{"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-offline-policy-evaluation-and","title":"Robust Offline Reinforcement learning with Heavy-Tailed Rewards","arxiv_id":"2310.18715","date":"2023-10-28","proceeding":null,"authors":["Jin Zhu","Runzhe Wan","Zhengling Qi","Shikai Luo","Chengchun Shi"],"abstract":"This paper endeavors to augment the robustness of offline reinforcement learning (RL) in scenarios laden with heavy-tailed rewards, a prevalent circumstance in real-world applications. We propose two algorithmic frameworks, ROAM and ROOM, for robust off-policy evaluation and offline policy optimization (OPO), respectively. Central to our frameworks is the strategic incorporation of the median-of-means method with offline RL, enabling straightforward uncertainty estimation for the value function estimator. This not only adheres to the principle of pessimism in OPO but also adeptly manages heavy-tailed rewards. Theoretical results and extensive experiments demonstrate that our two frameworks outperform existing methods on the logged dataset exhibits heavy-tailed reward distributions. The implementation of the proposal is available at https://github.com/Mamba413/ROOM.","url_abs":"https://arxiv.org/abs/2310.18715v2","url_pdf":"https://arxiv.org/pdf/2310.18715v2.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-offline-policy-evaluation-and","repo_url":"https://github.com/mamba413/room","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"off-policy-evaluation","task_name":"Off-policy evaluation"},{"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=2310.18715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18715"}},"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/mamba413/room","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"e941d962072d50ed","entry":"get_agent_config","repo":"mamba413/room","repo_kind":"official","path":"Cartpole/_rllib_util.py","file_url":"https://github.com/mamba413/room/blob/HEAD/Cartpole/_rllib_util.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":"e941d962072d50ed"}},{"code_sha256_prefix":"b929cf9dffdc887a","entry":"listinlist2list","repo":"mamba413/room","repo_kind":"official","path":"Cartpole/_util.py","file_url":"https://github.com/mamba413/room/blob/HEAD/Cartpole/_util.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":"b929cf9dffdc887a"}},{"code_sha256_prefix":"c03957231341007b","entry":"load","repo":"mamba413/room","repo_kind":"official","path":"Cartpole/_util.py","file_url":"https://github.com/mamba413/room/blob/HEAD/Cartpole/_util.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":"c03957231341007b"}},{"code_sha256_prefix":"fe85da14d45dd5ae","entry":"setminus","repo":"mamba413/room","repo_kind":"official","path":"Cartpole/_util.py","file_url":"https://github.com/mamba413/room/blob/HEAD/Cartpole/_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fe85da14d45dd5ae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}