{"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/when-is-off-policy-evaluation-useful-a-data","title":"When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric Perspective","arxiv_id":"2311.14110","date":"2023-11-23","proceeding":null,"authors":["Hao Sun","Alex J. Chan","Nabeel Seedat","Alihan Hüyük","Mihaela van der Schaar"],"abstract":"Evaluating the value of a hypothetical target policy with only a logged dataset is important but challenging. On the one hand, it brings opportunities for safe policy improvement under high-stakes scenarios like clinical guidelines. On the other hand, such opportunities raise a need for precise off-policy evaluation (OPE). While previous work on OPE focused on improving the algorithm in value estimation, in this work, we emphasize the importance of the offline dataset, hence putting forward a data-centric framework for evaluating OPE problems. We propose DataCOPE, a data-centric framework for evaluating OPE, that answers the questions of whether and to what extent we can evaluate a target policy given a dataset. DataCOPE (1) forecasts the overall performance of OPE algorithms without access to the environment, which is especially useful before real-world deployment where evaluating OPE is impossible; (2) identifies the sub-group in the dataset where OPE can be inaccurate; (3) permits evaluations of datasets or data-collection strategies for OPE problems. Our empirical analysis of DataCOPE in the logged contextual bandit settings using healthcare datasets confirms its ability to evaluate both machine-learning and human expert policies like clinical guidelines. Finally, we apply DataCOPE to the task of reward modeling in Large Language Model alignment to demonstrate its scalability in real-world applications.","url_abs":"https://arxiv.org/abs/2311.14110v2","url_pdf":"https://arxiv.org/pdf/2311.14110v2.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":"when-is-off-policy-evaluation-useful-a-data","repo_url":"https://github.com/holarissun/Data-Centric-OPE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"multi-armed-bandits","task_name":"Multi-Armed Bandits"},{"task_slug":"off-policy-evaluation","task_name":"Off-policy evaluation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.14110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.14110"}},"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/holarissun/Data-Centric-OPE","reach":{"status":"ok"}}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"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":6,"samples":[{"code_sha256_prefix":"d1f8a9fe735e4977","entry":"continuous_approx_equal","repo":"holarissun/Data-Centric-OPE","repo_kind":"official","path":"ope_algos_reg.py","file_url":"https://github.com/holarissun/Data-Centric-OPE/blob/HEAD/ope_algos_reg.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":"d1f8a9fe735e4977"}},{"code_sha256_prefix":"2028cdf297827961","entry":"direct_method_mse","repo":"holarissun/Data-Centric-OPE","repo_kind":"official","path":"ope_algos_reg.py","file_url":"https://github.com/holarissun/Data-Centric-OPE/blob/HEAD/ope_algos_reg.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":"2028cdf297827961"}},{"code_sha256_prefix":"0a882b973a8f824e","entry":"gaussian_probability","repo":"holarissun/Data-Centric-OPE","repo_kind":"official","path":"mdn.py","file_url":"https://github.com/holarissun/Data-Centric-OPE/blob/HEAD/mdn.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":"0a882b973a8f824e"}},{"code_sha256_prefix":"fdee614fa01549c8","entry":"log_prob_gaussian","repo":"holarissun/Data-Centric-OPE","repo_kind":"official","path":"ope_algos_reg.py","file_url":"https://github.com/holarissun/Data-Centric-OPE/blob/HEAD/ope_algos_reg.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":"fdee614fa01549c8"}},{"code_sha256_prefix":"b94e4004ae0d0c13","entry":"mdn_loss","repo":"holarissun/Data-Centric-OPE","repo_kind":"official","path":"mdn.py","file_url":"https://github.com/holarissun/Data-Centric-OPE/blob/HEAD/mdn.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":"b94e4004ae0d0c13"}},{"code_sha256_prefix":"5c382a5efb0a12aa","entry":"sample","repo":"holarissun/Data-Centric-OPE","repo_kind":"official","path":"mdn.py","file_url":"https://github.com/holarissun/Data-Centric-OPE/blob/HEAD/mdn.py","link_basis":"first_harvest_node","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":"5c382a5efb0a12aa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}