{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/corruption-robust-offline-reinforcement-2","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","arxiv_id":"2310.14550","date":"2023-10-23","proceeding":"NeurIPS 2023 11","authors":["Chenlu Ye","Rui Yang","Quanquan Gu","Tong Zhang"],"abstract":"We investigate the problem of corruption robustness in offline reinforcement learning (RL) with general function approximation, where an adversary can corrupt each sample in the offline dataset, and the corruption level $\\zeta\\geq0$ quantifies the cumulative corruption amount over $n$ episodes and $H$ steps. Our goal is to find a policy that is robust to such corruption and minimizes the suboptimality gap with respect to the optimal policy for the uncorrupted Markov decision processes (MDPs). Drawing inspiration from the uncertainty-weighting technique from the robust online RL setting \\citep{he2022nearly,ye2022corruptionrobust}, we design a new uncertainty weight iteration procedure to efficiently compute on batched samples and propose a corruption-robust algorithm for offline RL. Notably, under the assumption of single policy coverage and the knowledge of $\\zeta$, our proposed algorithm achieves a suboptimality bound that is worsened by an additive factor of $\\mathcal{O}(\\zeta (C(\\widehat{\\mathcal{F}},\\mu)n)^{-1})$ due to the corruption. Here $\\widehat{\\mathcal{F}}$ is the confidence set, and the dataset $\\mathcal{Z}_n^H$, and $C(\\widehat{\\mathcal{F}},\\mu)$ is a coefficient that depends on $\\widehat{\\mathcal{F}}$ and the underlying data distribution $\\mu$. When specialized to linear MDPs, the corruption-dependent error term reduces to $\\mathcal{O}(\\zeta d n^{-1})$ with $d$ being the dimension of the feature map, which matches the existing lower bound for corrupted linear MDPs. This suggests that our analysis is tight in terms of the corruption-dependent term.","url_abs":"https://arxiv.org/abs/2310.14550v3","url_pdf":"https://arxiv.org/pdf/2310.14550v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"corruption-robust-offline-reinforcement-2","repo_url":"https://github.com/yangrui2015/uwmsg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"offline-rl","task_name":"Offline RL"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.14550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14550"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangrui2015/uwmsg","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"b7c0c6c1a8acecf2","entry":"asdict","repo":"yangrui2015/uwmsg","repo_kind":"official","path":"UWMSG.py","file_url":"https://github.com/yangrui2015/uwmsg/blob/HEAD/UWMSG.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b7c0c6c1a8acecf2"}},{"code_sha256_prefix":"433fa11651ba0f09","entry":"eval_actor","repo":"yangrui2015/uwmsg","repo_kind":"official","path":"UWMSG.py","file_url":"https://github.com/yangrui2015/uwmsg/blob/HEAD/UWMSG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"433fa11651ba0f09"}},{"code_sha256_prefix":"4dd56ecf0f797666","entry":"wrap_env","repo":"yangrui2015/uwmsg","repo_kind":"official","path":"UWMSG.py","file_url":"https://github.com/yangrui2015/uwmsg/blob/HEAD/UWMSG.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4dd56ecf0f797666"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}