{"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/data-efficient-policy-evaluation-through","title":"Data-Efficient Policy Evaluation Through Behavior Policy Search","arxiv_id":"1706.03469","date":"2017-06-12","proceeding":"ICML 2017 8","authors":["Josiah P. Hanna","Philip S. Thomas","Peter Stone","Scott Niekum"],"abstract":"We consider the task of evaluating a policy for a Markov decision process\n(MDP). The standard unbiased technique for evaluating a policy is to deploy the\npolicy and observe its performance. We show that the data collected from\ndeploying a different policy, commonly called the behavior policy, can be used\nto produce unbiased estimates with lower mean squared error than this standard\ntechnique. We derive an analytic expression for the optimal behavior policy ---\nthe behavior policy that minimizes the mean squared error of the resulting\nestimates. Because this expression depends on terms that are unknown in\npractice, we propose a novel policy evaluation sub-problem, behavior policy\nsearch: searching for a behavior policy that reduces mean squared error. We\npresent a behavior policy search algorithm and empirically demonstrate its\neffectiveness in lowering the mean squared error of policy performance\nestimates.","url_abs":"http://arxiv.org/abs/1706.03469v1","url_pdf":"http://arxiv.org/pdf/1706.03469v1.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":"data-efficient-policy-evaluation-through","repo_url":"https://github.com/Qmaoboy/Data-Efficient-Policy-Evaluation-Through-Behavior-Policy-Search","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.03469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.03469"}},"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/Qmaoboy/Data-Efficient-Policy-Evaluation-Through-Behavior-Policy-Search","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"0602cebbefc23592","entry":"IS","repo":"Qmaoboy/Data-Efficient-Policy-Evaluation-Through-Behavior-Policy-Search","repo_kind":"listed","path":"Acrobot_withBPG.py","file_url":"https://github.com/Qmaoboy/Data-Efficient-Policy-Evaluation-Through-Behavior-Policy-Search/blob/HEAD/Acrobot_withBPG.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0602cebbefc23592"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}