{"id":"https://openalex.org/W4200424214","doi":"https://doi.org/10.1111/rssb.12465","title":"Statistical Inference of the Value Function for Reinforcement Learning in Infinite-Horizon Settings","display_name":"Statistical Inference of the Value Function for Reinforcement Learning in Infinite-Horizon Settings","publication_year":2021,"publication_date":"2021-12-22","ids":{"openalex":"https://openalex.org/W4200424214","doi":"https://doi.org/10.1111/rssb.12465"},"language":"en","primary_location":{"id":"doi:10.1111/rssb.12465","doi":"https://doi.org/10.1111/rssb.12465","is_oa":false,"landing_page_url":"https://doi.org/10.1111/rssb.12465","pdf_url":null,"source":{"id":"https://openalex.org/S145009937","display_name":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","issn_l":"1369-7412","issn":["1369-7412","1467-9868"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-a-star","anvur-class-a","anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-1","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the Royal Statistical Society Series B: Statistical Methodology","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.04515","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025970743","display_name":"Chengchun Shi","orcid":"https://orcid.org/0000-0001-7773-2099","observed_orcids":["https://orcid.org/0000-0001-7773-2099"]},"institutions":[{"id":"https://openalex.org/I909854389","display_name":"London School of Economics and Political Science","ror":"https://ror.org/0090zs177","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I909854389"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chengchun Shi","raw_affiliation_strings":["London School of Economics and Political Science , London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"London School of Economics and Political Science , London , UK","institution_ids":["https://openalex.org/I909854389"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394044","display_name":"Sheng Zhang","orcid":"https://orcid.org/0000-0003-1034-6622","observed_orcids":["https://orcid.org/0000-0003-1034-6622"]},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Zhang","raw_affiliation_strings":["North Carolina State University , Raleigh , North Carolina , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University , Raleigh , North Carolina , USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059203764","display_name":"Wenbin Lu","orcid":"https://orcid.org/0000-0002-7320-4755","observed_orcids":["https://orcid.org/0000-0002-7320-4755"]},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenbin Lu","raw_affiliation_strings":["North Carolina State University , Raleigh , North Carolina , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University , Raleigh , North Carolina , USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089012283","display_name":"Rui Song","orcid":"https://orcid.org/0000-0003-1875-2115","observed_orcids":["https://orcid.org/0000-0003-1875-2115"]},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rui Song","raw_affiliation_strings":["North Carolina State University , Raleigh , North Carolina , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University , Raleigh , North Carolina , USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5089012283"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":{"value":2000,"currency":"GBP","value_usd":3000},"apc_paid":null,"fwci":2.463,"has_fulltext":true,"cited_by_count":48,"citation_normalized_percentile":{"value":0.90750744,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"84","issue":"3","first_page":"765","last_page":"793"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9911999702453613,"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":0.9911999702453613,"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":0.003700000001117587,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.0010999999940395355,"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":0.7699999809265137},{"id":"https://openalex.org/keywords/value-function","display_name":"value function","score":0.7289999723434448},{"id":"https://openalex.org/keywords/confidence-intervals","display_name":"confidence intervals","score":0.9079999923706055},{"id":"https://openalex.org/keywords/q-function","display_name":"Q-function","score":0.7689999938011169},{"id":"https://openalex.org/keywords/sieve-estimation","display_name":"sieve estimation","score":0.6520000100135803},{"id":"https://openalex.org/keywords/series-estimation","display_name":"series estimation","score":0.7670000195503235},{"id":"https://openalex.org/keywords/policy-evaluation","display_name":"policy evaluation","score":0.5490000247955322},{"id":"https://openalex.org/keywords/mobile-health","display_name":"mobile health","score":0.6010000109672546},{"id":"https://openalex.org/keywords/sequential-decision-making","display_name":"sequential decision making","score":0.6899999976158142}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8422926664352417},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7006098031997681},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6123384237289429},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5374212265014648},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.49946022033691406},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4789167642593384},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.46659234166145325},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4348357915878296},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38809338212013245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3647629916667938},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35143715143203735},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25294429063796997},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20284229516983032},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1111/rssb.12465","doi":"https://doi.org/10.1111/rssb.12465","is_oa":false,"landing_page_url":"https://doi.org/10.1111/rssb.12465","pdf_url":null,"source":{"id":"https://openalex.org/S145009937","display_name":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","issn_l":"1369-7412","issn":["1369-7412","1467-9868"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-a-star","anvur-class-a","anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-1","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the Royal Statistical Society Series B: Statistical Methodology","raw_type":"journal-article"},{"id":"pmh:oai:eprints.lse.ac.uk:110882","doi":null,"is_oa":false,"landing_page_url":"https://orcid.org/0000-0001-7773-2099>,","pdf_url":null,"source":{"id":"https://openalex.org/S4306401593","display_name":"London School of Economics and Political Science Research Online (London School of Economics and Political Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I909854389","host_organization_name":"London School of Economics and Political Science","host_organization_lineage":["https://openalex.org/I909854389"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:arXiv.org:2001.04515","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.04515","pdf_url":"https://arxiv.org/pdf/2001.04515","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":"pmh:oai:researchonline.lse.ac.uk:110882","doi":null,"is_oa":true,"landing_page_url":"https://orcid.org/0000-0001-7773-2099>,","pdf_url":"https://researchonline.lse.ac.uk/id/eprint/110882/1/Statistical_Inference_of_the_Value_Function_for.pdf","source":{"id":"https://openalex.org/S4306400050","display_name":"London School of Economics and Political Science Theses Online (London School of Economics and Political Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I909854389","host_organization_name":"London School of Economics and Political Science","host_organization_lineage":["https://openalex.org/I909854389"],"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":"Article"},{"id":"pmh:oai:RePEc:ehl:lserod:110882","doi":null,"is_oa":false,"landing_page_url":"http://eprints.lse.ac.uk/110882/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"preprint"},{"id":"doi:10.48550/arxiv.2001.04515","doi":"https://doi.org/10.48550/arxiv.2001.04515","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.04515","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:2001.04515","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.04515","pdf_url":"https://arxiv.org/pdf/2001.04515","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":[{"id":"https://openalex.org/G1476930183","display_name":"Offline Statistical Reinforcement Learning with Applications in Precision Health","funder_award_id":"2113637","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8298277537","display_name":"CAREER:  Semiparametric and Machine Learning Approaches to Big Data Challenges in Precision Medicine","funder_award_id":"1555244","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W41554520","https://openalex.org/W166862392","https://openalex.org/W1741702827","https://openalex.org/W1996437515","https://openalex.org/W2038146650","https://openalex.org/W2043919728","https://openalex.org/W2044974898","https://openalex.org/W2046262211","https://openalex.org/W2076051662","https://openalex.org/W2100967164","https://openalex.org/W2116034036","https://openalex.org/W2120346334","https://openalex.org/W2124267516","https://openalex.org/W2145339207","https://openalex.org/W2164985671","https://openalex.org/W2165612525","https://openalex.org/W2207219039","https://openalex.org/W2234859443","https://openalex.org/W2235073584","https://openalex.org/W2257979135","https://openalex.org/W2273088453","https://openalex.org/W2291713832","https://openalex.org/W2334782222","https://openalex.org/W2411613392","https://openalex.org/W2584650420","https://openalex.org/W2788125442","https://openalex.org/W2802230479","https://openalex.org/W2802737765","https://openalex.org/W2808810245","https://openalex.org/W2889087356","https://openalex.org/W2889748820","https://openalex.org/W2910754418","https://openalex.org/W2969337892","https://openalex.org/W2980414783","https://openalex.org/W2981972696","https://openalex.org/W3047597742","https://openalex.org/W3161330381","https://openalex.org/W3173431779","https://openalex.org/W4212774754","https://openalex.org/W4303674035"],"related_works":["https://openalex.org/W2105114545","https://openalex.org/W3093731986","https://openalex.org/W7212172939","https://openalex.org/W3045055178","https://openalex.org/W4221156641","https://openalex.org/W4384927887","https://openalex.org/W7147686366","https://openalex.org/W2809151193","https://openalex.org/W3157634301","https://openalex.org/W7203483596"],"abstract_inverted_index":{"Abstract":[0],"Reinforcement":[1],"learning":[2,182],"is":[3,30,153,197],"a":[4,28,53,80,104,172],"general":[5],"technique":[6],"that":[7,139,180],"allows":[8],"an":[9,13,19],"agent":[10],"to":[11,47,67,71,86,110,135,160,171],"learn":[12],"optimal":[14,151],"policy":[15,29,81,94,115,152],"and":[16,116,178],"interact":[17],"with":[18,79],"environment":[20],"in":[21,56,147],"sequential":[22],"decision-making":[23],"problems.":[24],"The":[25,41],"goodness":[26],"of":[27,43,63,126,131,193],"measured":[31],"by":[32],"its":[33,88,117],"value":[34,55,118],"function":[35,76],"starting":[36],"from":[37,174],"some":[38],"initial":[39],"state.":[40],"focus":[42],"this":[44],"paper":[45],"was":[46],"construct":[48],"confidence":[49,89],"intervals":[50],"(CIs)":[51],"for":[52],"policy\u2019s":[54],"infinite":[57],"horizon":[58],"settings":[59],"where":[60,149],"the":[61,73,92,97,113,124,129,140,150,168,194],"number":[62,125,130],"decision":[64,132],"points":[65,133],"diverges":[66,134],"infinity.":[68],"We":[69,166],"propose":[70,103],"model":[72],"action-value":[74],"state":[75],"(Q-function)":[77],"associated":[78],"based":[82],"on":[83,96],"series/sieve":[84],"method":[85,109,170],"derive":[87],"interval.":[90],"When":[91],"target":[93],"depends":[95],"observed":[98],"data":[99],"as":[100,122],"well,":[101],"we":[102,137],"SequentiAl":[105],"Value":[106],"Evaluation":[107],"(SAVE)":[108],"recursively":[111],"update":[112],"estimated":[114],"estimator.":[119],"As":[120],"long":[121],"either":[123],"trajectories":[127],"or":[128],"infinity,":[136],"show":[138],"proposed":[141,169,195],"CI":[142],"achieves":[143],"nominal":[144],"coverage":[145],"even":[146],"cases":[148],"not":[154],"unique.":[155],"Simulation":[156],"studies":[157,177],"are":[158],"conducted":[159],"back":[161],"up":[162],"our":[163],"theoretical":[164],"findings.":[165],"apply":[167],"dataset":[173],"mobile":[175],"health":[176,188],"find":[179],"reinforcement":[181],"algorithms":[183],"could":[184],"help":[185],"improve":[186],"patient\u2019s":[187],"status.":[189],"A":[190],"Python":[191],"implementation":[192],"procedure":[196],"available":[198],"at":[199],"https://github.com/shengzhang37/SAVE.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2021-12-31T00:00:00"}