2412.18946","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/constraint-adaptive-policy-switching-for#ran","syntology_url":"https://syntology.ai/paper/2412.18946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18946"}},"official":{"repos":["yassinech/caps"],"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/optimistic-critic-reconstruction-and","slug":"optimistic-critic-reconstruction-and","title":"Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL","date":"2024-12-25","arxiv_id":"2412.18855","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"4 ran (of which 3 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/optimistic-critic-reconstruction-and#ran","syntology_url":"https://syntology.ai/paper/2412.18855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18855"}},"official":{"repos":["QinwenLuo/OCR-CFT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/are-expressive-models-truly-necessary-for","slug":"are-expressive-models-truly-necessary-for","title":"Are Expressive Models Truly Necessary for Offline RL?","date":"2024-12-15","arxiv_id":"2412.11253","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/are-expressive-models-truly-necessary-for#ran","syntology_url":"https://syntology.ai/paper/2412.11253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11253"}},"official":{"repos":["imoneoi/RSP_JAX"],"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/in-dataset-trajectory-return-regularization","slug":"in-dataset-trajectory-return-regularization","title":"In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning","date":"2024-12-12","arxiv_id":"2412.09104","repositories_listed":1,"syntology":null},{"url":"/paper/latent-safety-constrained-policy-approach-for","slug":"latent-safety-constrained-policy-approach-for","title":"Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning","date":"2024-12-11","arxiv_id":"2412.08794","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":3,"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/latent-safety-constrained-policy-approach-for#ran","syntology_url":"https://syntology.ai/paper/2412.08794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.08794"}},"official":{"repos":["PrajwalKoirala/LSPC-Safe-Offline-RL"],"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/efficient-online-reinforcement-learning-fine","slug":"efficient-online-reinforcement-learning-fine","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","date":"2024-12-10","arxiv_id":"2412.07762","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":8,"phrase":"7 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficient-online-reinforcement-learning-fine#ran","syntology_url":"https://syntology.ai/paper/2412.07762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07762"}},"official":{"repos":["zhouzypaul/wsrl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-an-overview","slug":"reinforcement-learning-an-overview","title":"Reinforcement Learning: An Overview","date":"2024-12-06","arxiv_id":"2412.05265","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-generative-policies-a-simpler","slug":"revisiting-generative-policies-a-simpler","title":"Revisiting Generative Policies: A Simpler Reinforcement Learning Algorithmic Perspective","date":"2024-12-02","arxiv_id":"2412.01245","repositories_listed":1,"syntology":null},{"url":"/paper/pretrained-llm-adapted-with-lora-as-a","slug":"pretrained-llm-adapted-with-lora-as-a","title":"Pretrained LLM Adapted with LoRA as a Decision Transformer for Offline RL in Quantitative Trading","date":"2024-11-26","arxiv_id":"2411.17900","repositories_listed":1,"syntology":null},{"url":"/paper/continual-task-learning-through-adaptive","slug":"continual-task-learning-through-adaptive","title":"Continual Task Learning through Adaptive Policy Self-Composition","date":"2024-11-18","arxiv_id":"2411.11364","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":4,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/continual-task-learning-through-adaptive#ran","syntology_url":"https://syntology.ai/paper/2411.11364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11364"}},"official":{"repos":["charleshsc/CompoFormer"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/doubly-mild-generalization-for-offline","slug":"doubly-mild-generalization-for-offline","title":"Doubly Mild Generalization for Offline Reinforcement Learning","date":"2024-11-12","arxiv_id":"2411.07934","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/doubly-mild-generalization-for-offline#ran","syntology_url":"https://syntology.ai/paper/2411.07934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07934"}},"official":{"repos":["maoyixiu/dmg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/uncertainty-based-offline-variational","slug":"uncertainty-based-offline-variational","title":"Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions","date":"2024-11-01","arxiv_id":"2411.00465","repositories_listed":1,"syntology":{"n":13,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/uncertainty-based-offline-variational#ran","syntology_url":"https://syntology.ai/paper/2411.00465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00465"}},"official":{"repos":["MIRALab-USTC/RL-TRACER"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/networkgym-reinforcement-learning","slug":"networkgym-reinforcement-learning","title":"NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation","date":"2024-10-30","arxiv_id":"2411.04138","repositories_listed":1,"syntology":{"n":18,"n_ran":15,"n_constructed":2,"n_ran_checked":7,"n_instrument":8,"n_unverified":3,"n_honours":4,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"15 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/networkgym-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2411.04138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04138"}},"official":{"repos":["hmomin/networkgym"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}}],"syntology_records":58,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":15,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/offline-rl-on-d4rl","since_archive":"/sota/offline-rl-on-d4rl#since-judged","papers_judged":4,"placed":0},{"leaderboard":"/sota/offline-rl-on-walker2d","since_archive":"/sota/offline-rl-on-walker2d#since-judged","papers_judged":11,"placed":0}]},"papers_where_code_ran":164,"papers_where_code_ran_first_page":"/task/offline-rl/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":8,"url":"/task/offline-rl/papers/2","json":"/task/offline-rl/papers/2.json","rows":100},{"order":"archive","page":3,"of":8,"url":"/task/offline-rl/papers/3","json":"/task/offline-rl/papers/3.json","rows":100},{"order":"archive","page":4,"of":8,"url":"/task/offline-rl/papers/4","json":"/task/offline-rl/papers/4.json","rows":100},{"order":"archive","page":5,"of":8,"url":"/task/offline-rl/papers/5","json":"/task/offline-rl/papers/5.json","rows":100},{"order":"archive","page":6,"of":8,"url":"/task/offline-rl/papers/6","json":"/task/offline-rl/papers/6.json","rows":100},{"order":"archive","page":7,"of":8,"url":"/task/offline-rl/papers/7","json":"/task/offline-rl/papers/7.json","rows":100},{"order":"archive","page":8,"of":8,"url":"/task/offline-rl/papers/8","json":"/task/offline-rl/papers/8.json","rows":55},{"order":"ran","page":1,"of":2,"url":"/task/offline-rl/papers/ran/1","json":"/task/offline-rl/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/offline-rl/papers/ran/2","json":"/task/offline-rl/papers/ran/2.json","rows":64}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"54bef4a974baa2a947c45bbf052c16a9fa186cde58290abc62818878fc265188","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}