{"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/papers/3","list_of":"/task/d4rl","task":"D4RL","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":3,"rows_per_page":100,"rows":[201,226],"of":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":59,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":59,"listed_every_run_a_failure_of_syntologys_instrument":9,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/d4rl","prev":"/task/d4rl/papers/2","next":null,"papers":[{"url":null,"slug":"boosting-offline-reinforcement-learning-via","title":"Boosting Offline Reinforcement Learning via Data Rebalancing","date":"2022-10-17","arxiv_id":"2210.09241","repositories_listed":0,"syntology":null},{"url":"/paper/state-advantage-weighting-for-offline-rl","slug":"state-advantage-weighting-for-offline-rl","title":"State Advantage Weighting for Offline RL","date":"2022-10-09","arxiv_id":"2210.04251","repositories_listed":0,"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 5 unverified","sample_list":"/paper/state-advantage-weighting-for-offline-rl#ran","syntology_url":"https://syntology.ai/paper/2210.04251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.04251"}},"official":null}},{"url":null,"slug":"dce-offline-reinforcement-learning-with","title":"DCE: Offline Reinforcement Learning With Double Conservative Estimates","date":"2022-09-27","arxiv_id":"2209.13132","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-decision-transformer","title":"Hierarchical Decision Transformer","date":"2022-09-21","arxiv_id":"2209.10447","repositories_listed":0,"syntology":null},{"url":null,"slug":"addressing-optimism-bias-in-sequence-modeling","title":"Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning","date":"2022-07-21","arxiv_id":"2207.10295","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-role-of-discount-factor-in-offline","title":"On the Role of Discount Factor in Offline Reinforcement Learning","date":"2022-06-07","arxiv_id":"2206.03383","repositories_listed":0,"syntology":null},{"url":null,"slug":"know-your-boundaries-the-necessity-of","title":"Know Your Boundaries: The Necessity of Explicit Behavioral Cloning in Offline RL","date":"2022-06-01","arxiv_id":"2206.00695","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-regularized-implicit-policy-for-offline","title":"A Behavior Regularized Implicit Policy for Offline Reinforcement Learning","date":"2022-02-19","arxiv_id":"2202.09673","repositories_listed":0,"syntology":null},{"url":null,"slug":"moore-model-based-offline-to-online","title":"MOORe: Model-based Offline-to-Online Reinforcement Learning","date":"2022-01-25","arxiv_id":"2201.10070","repositories_listed":0,"syntology":null},{"url":null,"slug":"dr3-value-based-deep-reinforcement-learning-1","title":"DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization","date":"2021-12-09","arxiv_id":"2112.04716","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantile-filtered-imitation-learning","title":"Quantile Filtered Imitation Learning","date":"2021-12-02","arxiv_id":"2112.00950","repositories_listed":0,"syntology":null},{"url":"/paper/koopman-q-learning-offline-reinforcement-1","slug":"koopman-q-learning-offline-reinforcement-1","title":"Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics","date":"2021-11-02","arxiv_id":"2111.01365","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-rl-with-resource-constrained-online","title":"Offline RL With Resource Constrained Online Deployment","date":"2021-10-07","arxiv_id":"2110.03165","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-only-evaluate-once-a-simple-baseline","title":"You Only Evaluate Once: a Simple Baseline Algorithm for Offline RL","date":"2021-10-05","arxiv_id":"2110.02304","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-reinforcement-learning-with-resource","title":"Offline Reinforcement Learning with Resource Constrained Online Deployment","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pareto-policy-pool-for-model-based-offline","title":"Pareto Policy Pool for Model-based Offline Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-offline-reinforcement","title":"Semi-supervised Offline Reinforcement Learning with Pre-trained Decision Transformers","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"state-action-joint-regularized-implicit","title":"State-Action Joint Regularized Implicit Policy for Offline Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-regularized-policy-learning-for","title":"Uncertainty Regularized Policy Learning for Offline Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"why-so-pessimistic-estimating-uncertainties","title":"Why so pessimistic? Estimating uncertainties for offline RL through ensembles, and why their independence matters.","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"behavioral-priors-and-dynamics-models","title":"Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL","date":"2021-06-16","arxiv_id":"2106.09119","repositories_listed":0,"syntology":null},{"url":null,"slug":"s4rl-surprisingly-simple-self-supervision-for","title":"S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning","date":"2021-03-10","arxiv_id":"2103.06326","repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-conservativeness-oriented-offline","title":"Reducing Conservativeness Oriented Offline Reinforcement Learning","date":"2021-02-27","arxiv_id":"2103.00098","repositories_listed":0,"syntology":null},{"url":null,"slug":"addressing-distribution-shift-in-online","title":"Addressing Distribution Shift in Online Reinforcement Learning with Offline Datasets","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-offline-reinforcement-learning","title":"Fine-Tuning Offline Reinforcement Learning with Model-Based Policy Optimization","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"emaq-expected-max-q-learning-operator-for","title":"EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL","date":"2020-07-21","arxiv_id":"2007.11091","repositories_listed":0,"syntology":null}],"record_sha256":"7181e2a399eec88204d5aba2cdcd369977f8b5537bcc8218fea3de2e6e906c0d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}