{"id":"https://openalex.org/W3106200437","doi":"https://doi.org/10.1137/20m1381691","title":"Simple and Optimal Methods for Stochastic Variational Inequalities, II: Markovian Noise and Policy Evaluation in Reinforcement Learning","display_name":"Simple and Optimal Methods for Stochastic Variational Inequalities, II: Markovian Noise and Policy Evaluation in Reinforcement Learning","publication_year":2022,"publication_date":"2022-05-26","ids":{"openalex":"https://openalex.org/W3106200437","doi":"https://doi.org/10.1137/20m1381691","mag":"3106200437"},"language":"en","primary_location":{"id":"doi:10.1137/20m1381691","is_oa":false,"landing_page_url":"https://doi.org/10.1137/20m1381691","pdf_url":null,"source":{"id":"https://openalex.org/S928796702","display_name":"SIAM Journal on Optimization","issn_l":"1052-6234","issn":["1052-6234","1095-7189"],"is_oa":false,"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 Optimization","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/A5052705774","display_name":"Georgios Kotsalis","orcid":"https://orcid.org/0000-0001-8105-4251"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Georgios Kotsalis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042544900","display_name":"Guanghui Lan","orcid":"https://orcid.org/0000-0002-2103-087X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanghui Lan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100736706","display_name":"Tianjiao Li","orcid":"https://orcid.org/0000-0001-6660-0883"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianjiao Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052705774"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9885,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.87891829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"32","issue":"2","first_page":"1120","last_page":"1155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9858999848365784,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.975600004196167,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6551408171653748},{"id":"https://openalex.org/keywords/subgradient-method","display_name":"Subgradient method","score":0.6544650197029114},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5769097805023193},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4921845495700836},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.46666544675827026},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4615936279296875},{"id":"https://openalex.org/keywords/variational-inequality","display_name":"Variational inequality","score":0.4482927620410919},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4265373647212982},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.42591628432273865},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41783881187438965},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4001428484916687},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37808364629745483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15589910745620728}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6551408171653748},{"id":"https://openalex.org/C158968445","wikidata":"https://www.wikidata.org/wiki/Q7631150","display_name":"Subgradient method","level":2,"score":0.6544650197029114},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5769097805023193},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4921845495700836},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.46666544675827026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4615936279296875},{"id":"https://openalex.org/C161999928","wikidata":"https://www.wikidata.org/wiki/Q4556320","display_name":"Variational inequality","level":2,"score":0.4482927620410919},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4265373647212982},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.42591628432273865},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41783881187438965},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4001428484916687},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37808364629745483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15589910745620728},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/20m1381691","is_oa":false,"landing_page_url":"https://doi.org/10.1137/20m1381691","pdf_url":null,"source":{"id":"https://openalex.org/S928796702","display_name":"SIAM Journal on Optimization","issn_l":"1052-6234","issn":["1052-6234","1095-7189"],"is_oa":false,"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 Optimization","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2278043753","display_name":null,"funder_award_id":"W911NF-18-1-0223","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"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"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1529558080","https://openalex.org/W1568229137","https://openalex.org/W1569273527","https://openalex.org/W1980404857","https://openalex.org/W1990585910","https://openalex.org/W1995713768","https://openalex.org/W2018807138","https://openalex.org/W2045744861","https://openalex.org/W2064076655","https://openalex.org/W2075268401","https://openalex.org/W2082569121","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2119567691","https://openalex.org/W2121703796","https://openalex.org/W2121863487","https://openalex.org/W2124477018","https://openalex.org/W2139418546","https://openalex.org/W2156737235","https://openalex.org/W2798888671","https://openalex.org/W2806157618","https://openalex.org/W2896292273","https://openalex.org/W2963818535","https://openalex.org/W2965002481","https://openalex.org/W3015646168","https://openalex.org/W3025638325","https://openalex.org/W3041202696","https://openalex.org/W3096202298","https://openalex.org/W3106345847","https://openalex.org/W4254807044","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2755725405","https://openalex.org/W2962762987","https://openalex.org/W2781777036","https://openalex.org/W2078980565","https://openalex.org/W3196983597","https://openalex.org/W4394850849","https://openalex.org/W2503607608","https://openalex.org/W1991765628","https://openalex.org/W2072534783","https://openalex.org/W3209321203"],"abstract_inverted_index":{"The":[0],"focus":[1],"of":[2,17,61,86,91,103,120,144,152,167,177,203,211,236],"this":[3],"paper":[4],"is":[5,21,240],"on":[6,36],"stochastic":[7,23,49,104,113,179,207],"variational":[8],"inequalities":[9],"(VI)":[10],"under":[11],"Markovian":[12],"noise.":[13],"A":[14],"prominent":[15],"application":[16],"our":[18],"algorithmic":[19],"developments":[20],"the":[22,33,59,88,100,153,178,183,195,206,212,225,237],"policy":[24,114,222],"evaluation":[25],"problem":[26],"in":[27,32,99,107],"reinforcement":[28],"learning.":[29],"Prior":[30],"investigations":[31],"literature":[34],"focused":[35],"temporal":[37],"difference":[38],"(TD)":[39],"learning":[40,123],"by":[41,48,127],"employing":[42],"nonsmooth":[43],"finite":[44],"time":[45],"analysis":[46,142,151],"motivated":[47,126],"subgradient":[50],"descent":[51],"leading":[52],"to":[53,70,112,194,247],"certain":[54],"limitations.":[55],"These":[56],"limitations":[57],"encompass":[58],"requirement":[60],"analyzing":[62],"a":[63,72,78,118,140,168,216,233],"modified":[64],"TD":[65,122,155,170,197],"algorithm":[66,156,171,199,238],"that":[67,131,157,173,239],"involves":[68,174],"projection":[69],"an":[71,149],"priori":[73],"defined":[74],"Euclidean":[75],"ball,":[76],"achieving":[77],"nonoptimal":[79],"convergence":[80,228],"rate":[81],"and":[82,106,185,205],"no":[83],"clear":[84],"way":[85],"deriving":[87],"beneficial":[89],"effects":[90],"parallel":[92,161],"implementation.":[93,162],"Our":[94],"approach":[95],"remedies":[96],"these":[97],"shortcomings":[98],"broader":[101],"context":[102],"VIs":[105],"particular":[108],"when":[109],"it":[110],"comes":[111],"evaluation.":[115],"We":[116,146,230],"developed":[117],"variety":[119],"simple":[121],"type":[124],"algorithms":[125],"its":[128,133],"original":[129],"version":[130,235],"maintain":[132],"simplicity,":[134],"while":[135],"offering":[136],"distinct":[137],"advantages":[138],"from":[139,160],"nonasymptotic":[141],"point":[143],"view.":[145],"first":[147],"provide":[148],"improved":[150,188],"standard":[154],"can":[158],"benefit":[159],"Then":[163],"we":[164],"present":[165],"versions":[166],"conditional":[169],"(CTD),":[172],"periodic":[175],"updates":[176],"iterates,":[180],"which":[181,200],"reduce":[182],"bias":[184],"therefore":[186],"exhibit":[187],"iteration":[189],"complexity.":[190],"This":[191],"brings":[192],"us":[193],"fast":[196],"(FTD)":[198],"combines":[201],"elements":[202],"CTD":[204],"operator":[208],"extrapolation":[209],"method":[210],"companion":[213],"paper.":[214],"For":[215],"novel":[217],"index":[218],"resetting":[219],"step":[220],"size":[221],"FTD":[223],"exhibits":[224],"best":[226],"known":[227],"rate.":[229],"also":[231],"devised":[232],"robust":[234],"particularly":[241],"suitable":[242],"for":[243],"discounting":[244],"factors":[245],"close":[246],"1.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}