{"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/deeply-debiased-off-policy-interval","title":"Deeply-Debiased Off-Policy Interval Estimation","arxiv_id":"2105.04646","date":"2021-05-10","proceeding":null,"authors":["Chengchun Shi","Runzhe Wan","Victor Chernozhukov","Rui Song"],"abstract":"Off-policy evaluation learns a target policy's value with a historical dataset generated by a different behavior policy. In addition to a point estimate, many applications would benefit significantly from having a confidence interval (CI) that quantifies the uncertainty of the point estimate. In this paper, we propose a novel deeply-debiasing procedure to construct an efficient, robust, and flexible CI on a target policy's value. Our method is justified by theoretical results and numerical experiments. A Python implementation of the proposed procedure is available at https://github.com/RunzheStat/D2OPE.","url_abs":"https://arxiv.org/abs/2105.04646v2","url_pdf":"https://arxiv.org/pdf/2105.04646v2.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":"deeply-debiased-off-policy-interval","repo_url":"https://github.com/RunzheStat/D2OPE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"off-policy-evaluation","task_name":"Off-policy evaluation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.04646","atlas_url":"https://app.syntology.ai/?focus=2105.04646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.04646"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/RunzheStat/D2OPE","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":7},"by_repo_kind":{"official":{"samples":9,"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":0,"samples":[{"code_sha256_prefix":"b929cf9dffdc887a","entry":"listinlist2list","repo":"RunzheStat/D2OPE","repo_kind":"official","path":"_util.py","file_url":"https://github.com/RunzheStat/D2OPE/blob/HEAD/_util.py","link_basis":"plan_row","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":"b929cf9dffdc887a"}},{"code_sha256_prefix":"fe85da14d45dd5ae","entry":"setminus","repo":"RunzheStat/D2OPE","repo_kind":"official","path":"_util.py","file_url":"https://github.com/RunzheStat/D2OPE/blob/HEAD/_util.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fe85da14d45dd5ae"}},{"code_sha256_prefix":"7b6f6a0ada2bb35c","entry":"cal_Bernstein_CI","repo":"RunzheStat/D2OPE","repo_kind":"official","path":"_IS.py","file_url":"https://github.com/RunzheStat/D2OPE/blob/HEAD/_IS.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b6f6a0ada2bb35c"}},{"code_sha256_prefix":"50895e5150c19e74","entry":"cal_step_IS","repo":"RunzheStat/D2OPE","repo_kind":"official","path":"_IS.py","file_url":"https://github.com/RunzheStat/D2OPE/blob/HEAD/_IS.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50895e5150c19e74"}},{"code_sha256_prefix":"7d3c6e37d22c4a6f","entry":"change_rate","repo":"RunzheStat/D2OPE","repo_kind":"official","path":"_RL/DQN.py","file_url":"https://github.com/RunzheStat/D2OPE/blob/HEAD/_RL/DQN.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d3c6e37d22c4a6f"}},{"code_sha256_prefix":"a9d18fac29e08110","entry":"get_std_of_RMSE","repo":"RunzheStat/D2OPE","repo_kind":"official","path":"TOY/_plot.py","file_url":"https://github.com/RunzheStat/D2OPE/blob/HEAD/TOY/_plot.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9d18fac29e08110"}},{"code_sha256_prefix":"73535df49f40fd66","entry":"get_width","repo":"RunzheStat/D2OPE","repo_kind":"official","path":"TOY/_plot.py","file_url":"https://github.com/RunzheStat/D2OPE/blob/HEAD/TOY/_plot.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73535df49f40fd66"}},{"code_sha256_prefix":"a246811bbf2a0a91","entry":"parmap","repo":"RunzheStat/D2OPE","repo_kind":"official","path":"_util.py","file_url":"https://github.com/RunzheStat/D2OPE/blob/HEAD/_util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a246811bbf2a0a91"}},{"code_sha256_prefix":"c9efb421a11d3764","entry":"plot_curves","repo":"RunzheStat/D2OPE","repo_kind":"official","path":"TOY/_plot.py","file_url":"https://github.com/RunzheStat/D2OPE/blob/HEAD/TOY/_plot.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c9efb421a11d3764"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}