{"id":"https://openalex.org/W4328051309","doi":"https://doi.org/10.1137/21m1468668","title":"Accelerated and Instance-Optimal Policy Evaluation with Linear Function Approximation","display_name":"Accelerated and Instance-Optimal Policy Evaluation with Linear Function Approximation","publication_year":2023,"publication_date":"2023-03-21","ids":{"openalex":"https://openalex.org/W4328051309","doi":"https://doi.org/10.1137/21m1468668"},"language":"en","primary_location":{"id":"doi:10.1137/21m1468668","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1137/21m1468668","pdf_url":null,"source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://dx.doi.org/10.1137/21m1468668","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100736706","display_name":"Tianjiao Li","orcid":"https://orcid.org/0000-0001-6660-0883"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianjiao Li","raw_affiliation_strings":["Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA"],"raw_orcid":"https://orcid.org/0000-0001-6660-0883","affiliations":[{"raw_affiliation_string":"Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042544900","display_name":"Guanghui Lan","orcid":"https://orcid.org/0000-0002-2103-087X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanghui Lan","raw_affiliation_strings":["Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085869933","display_name":"Ashwin Pananjady","orcid":"https://orcid.org/0000-0003-0824-9815"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashwin Pananjady","raw_affiliation_strings":["Industrial & Systems Engineering and Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA"],"raw_orcid":"https://orcid.org/0000-0003-0824-9815","affiliations":[{"raw_affiliation_string":"Industrial & Systems Engineering and Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.2608,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61777131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"5","issue":"1","first_page":"174","last_page":"200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998000264167786,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998000264167786,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9991999864578247,"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":0.9987000226974487,"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/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.6150853633880615},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.5970970392227173},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.5750483870506287},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5490956902503967},{"id":"https://openalex.org/keywords/independent-and-identically-distributed-random-variables","display_name":"Independent and identically distributed random variables","score":0.517006516456604},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47634032368659973},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.46241000294685364},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.46036943793296814},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4559730291366577},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.45256996154785156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3787016272544861},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3769547939300537},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.2174198031425476}],"concepts":[{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.6150853633880615},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.5970970392227173},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5750483870506287},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5490956902503967},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.517006516456604},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47634032368659973},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46241000294685364},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.46036943793296814},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4559730291366577},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.45256996154785156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3787016272544861},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3769547939300537},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.2174198031425476},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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":1,"locations":[{"id":"doi:10.1137/21m1468668","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1137/21m1468668","pdf_url":null,"source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1137/21m1468668","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1137/21m1468668","pdf_url":null,"source":{"id":"https://openalex.org/S4210229561","display_name":"SIAM Journal on Mathematics of Data Science","issn_l":"2577-0187","issn":["2577-0187"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Mathematics of Data Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G7249327428","display_name":null,"funder_award_id":"N00014-20-1-2089","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7933359309","display_name":"CIF: Medium: Learning, refining, and understanding models through relational feedback","funder_award_id":"2107455","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"},{"id":"https://openalex.org/F4320306164","display_name":"Simons Foundation","ror":"https://ror.org/01cmst727"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W1988795359","https://openalex.org/W2026040627","https://openalex.org/W2047152541","https://openalex.org/W2071983464","https://openalex.org/W2082569121","https://openalex.org/W2086161653","https://openalex.org/W2107726111","https://openalex.org/W2120339885","https://openalex.org/W2124541940","https://openalex.org/W2139418546","https://openalex.org/W2334782222","https://openalex.org/W2559655401","https://openalex.org/W2604272474","https://openalex.org/W2963156201","https://openalex.org/W2965299328","https://openalex.org/W3090442079","https://openalex.org/W3203759272","https://openalex.org/W4212774754","https://openalex.org/W4243772471","https://openalex.org/W4293508270"],"related_works":["https://openalex.org/W2016058626","https://openalex.org/W2474724840","https://openalex.org/W2895916002","https://openalex.org/W3110702597","https://openalex.org/W1530911128","https://openalex.org/W1814049089","https://openalex.org/W1570812264","https://openalex.org/W2073713056","https://openalex.org/W2369683208","https://openalex.org/W2084836983"],"abstract_inverted_index":{".We":[0],"study":[1],"the":[2,34,53,62,66,72,84,88,127,162,166],"problem":[3],"of":[4,65,104,115,157,179],"policy":[5],"evaluation":[6],"with":[7,19,61,168],"linear":[8],"function":[9],"approximation":[10],"and":[11,14,37,69,90,152,171],"present":[12],"efficient":[13],"practical":[15],"algorithms":[16,97],"that":[17,29,122,146],"come":[18],"strong":[20,155],"optimality":[21,180],"guarantees.":[22],"We":[23],"begin":[24],"by":[25,183],"proving":[26],"lower":[27,50,81,106,130,150],"bounds":[28,151],"establish":[30],"baselines":[31],"on":[32,52,83],"both":[33,149],"deterministic":[35,54],"error":[36,39,55,86],"stochastic":[38,85],"in":[40,56,87,120],"this":[41,134],"problem.":[42],"In":[43],"particular,":[44],"we":[45,70,110,136,160],"prove":[46,78],"an":[47,57,79,138],"oracle":[48,128],"complexity":[49,129],"bound":[51,82],"instance-dependent":[58,80,173],"norm":[59],"associated":[60],"stationary":[63],"distribution":[64],"transition":[67],"kernel,":[68],"use":[71],"local":[73],"asymptotic":[74],"minimax":[75],"machinery":[76],"to":[77,99,125,165],"independent":[89],"identically":[91],"distributed":[92],"(i.i.d.)":[93],"observation":[94],"model.":[95],"Existing":[96],"fail":[98],"match":[100],"at":[101],"least":[102],"one":[103],"these":[105],"bounds:":[107],"To":[108,132],"illustrate,":[109],"analyze":[111],"a":[112,154],"variance-reduced":[113,140],"variant":[114],"temporal":[116,142],"difference":[117,143],"learning,":[118],"showing":[119],"particular":[121],"it":[123],"fails":[124],"achieve":[126],"bound.":[131],"remedy":[133],"issue,":[135],"develop":[137],"accelerated,":[139],"fast":[141],"(VRFTD)":[144],"algorithm":[145,164],"simultaneously":[147],"matches":[148],"attains":[153],"notion":[156],"instance-optimality.":[158],"Finally,":[159],"extend":[161],"VRFTD":[163],"setting":[167],"Markovian":[169],"observations":[170],"provide":[172],"convergence":[174],"results.":[175],"Our":[176],"theoretical":[177],"guarantees":[178],"are":[181],"corroborated":[182],"numerical":[184],"experiments.Keywordspolicy":[185],"evaluationtemporal":[186],"differencevariance":[187],"reductionaccelerationMarkovian":[188],"noiseMSC":[189],"codes62M2068Q2590C1590C6093E10":[190]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}