{"id":"https://openalex.org/W4387074916","doi":"https://doi.org/10.48550/arxiv.2309.13278","title":"Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework","display_name":"Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework","publication_year":2023,"publication_date":"2023-09-23","ids":{"openalex":"https://openalex.org/W4387074916","doi":"https://doi.org/10.48550/arxiv.2309.13278"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.13278","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.13278","pdf_url":"https://arxiv.org/pdf/2309.13278","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.13278","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028993237","display_name":"Wenzhuo Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Wenzhuo","raw_affiliation_strings":["University of California Irvine ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Irvine ,","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332396","display_name":"Yuhan Li","orcid":"https://orcid.org/0000-0002-0133-7065","observed_orcids":["https://orcid.org/0000-0002-0133-7065"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Yuhan","raw_affiliation_strings":["University of Illinois Urbana Champaign ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana Champaign ,","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076762447","display_name":"Ruoqing Zhu","orcid":"https://orcid.org/0000-0002-0753-5716","observed_orcids":["https://orcid.org/0000-0002-0753-5716"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhu, Ruoqing","raw_affiliation_strings":["University of Illinois Urbana Champaign ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana Champaign ,","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029794342","display_name":"Annie Qu","orcid":"https://orcid.org/0000-0002-8396-7828","observed_orcids":["https://orcid.org/0000-0002-8396-7828"]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qu, Annie","raw_affiliation_strings":["University of California Irvine ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Irvine ,","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9365000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9365000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.03449999913573265,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.006800000090152025,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/off-policy-evaluation","display_name":"off-policy evaluation","score":0.9940000176429749},{"id":"https://openalex.org/keywords/confidence-intervals","display_name":"confidence intervals","score":0.7649999856948853},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.9639999866485596},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"importance sampling","score":0.5260000228881836},{"id":"https://openalex.org/keywords/error-quantification","display_name":"error quantification","score":0.6029999852180481},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8180000185966492},{"id":"https://openalex.org/keywords/offline-data","display_name":"offline data","score":0.5699999928474426},{"id":"https://openalex.org/keywords/supermartingales","display_name":"supermartingales","score":0.5920000076293945},{"id":"https://openalex.org/keywords/martingales","display_name":"martingales","score":0.7879999876022339},{"id":"https://openalex.org/keywords/time-dependent-data","display_name":"time-dependent data","score":0.699999988079071},{"id":"https://openalex.org/keywords/function-approximation","display_name":"function approximation","score":0.5989999771118164},{"id":"https://openalex.org/keywords/mobile-health","display_name":"mobile health","score":0.546999990940094},{"id":"https://openalex.org/keywords/type-1-diabetes","display_name":"type 1 diabetes","score":0.8830000162124634}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.671664297580719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6710380911827087},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6381192207336426},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5401822924613953},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43757447600364685},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3993625044822693},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36913207173347473},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24243202805519104},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22756356000900269},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2309.13278","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.13278","pdf_url":"https://arxiv.org/pdf/2309.13278","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2309.13278","doi":"https://doi.org/10.48550/arxiv.2309.13278","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.13278","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.13278","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.13278","pdf_url":"https://arxiv.org/pdf/2309.13278","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387074916.pdf","grobid_xml":"https://content.openalex.org/works/W4387074916.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4221156641","https://openalex.org/W3161330381","https://openalex.org/W4282981580","https://openalex.org/W4409364174","https://openalex.org/W3093731986","https://openalex.org/W3005407492","https://openalex.org/W7213590418","https://openalex.org/W6889779352","https://openalex.org/W4391020688","https://openalex.org/W3119650156"],"abstract_inverted_index":{"We":[0],"study":[1],"high-confidence":[2],"off-policy":[3],"evaluation":[4],"in":[5,50,196,210],"the":[6,14,24,55,63,67,71,85,91,100,119,123,126,135,143,146,150,156,205],"context":[7],"of":[8,88,125,145,204],"infinite-horizon":[9],"Markov":[10],"decision":[11],"processes,":[12],"where":[13],"objective":[15],"is":[16,166,189,208],"to":[17,104,148,158,168],"establish":[18],"a":[19,44,107,114,130,139,179],"confidence":[20],"interval":[21],"(CI)":[22],"for":[23],"target":[25,68],"policy":[26,69],"value":[27],"using":[28],"only":[29],"offline":[30,72],"data":[31,170],"pre-collected":[32],"from":[33,60],"unknown":[34],"behavior":[35],"policies.":[36],"This":[37,110],"task":[38],"faces":[39],"two":[40,86],"primary":[41],"challenges:":[42],"providing":[43],"comprehensive":[45],"and":[46,53,70,99,154,192,213],"rigorous":[47],"error":[48,80,93],"quantification":[49],"CI":[51,157],"estimation,":[52],"addressing":[54],"distributional":[56,162],"shift":[57],"that":[58,186],"results":[59],"discrepancies":[61],"between":[62,118],"distribution":[64],"induced":[65],"by":[66,76],"data-generating":[73],"process.":[74],"Motivated":[75],"an":[77,214],"innovative":[78],"unified":[79,111],"analysis,":[81],"we":[82,184],"jointly":[83],"quantify":[84],"sources":[87],"estimation":[89],"errors:":[90],"misspecification":[92],"on":[94,129],"modeling":[95],"marginalized":[96],"importance":[97],"weights":[98],"statistical":[101],"uncertainty":[102],"due":[103],"sampling,":[105],"within":[106],"single":[108],"interval.":[109],"framework":[112],"reveals":[113],"previously":[115],"hidden":[116],"tradeoff":[117,147],"errors,":[120],"which":[121],"undermines":[122],"tightness":[124],"CI.":[127],"Relying":[128],"carefully":[131],"designed":[132],"discriminator":[133],"function,":[134],"proposed":[136,206],"estimator":[137],"achieves":[138],"dual":[140],"purpose:":[141],"breaking":[142],"curse":[144],"attain":[149],"tightest":[151],"possible":[152],"CI,":[153],"adapting":[155],"ensure":[159],"robustness":[160],"against":[161],"shifts.":[163],"Our":[164],"method":[165,207],"applicable":[167],"time-dependent":[169],"without":[171],"assuming":[172],"any":[173],"weak":[174],"dependence":[175],"conditions":[176],"via":[177],"leveraging":[178],"local":[180],"supermartingale/martingale":[181],"structure.":[182],"Theoretically,":[183],"show":[185],"our":[187],"algorithm":[188],"sample-efficient,":[190],"error-robust,":[191],"provably":[193],"convergent":[194],"even":[195],"non-linear":[197],"function":[198],"approximation":[199],"settings.":[200],"The":[201],"numerical":[202],"performance":[203],"examined":[209],"synthetic":[211],"datasets":[212],"OhioT1DM":[215],"mobile":[216],"health":[217],"study.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-09-27T00:00:00"}