{"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/robust-reinforcement-learning-using-offline","title":"Robust Reinforcement Learning using Offline Data","arxiv_id":"2208.05129","date":"2022-08-10","proceeding":null,"authors":["Kishan Panaganti","Zaiyan Xu","Dileep Kalathil","Mohammad Ghavamzadeh"],"abstract":"The goal of robust reinforcement learning (RL) is to learn a policy that is robust against the uncertainty in model parameters. Parameter uncertainty commonly occurs in many real-world RL applications due to simulator modeling errors, changes in the real-world system dynamics over time, and adversarial disturbances. Robust RL is typically formulated as a max-min problem, where the objective is to learn the policy that maximizes the value against the worst possible models that lie in an uncertainty set. In this work, we propose a robust RL algorithm called Robust Fitted Q-Iteration (RFQI), which uses only an offline dataset to learn the optimal robust policy. Robust RL with offline data is significantly more challenging than its non-robust counterpart because of the minimization over all models present in the robust Bellman operator. This poses challenges in offline data collection, optimization over the models, and unbiased estimation. In this work, we propose a systematic approach to overcome these challenges, resulting in our RFQI algorithm. We prove that RFQI learns a near-optimal robust policy under standard assumptions and demonstrate its superior performance on standard benchmark problems.","url_abs":"https://arxiv.org/abs/2208.05129v2","url_pdf":"https://arxiv.org/pdf/2208.05129v2.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":"robust-reinforcement-learning-using-offline","repo_url":"https://github.com/zaiyan-x/RFQI","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"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":{"syntology_url":"https://syntology.ai/paper/2208.05129","atlas_url":"https://app.syntology.ai/?focus=2208.05129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.05129"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/zaiyan-x/RFQI","reach":null}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":0,"samples":[{"code_sha256_prefix":"bd43dccfb7a0ad6d","entry":"Actor","repo":"zaiyan-x/RFQI","repo_kind":"official","path":"rfqi.py","file_url":"https://github.com/zaiyan-x/RFQI/blob/HEAD/rfqi.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd43dccfb7a0ad6d"}},{"code_sha256_prefix":"5e377d73ec00233f","entry":"Critic","repo":"zaiyan-x/RFQI","repo_kind":"official","path":"rfqi.py","file_url":"https://github.com/zaiyan-x/RFQI/blob/HEAD/rfqi.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5e377d73ec00233f"}},{"code_sha256_prefix":"55977265de0d0bf0","entry":"ETA","repo":"zaiyan-x/RFQI","repo_kind":"official","path":"rfqi.py","file_url":"https://github.com/zaiyan-x/RFQI/blob/HEAD/rfqi.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"55977265de0d0bf0"}},{"code_sha256_prefix":"ec8a95d1fa39bff2","entry":"RFQI","repo":"zaiyan-x/RFQI","repo_kind":"official","path":"rfqi.py","file_url":"https://github.com/zaiyan-x/RFQI/blob/HEAD/rfqi.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec8a95d1fa39bff2"}},{"code_sha256_prefix":"faab3001b1787a75","entry":"VAE","repo":"zaiyan-x/RFQI","repo_kind":"official","path":"rfqi.py","file_url":"https://github.com/zaiyan-x/RFQI/blob/HEAD/rfqi.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"faab3001b1787a75"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}