{"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/d4rl","name":"D4RL","slug":"d4rl","description_markdown":null,"categories":[{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":226,"papers_with_code":108,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/d4rl-on-d4rl","slug":"d4rl-on-d4rl","dataset":"D4RL","dataset_url":"/dataset/d4rl","rows_in_archive":9,"metrics":["Average Reward"],"first_row_in_archive_order":{"model":"PMDB","paper_title":"Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief","paper_url":"/paper/model-based-offline-reinforcement-learning","paper_date":"2022-10-13","arxiv_id":"2210.06692","code_links":[{"title":"huawei-noah/HEBO","url":"https://github.com/huawei-noah/HEBO/tree/master/PMDB"},{"title":"huawei-noah/hebo","url":"https://github.com/huawei-noah/hebo"},{"title":"2023-MindSpore-1/ms-code-220","url":"https://github.com/2023-MindSpore-1/ms-code-220/tree/main/pmdb"}],"syntology":null}}],"datasets":[{"url":"/dataset/d4rl","name":"D4RL","full_name":"D4RL","num_papers_in_archive":538}],"subtasks":[],"parent_tasks":[{"url":"/task/mujoco-games","name":"MuJoCo Games"}],"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":3,"rows_per_page":100,"shown":100,"of":226,"of_with_code":108,"tagged_in_all":226,"counts":{"archive_papers_tagged":226,"with_a_code_link":108,"where_syntology_ran_a_sample":68,"not_listed_spam_title":0,"listed":226,"listed_where_code_ran":68,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":58,"every_run_a_failure_of_syntologys_instrument":10,"listed_with_a_run_with_no_instrument_failure":58,"listed_every_run_a_failure_of_syntologys_instrument":10,"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/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/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/corl-research-oriented-deep-offline-1","slug":"corl-research-oriented-deep-offline-1","title":"CORL: Research-oriented Deep Offline Reinforcement Learning Library","date":"2022-10-13","arxiv_id":"2210.07105","repositories_listed":5,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/corl-research-oriented-deep-offline-1#ran","syntology_url":"https://syntology.ai/paper/2210.07105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07105"}},"official":{"repos":["corl-team/CORL","hanjuku-kaso/awesome-offline-rl","tinkoff-ai/CORL"],"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/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/implicit-behavioral-cloning","slug":"implicit-behavioral-cloning","title":"Implicit Behavioral Cloning","date":"2021-09-01","arxiv_id":"2109.00137","repositories_listed":5,"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/implicit-behavioral-cloning#ran","syntology_url":"https://syntology.ai/paper/2109.00137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00137"}},"official":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/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/datasets-and-benchmarks-for-offline-safe","slug":"datasets-and-benchmarks-for-offline-safe","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","date":"2023-06-15","arxiv_id":"2306.09303","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/datasets-and-benchmarks-for-offline-safe#ran","syntology_url":"https://syntology.ai/paper/2306.09303","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.09303"}},"official":{"repos":["liuzuxin/dsrl","liuzuxin/fsrl","liuzuxin/osrl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"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/contrastive-energy-prediction-for-exact","slug":"contrastive-energy-prediction-for-exact","title":"Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning","date":"2023-04-25","arxiv_id":"2304.12824","repositories_listed":3,"syntology":{"n":27,"n_ran":19,"n_constructed":1,"n_ran_checked":7,"n_instrument":12,"n_unverified":8,"n_honours":3,"n_violates":0,"n_no_contract":4,"n_pointer_only":17,"phrase":"19 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 12 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/contrastive-energy-prediction-for-exact#ran","syntology_url":"https://syntology.ai/paper/2304.12824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.12824"}},"official":{"repos":["thu-ml/cep-energy-guided-diffusion"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/anti-exploration-by-random-network","slug":"anti-exploration-by-random-network","title":"Anti-Exploration by Random Network Distillation","date":"2023-01-31","arxiv_id":"2301.13616","repositories_listed":3,"syntology":{"n":26,"n_ran":20,"n_constructed":18,"n_ran_checked":19,"n_instrument":1,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":18,"n_pointer_only":7,"phrase":"20 ran (of which 18 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/anti-exploration-by-random-network#ran","syntology_url":"https://syntology.ai/paper/2301.13616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13616"}},"official":{"repos":["tinkoff-ai/sac-rnd"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":15,"n_ran_no_instrument_failure":16,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"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/mildly-conservative-q-learning-for-offline","slug":"mildly-conservative-q-learning-for-offline","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","date":"2022-06-09","arxiv_id":"2206.04745","repositories_listed":3,"syntology":{"n":16,"n_ran":13,"n_constructed":6,"n_ran_checked":12,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":10,"n_pointer_only":11,"phrase":"13 ran (of which 6 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mildly-conservative-q-learning-for-offline#ran","syntology_url":"https://syntology.ai/paper/2206.04745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04745"}},"official":{"repos":["dmksjfl/mcq"],"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":["found_in_text","listed"]}}},{"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/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/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/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/hierarchical-decision-mamba","slug":"hierarchical-decision-mamba","title":"Decision Mamba Architectures","date":"2024-05-13","arxiv_id":"2405.07943","repositories_listed":2,"syntology":null},{"url":"/paper/exploration-and-anti-exploration-with","slug":"exploration-and-anti-exploration-with","title":"Exploration and Anti-Exploration with Distributional Random Network Distillation","date":"2024-01-18","arxiv_id":"2401.09750","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exploration-and-anti-exploration-with#ran","syntology_url":"https://syntology.ai/paper/2401.09750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09750"}},"official":{"repos":["yk7333/drnd"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["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/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/understanding-expertise-through","slug":"understanding-expertise-through","title":"When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning","date":"2023-02-15","arxiv_id":"2302.07457","repositories_listed":2,"syntology":null},{"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/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/online-decision-transformer","slug":"online-decision-transformer","title":"Online Decision Transformer","date":"2022-02-11","arxiv_id":"2202.05607","repositories_listed":2,"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/online-decision-transformer#ran","syntology_url":"https://syntology.ai/paper/2202.05607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.05607"}},"official":{"repos":["facebookresearch/online-dt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"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/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/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/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/beyond-the-known-decision-making-with","slug":"beyond-the-known-decision-making-with","title":"Beyond the Known: Decision Making with Counterfactual Reasoning Decision Transformer","date":"2025-05-14","arxiv_id":"2505.09114","repositories_listed":1,"syntology":null},{"url":"/paper/directly-forecasting-belief-for-reinforcement","slug":"directly-forecasting-belief-for-reinforcement","title":"Directly Forecasting Belief for Reinforcement Learning with Delays","date":"2025-05-01","arxiv_id":"2505.00546","repositories_listed":1,"syntology":null},{"url":"/paper/habitizing-diffusion-planning-for-efficient","slug":"habitizing-diffusion-planning-for-efficient","title":"Habitizing Diffusion Planning for Efficient and Effective Decision Making","date":"2025-02-10","arxiv_id":"2502.06401","repositories_listed":1,"syntology":null},{"url":"/paper/skill-expansion-and-composition-in-parameter","slug":"skill-expansion-and-composition-in-parameter","title":"Skill Expansion and Composition in Parameter Space","date":"2025-02-09","arxiv_id":"2502.05932","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":2,"n_honours":4,"n_violates":2,"n_no_contract":2,"n_pointer_only":9,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 2 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/skill-expansion-and-composition-in-parameter#ran","syntology_url":"https://syntology.ai/paper/2502.05932","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05932"}},"official":{"repos":["ltlhuuu/PSEC"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"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/m-3-pc-test-time-model-predictive-control-for","slug":"m-3-pc-test-time-model-predictive-control-for","title":"M$^3$PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model","date":"2024-12-07","arxiv_id":"2412.05675","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"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 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) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/m-3-pc-test-time-model-predictive-control-for#ran","syntology_url":"https://syntology.ai/paper/2412.05675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05675"}},"official":{"repos":["wkh923/m3pc"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-on-one-mode-addressing-multi","slug":"learning-on-one-mode-addressing-multi","title":"Learning on One Mode: Addressing Multi-Modality in Offline Reinforcement Learning","date":"2024-12-04","arxiv_id":"2412.03258","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"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 4 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; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/learning-on-one-mode-addressing-multi#ran","syntology_url":"https://syntology.ai/paper/2412.03258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03258"}},"official":{"repos":["MianchuWang/LOM"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/constrained-latent-action-policies-for-model","slug":"constrained-latent-action-policies-for-model","title":"Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning","date":"2024-11-07","arxiv_id":"2411.04562","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/constrained-latent-action-policies-for-model#ran","syntology_url":"https://syntology.ai/paper/2411.04562","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04562"}},"official":{"repos":["marvinalles/c-lap"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/hypercube-policy-regularization-framework-for","slug":"hypercube-policy-regularization-framework-for","title":"Hypercube Policy Regularization Framework for Offline Reinforcement Learning","date":"2024-11-07","arxiv_id":"2411.04534","repositories_listed":1,"syntology":null},{"url":"/paper/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"]}}},{"url":"/paper/offline-behavior-distillation","slug":"offline-behavior-distillation","title":"Offline Behavior Distillation","date":"2024-10-30","arxiv_id":"2410.22728","repositories_listed":1,"syntology":{"n":16,"n_ran":9,"n_constructed":1,"n_ran_checked":6,"n_instrument":3,"n_unverified":7,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_pointer_only":16,"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) · 7 unverified","sample_list":"/paper/offline-behavior-distillation#ran","syntology_url":"https://syntology.ai/paper/2410.22728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22728"}},"official":{"repos":["leaveslei/obd"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":1,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/q-distribution-guided-q-learning-for-offline","slug":"q-distribution-guided-q-learning-for-offline","title":"Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model","date":"2024-10-27","arxiv_id":"2410.20312","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/q-distribution-guided-q-learning-for-offline#ran","syntology_url":"https://syntology.ai/paper/2410.20312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20312"}},"official":{"repos":["evalarzj/qdq"],"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/bayes-adaptive-monte-carlo-tree-search-for","slug":"bayes-adaptive-monte-carlo-tree-search-for","title":"Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning","date":"2024-10-15","arxiv_id":"2410.11234","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bayes-adaptive-monte-carlo-tree-search-for#ran","syntology_url":"https://syntology.ai/paper/2410.11234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11234"}},"official":{"repos":["lucascjysdl/offline-rl-kit"],"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/the-role-of-deep-learning-regularizations-on","slug":"the-role-of-deep-learning-regularizations-on","title":"The Role of Deep Learning Regularizations on Actors in Offline RL","date":"2024-09-11","arxiv_id":"2409.07606","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-models-as-optimizers-for-efficient","slug":"diffusion-models-as-optimizers-for-efficient","title":"Diffusion Models as Optimizers for Efficient Planning in Offline RL","date":"2024-07-23","arxiv_id":"2407.16142","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-diffusion-behaviors-with-q-functions","slug":"aligning-diffusion-behaviors-with-q-functions","title":"Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control","date":"2024-07-12","arxiv_id":"2407.09024","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":12,"phrase":"8 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; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/aligning-diffusion-behaviors-with-q-functions#ran","syntology_url":"https://syntology.ai/paper/2407.09024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09024"}},"official":{"repos":["thu-ml/efficient-diffusion-alignment"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/residual-learning-and-context-encoding-for","slug":"residual-learning-and-context-encoding-for","title":"Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning","date":"2024-06-12","arxiv_id":"2406.08238","repositories_listed":1,"syntology":null},{"url":"/paper/plandq-hierarchical-plan-orchestration-via-d","slug":"plandq-hierarchical-plan-orchestration-via-d","title":"PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer","date":"2024-06-10","arxiv_id":"2406.06793","repositories_listed":1,"syntology":null},{"url":"/paper/stabilizing-extreme-q-learning-by-maclaurin","slug":"stabilizing-extreme-q-learning-by-maclaurin","title":"Stabilizing Extreme Q-learning by Maclaurin Expansion","date":"2024-06-07","arxiv_id":"2406.04896","repositories_listed":1,"syntology":null},{"url":"/paper/strategically-conservative-q-learning","slug":"strategically-conservative-q-learning","title":"Strategically Conservative Q-Learning","date":"2024-06-06","arxiv_id":"2406.04534","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-actor-critic-formulating","slug":"diffusion-actor-critic-formulating","title":"Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning","date":"2024-05-31","arxiv_id":"2405.20555","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"8 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/diffusion-actor-critic-formulating#ran","syntology_url":"https://syntology.ai/paper/2405.20555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20555"}},"official":{"repos":["Fang-Lin93/DAC"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/in-context-decision-transformer-reinforcement","slug":"in-context-decision-transformer-reinforcement","title":"In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought","date":"2024-05-31","arxiv_id":"2405.20692","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/in-context-decision-transformer-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2405.20692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20692"}},"official":{"repos":["silihuang-ai/idt"],"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","unlocated"]}}},{"url":"/paper/adaptive-advantage-guided-policy","slug":"adaptive-advantage-guided-policy","title":"Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning","date":"2024-05-30","arxiv_id":"2405.19909","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/adaptive-advantage-guided-policy#ran","syntology_url":"https://syntology.ai/paper/2405.19909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19909"}},"official":{"repos":["ltlhuuu/a2pr"],"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/diffusion-policies-creating-a-trust-region","slug":"diffusion-policies-creating-a-trust-region","title":"Diffusion Policies creating a Trust Region for Offline Reinforcement Learning","date":"2024-05-30","arxiv_id":"2405.19690","repositories_listed":1,"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":10,"n_instrument":7,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":20,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/diffusion-policies-creating-a-trust-region#ran","syntology_url":"https://syntology.ai/paper/2405.19690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19690"}},"official":{"repos":["tianyucodings/diffusion_trusted_q_learning"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/aligniql-policy-alignment-in-implicit-q","slug":"aligniql-policy-alignment-in-implicit-q","title":"AlignIQL: Policy Alignment in Implicit Q-Learning through Constrained Optimization","date":"2024-05-28","arxiv_id":"2405.18187","repositories_listed":1,"syntology":null},{"url":"/paper/didi-diffusion-guided-diversity-for-offline","slug":"didi-diffusion-guided-diversity-for-offline","title":"DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation","date":"2024-05-23","arxiv_id":"2405.14790","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":4,"n_honours":4,"n_violates":0,"n_no_contract":0,"n_pointer_only":13,"phrase":"9 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; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/didi-diffusion-guided-diversity-for-offline#ran","syntology_url":"https://syntology.ai/paper/2405.14790","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14790"}},"official":{"repos":["huey0528/icml24didi"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/reinformer-max-return-sequence-modeling-for","slug":"reinformer-max-return-sequence-modeling-for","title":"Reinformer: Max-Return Sequence Modeling for Offline RL","date":"2024-05-14","arxiv_id":"2405.08740","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/reinformer-max-return-sequence-modeling-for#ran","syntology_url":"https://syntology.ai/paper/2405.08740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.08740"}},"official":{"repos":["dragon-zhuang/reinformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/compositional-conservatism-a-transductive","slug":"compositional-conservatism-a-transductive","title":"Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning","date":"2024-04-06","arxiv_id":"2404.04682","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/compositional-conservatism-a-transductive#ran","syntology_url":"https://syntology.ai/paper/2404.04682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04682"}},"official":{"repos":["runamu/compositional-conservatism"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/grid-mapping-pseudo-count-constraint-for","slug":"grid-mapping-pseudo-count-constraint-for","title":"Grid-Mapping Pseudo-Count Constraint for Offline Reinforcement Learning","date":"2024-04-03","arxiv_id":"2404.02545","repositories_listed":1,"syntology":null},{"url":"/paper/advantage-aware-policy-optimization-for","slug":"advantage-aware-policy-optimization-for","title":"A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective","date":"2024-03-12","arxiv_id":"2403.07262","repositories_listed":1,"syntology":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/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/reframing-offline-reinforcement-learning-as-a","slug":"reframing-offline-reinforcement-learning-as-a","title":"Solving Offline Reinforcement Learning with Decision Tree Regression","date":"2024-01-21","arxiv_id":"2401.11630","repositories_listed":1,"syntology":null},{"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/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":2,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 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":2,"n_unverified":4,"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/crop-conservative-reward-for-model-based","slug":"crop-conservative-reward-for-model-based","title":"CROP: Conservative Reward for Model-based Offline Policy Optimization","date":"2023-10-26","arxiv_id":"2310.17245","repositories_listed":1,"syntology":null},{"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/score-regularized-policy-optimization-through","slug":"score-regularized-policy-optimization-through","title":"Score Regularized Policy Optimization through Diffusion Behavior","date":"2023-10-11","arxiv_id":"2310.07297","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/score-regularized-policy-optimization-through#ran","syntology_url":"https://syntology.ai/paper/2310.07297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07297"}},"official":{"repos":["thu-ml/srpo"],"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/diffcps-diffusion-model-based-constrained","slug":"diffcps-diffusion-model-based-constrained","title":"DiffCPS: Diffusion Model based Constrained Policy Search for Offline Reinforcement Learning","date":"2023-10-09","arxiv_id":"2310.05333","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":4,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/diffcps-diffusion-model-based-constrained#ran","syntology_url":"https://syntology.ai/paper/2310.05333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05333"}},"official":{"repos":["felix-thu/DiffCPS"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/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/pre-training-with-synthetic-data-helps","slug":"pre-training-with-synthetic-data-helps","title":"Pre-training with Synthetic Data Helps Offline Reinforcement Learning","date":"2023-10-01","arxiv_id":"2310.00771","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pre-training-with-synthetic-data-helps#ran","syntology_url":"https://syntology.ai/paper/2310.00771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00771"}},"official":{"repos":["victor-wang-902/synthetic-pretrain-rl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/model-based-offline-reinforcement-learning-2","slug":"model-based-offline-reinforcement-learning-2","title":"Model-based Offline Reinforcement Learning with Count-based Conservatism","date":"2023-07-21","arxiv_id":"2307.11352","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 1 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) · 2 unverified","sample_list":"/paper/model-based-offline-reinforcement-learning-2#ran","syntology_url":"https://syntology.ai/paper/2307.11352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.11352"}},"official":{"repos":["oh-lab/count-morl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/curricular-subgoals-for-inverse-reinforcement","slug":"curricular-subgoals-for-inverse-reinforcement","title":"Curricular Subgoals for Inverse Reinforcement Learning","date":"2023-06-14","arxiv_id":"2306.08232","repositories_listed":1,"syntology":null},{"url":"/paper/katakomba-tools-and-benchmarks-for-data","slug":"katakomba-tools-and-benchmarks-for-data","title":"Katakomba: Tools and Benchmarks for Data-Driven NetHack","date":"2023-06-14","arxiv_id":"2306.08772","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/katakomba-tools-and-benchmarks-for-data#ran","syntology_url":"https://syntology.ai/paper/2306.08772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08772"}},"official":{"repos":["corl-team/katakomba"],"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/mildly-constrained-evaluation-policy-for","slug":"mildly-constrained-evaluation-policy-for","title":"Mildly Constrained Evaluation Policy for Offline Reinforcement Learning","date":"2023-06-06","arxiv_id":"2306.03680","repositories_listed":1,"syntology":null},{"url":"/paper/improving-and-benchmarking-offline","slug":"improving-and-benchmarking-offline","title":"Improving and Benchmarking Offline Reinforcement Learning Algorithms","date":"2023-06-01","arxiv_id":"2306.00972","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-diffusion-policies-for-offline-1","slug":"efficient-diffusion-policies-for-offline-1","title":"Efficient Diffusion Policies for Offline Reinforcement Learning","date":"2023-05-31","arxiv_id":"2305.20081","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-diffusion-policies-for-offline-1#ran","syntology_url":"https://syntology.ai/paper/2305.20081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.20081"}},"official":{"repos":["sail-sg/edp"],"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/primal-attention-self-attention-through","slug":"primal-attention-self-attention-through","title":"Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation","date":"2023-05-31","arxiv_id":"2305.19798","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/primal-attention-self-attention-through#ran","syntology_url":"https://syntology.ai/paper/2305.19798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19798"}},"official":{"repos":["yingyichen-cyy/PrimalAttention"],"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/2305-14550","slug":"2305-14550","title":"When should we prefer Decision Transformers for Offline Reinforcement Learning?","date":"2023-05-23","arxiv_id":"2305.14550","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/2305-14550#ran","syntology_url":"https://syntology.ai/paper/2305.14550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14550"}},"official":{"repos":["prajjwal1/rl_paradigm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/uncertainty-driven-trajectory-truncation-for","slug":"uncertainty-driven-trajectory-truncation-for","title":"Uncertainty-driven Trajectory Truncation for Data Augmentation in Offline Reinforcement Learning","date":"2023-04-10","arxiv_id":"2304.04660","repositories_listed":1,"syntology":null},{"url":"/paper/optimal-transport-for-offline-imitation","slug":"optimal-transport-for-offline-imitation","title":"Optimal Transport for Offline Imitation Learning","date":"2023-03-24","arxiv_id":"2303.13971","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/optimal-transport-for-offline-imitation#ran","syntology_url":"https://syntology.ai/paper/2303.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13971"}},"official":{"repos":["ethanluoyc/optimal_transport_reward"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/conservative-state-value-estimation-for-1","slug":"conservative-state-value-estimation-for-1","title":"Conservative State Value Estimation for Offline Reinforcement Learning","date":"2023-02-14","arxiv_id":"2302.06884","repositories_listed":1,"syntology":null},{"url":"/paper/td3-with-reverse-kl-regularizer-for-offline","slug":"td3-with-reverse-kl-regularizer-for-offline","title":"TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets","date":"2022-12-05","arxiv_id":"2212.02125","repositories_listed":1,"syntology":null},{"url":"/paper/robust-offline-reinforcement-learning-with","slug":"robust-offline-reinforcement-learning-with","title":"Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation","date":"2022-10-19","arxiv_id":"2210.10469","repositories_listed":1,"syntology":null},{"url":"/paper/a-policy-guided-imitation-approach-for","slug":"a-policy-guided-imitation-approach-for","title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","date":"2022-10-15","arxiv_id":"2210.08323","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":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/a-policy-guided-imitation-approach-for#ran","syntology_url":"https://syntology.ai/paper/2210.08323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.08323"}},"official":{"repos":["ryanxhr/por"],"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/mutual-information-regularized-offline-1","slug":"mutual-information-regularized-offline-1","title":"Mutual Information Regularized Offline Reinforcement Learning","date":"2022-10-14","arxiv_id":"2210.07484","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mutual-information-regularized-offline-1#ran","syntology_url":"https://syntology.ai/paper/2210.07484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07484"}},"official":{"repos":["sail-sg/misa"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/semi-supervised-offline-reinforcement-1","slug":"semi-supervised-offline-reinforcement-1","title":"Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories","date":"2022-10-12","arxiv_id":"2210.06518","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/semi-supervised-offline-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2210.06518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06518"}},"official":{"repos":["facebookresearch/ssorl"],"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":["found_in_text"]}}},{"url":"/paper/conservative-bayesian-model-based-value","slug":"conservative-bayesian-model-based-value","title":"Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization","date":"2022-10-07","arxiv_id":"2210.03802","repositories_listed":1,"syntology":null},{"url":"/paper/offline-reinforcement-learning-via-high","slug":"offline-reinforcement-learning-via-high","title":"Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling","date":"2022-09-29","arxiv_id":"2209.14548","repositories_listed":1,"syntology":null},{"url":"/paper/q-learning-decision-transformer-leveraging","slug":"q-learning-decision-transformer-leveraging","title":"Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL","date":"2022-09-08","arxiv_id":"2209.03993","repositories_listed":1,"syntology":null},{"url":"/paper/double-check-your-state-before-trusting-it","slug":"double-check-your-state-before-trusting-it","title":"Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination","date":"2022-06-16","arxiv_id":"2206.07989","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"3 ran (of which 1 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/double-check-your-state-before-trusting-it#ran","syntology_url":"https://syntology.ai/paper/2206.07989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07989"}},"official":{"repos":["dmksjfl/CABI"],"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":["found_in_text","official"]}}},{"url":"/paper/value-memory-graph-a-graph-structured-world","slug":"value-memory-graph-a-graph-structured-world","title":"Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning","date":"2022-06-09","arxiv_id":"2206.04384","repositories_listed":1,"syntology":null},{"url":"/paper/when-does-return-conditioned-supervised","slug":"when-does-return-conditioned-supervised","title":"When does return-conditioned supervised learning work for offline reinforcement learning?","date":"2022-06-02","arxiv_id":"2206.01079","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/when-does-return-conditioned-supervised#ran","syntology_url":"https://syntology.ai/paper/2206.01079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01079"}},"official":{"repos":["davidbrandfonbrener/rcsl-paper"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}}],"syntology_records":65,"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":4,"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/d4rl-on-d4rl","since_archive":"/sota/d4rl-on-d4rl#since-judged","papers_judged":4,"placed":0}]},"papers_where_code_ran":68,"papers_where_code_ran_first_page":"/task/d4rl/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":3,"url":"/task/d4rl/papers/2","json":"/task/d4rl/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/d4rl/papers/3","json":"/task/d4rl/papers/3.json","rows":26},{"order":"ran","page":1,"of":1,"url":"/task/d4rl/papers/ran/1","json":"/task/d4rl/papers/ran/1.json","rows":68}],"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":"19245a291db0036072cf563f1cf036d9428433775e48dd145d228605e0c688d1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}