{"id":"https://openalex.org/W7117135774","doi":"https://doi.org/10.1287/opre.2024.1019","title":"Post Reinforcement Learning Inference","display_name":"Post Reinforcement Learning Inference","publication_year":2025,"publication_date":"2025-12-24","ids":{"openalex":"https://openalex.org/W7117135774","doi":"https://doi.org/10.1287/opre.2024.1019"},"language":"en","primary_location":{"id":"doi:10.1287/opre.2024.1019","is_oa":false,"landing_page_url":"https://doi.org/10.1287/opre.2024.1019","pdf_url":null,"source":{"id":"https://openalex.org/S125775545","display_name":"Operations Research","issn_l":"0030-364X","issn":["0030-364X","1526-5463"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315699","host_organization_name":"Institute for Operations Research and the Management Sciences","host_organization_lineage":["https://openalex.org/P4310315699"],"host_organization_lineage_names":["Institute for Operations Research and the Management Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Operations Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121240675","display_name":"Vasilis Syrgkanis","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vasilis Syrgkanis","raw_affiliation_strings":["Management Science and Engineering, Stanford University, Stanford, California 94305"],"affiliations":[{"raw_affiliation_string":"Management Science and Engineering, Stanford University, Stanford, California 94305","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053491985","display_name":"Ruohan Zhan","orcid":"https://orcid.org/0000-0002-3426-2784"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ruohan Zhan","raw_affiliation_strings":["UCL School of Management, University College London, London E14 5AA, United Kingdom"],"affiliations":[{"raw_affiliation_string":"UCL School of Management, University College London, London E14 5AA, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5121240675"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.77197545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"74","issue":"2","first_page":"917","last_page":"957"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.7915999889373779,"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"}},"topics":[{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.7915999889373779,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.09369999915361404,"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":0.010300000198185444,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7635999917984009},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7505999803543091},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6890000104904175},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.616599977016449},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5730000138282776},{"id":"https://openalex.org/keywords/statistical-inference","display_name":"Statistical inference","score":0.5},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4952999949455261}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7635999917984009},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7505999803543091},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6890000104904175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6643999814987183},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.616599977016449},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5730000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5360000133514404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5134000182151794},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.5},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4952999949455261},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.3580999970436096},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.31949999928474426},{"id":"https://openalex.org/C95167961","wikidata":"https://www.wikidata.org/wiki/Q4483495","display_name":"Fiducial inference","level":5,"score":0.31610000133514404},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.31310001015663147},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.3086000084877014},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29280000925064087},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2791000008583069}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1287/opre.2024.1019","is_oa":false,"landing_page_url":"https://doi.org/10.1287/opre.2024.1019","pdf_url":null,"source":{"id":"https://openalex.org/S125775545","display_name":"Operations Research","issn_l":"0030-364X","issn":["0030-364X","1526-5463"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315699","host_organization_name":"Institute for Operations Research and the Management Sciences","host_organization_lineage":["https://openalex.org/P4310315699"],"host_organization_lineage_names":["Institute for Operations Research and the Management Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Operations Research","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6861612200737,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W27306700","https://openalex.org/W174791359","https://openalex.org/W1572302037","https://openalex.org/W1646707810","https://openalex.org/W1986844034","https://openalex.org/W2027795129","https://openalex.org/W2057510184","https://openalex.org/W2082299845","https://openalex.org/W2150291618","https://openalex.org/W2163084572","https://openalex.org/W2165612525","https://openalex.org/W2400529174","https://openalex.org/W2902572901","https://openalex.org/W3123670345","https://openalex.org/W3125459412","https://openalex.org/W3128382782","https://openalex.org/W3146985724","https://openalex.org/W3168126546","https://openalex.org/W3214102131","https://openalex.org/W4214717370","https://openalex.org/W4236362309","https://openalex.org/W4289519159","https://openalex.org/W4416063861"],"related_works":[],"abstract_inverted_index":{"In":[0],"\u201cPost":[1],"Reinforcement":[2],"Learning":[3],"Inference,\u201d":[4],"Vasilis":[5],"Syrgkanis":[6,48],"and":[7,44,49,76,83,89,102,116],"Ruohan":[8],"Zhan":[9,50],"develop":[10],"a":[11,96],"new":[12],"inferential":[13],"framework":[14],"for":[15,86,99],"data":[16],"collected":[17],"via":[18],"reinforcement":[19],"learning":[20],"(RL)":[21],"algorithms,":[22],"the":[23,71],"adaptive":[24],"systems":[25],"that":[26,61,70],"update":[27],"strategies":[28],"as":[29],"outcomes":[30],"unfold.":[31],"Traditional":[32],"statistical":[33],"methods":[34],"fail":[35],"in":[36],"this":[37,63],"setting":[38],"because":[39],"adaptivity":[40],"induces":[41],"time-varying":[42],"variance":[43,64],"dependence":[45],"across":[46],"samples.":[47],"propose":[51],"an":[52],"adaptively":[53,106],"weighted":[54,72],"generalized":[55],"method":[56,94],"of":[57],"moments":[58],"(AW-GMM)":[59],"estimator":[60,73],"stabilizes":[62],"through":[65],"data-dependent":[66],"weights.":[67],"They":[68],"prove":[69],"achieves":[74],"consistency":[75],"asymptotic":[77],"normality,":[78],"enabling":[79],"valid":[80],"hypothesis":[81],"testing":[82],"confidence":[84],"intervals":[85],"policy":[87],"values":[88],"dynamic":[90,113],"treatment":[91],"effects.":[92],"Their":[93],"provides":[95],"unified":[97],"approach":[98],"structural":[100],"estimation":[101],"inference":[103],"under":[104],"nonstationary,":[105],"generated":[107],"sequence":[108],"data,":[109],"with":[110],"applications":[111],"to":[112],"off-policy":[114],"evaluation":[115],"personalized":[117],"decision":[118],"systems.":[119]},"counts_by_year":[],"updated_date":"2026-03-21T06:30:42.041108","created_date":"2025-12-24T00:00:00"}