{"id":"https://openalex.org/W2157445687","doi":"https://doi.org/10.1109/cdc.2007.4434044","title":"Adversarial multi-armed bandit approach to two-person zero-sum Markov games","display_name":"Adversarial multi-armed bandit approach to two-person zero-sum Markov games","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2157445687","doi":"https://doi.org/10.1109/cdc.2007.4434044","mag":"2157445687"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2007.4434044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2007.4434044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 46th IEEE Conference on Decision and Control","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041693183","display_name":"Hyeong Soo Chang","orcid":"https://orcid.org/0000-0003-3298-0018"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeong Soo Chang","raw_affiliation_strings":["Department of Computer Science and Engineering, Sogang University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, Seoul, South Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000889975","display_name":"Michael C. Fu","orcid":"https://orcid.org/0000-0003-2105-4932"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael C. Fu","raw_affiliation_strings":["The Robert H. Smith School of Business, University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Robert H. Smith School of Business, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013807415","display_name":"Steven I. Marcus","orcid":"https://orcid.org/0000-0002-4926-9567"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven I. Marcus","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":null,"first_page":"127","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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/T12288","display_name":"Optimization and Search Problems","score":0.9923999905586243,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6904946565628052},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6215915679931641},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5639099478721619},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5189740061759949},{"id":"https://openalex.org/keywords/zero-sum-game","display_name":"Zero-sum game","score":0.49006807804107666},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.47309568524360657},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41916725039482117},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.3741058111190796},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.2945311367511749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29300034046173096},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2680777311325073},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1782681941986084},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13042792677879333}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6904946565628052},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6215915679931641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5639099478721619},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5189740061759949},{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.49006807804107666},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.47309568524360657},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41916725039482117},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3741058111190796},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.2945311367511749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29300034046173096},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2680777311325073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1782681941986084},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13042792677879333},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2007.4434044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2007.4434044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 46th IEEE Conference on Decision and Control","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1496590343","https://openalex.org/W1570963478","https://openalex.org/W1576452626","https://openalex.org/W1983916623","https://openalex.org/W2018528465","https://openalex.org/W2077902449","https://openalex.org/W2096229523","https://openalex.org/W2102534625","https://openalex.org/W2119567691","https://openalex.org/W2129512399","https://openalex.org/W2334782222","https://openalex.org/W2400458653"],"related_works":["https://openalex.org/W2739681863","https://openalex.org/W3170723600","https://openalex.org/W4287122294","https://openalex.org/W2039187327","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W1877069894","https://openalex.org/W2367222340"],"abstract_inverted_index":{"A":[0],"sampling-based":[1],"algorithm":[2,14,35,158],"for":[3,15,36,125,159,164],"solving":[4,37,126],"stochastic":[5],"optimization":[6],"problems,":[7],"based":[8],"on":[9],"Auer":[10],"et":[11],"al.\u2019s":[12],"Exp3":[13],"\u201cadversarial":[16],"mufti-armed":[17],"bandit":[18],"problems,\u201d":[19],"has":[20],"been":[21],"recently":[22],"presented":[23],"by":[24,66],"the":[25,29,33,51,56,60,67,71,75,79,85,99,102,106,111,117,120,137,141,151,166],"authors.":[26],"In":[27],"particular,":[28],"authors":[30],"recursively":[31,156],"extended":[32,124,157],"Exp3-based":[34],"finite-horizon":[38],"Markov":[39,129],"decision":[40],"processes":[41],"(MDPs)":[42],"and":[43,147],"analyzed":[44],"its":[45],"finite-iteration":[46,134],"performance":[47],"in":[48,70,91,110],"terms":[49],"of":[50,59,78,105,140,168],"expected":[52,80],"bias":[53,81],"relative":[54],"to":[55,95,98,101,116,136,150],"maximum":[57],"value":[58,104,139],"\u201crecursive":[61,143],"sample-average-approximation":[62],"(SAA)\u201d":[63],"problem":[64,109,146],"induced":[65,142],"sampling":[68,86],"process":[69],"algorithm,":[72],"showing":[73],"that":[74],"upper":[76],"bound":[77,135],"approaches":[82],"zero":[83],"as":[84],"size":[87],"per":[88],"state":[89],"sampled":[90],"each":[92],"stage":[93],"goes":[94],"infinity,":[96],"leading":[97],"convergence":[100,149],"optimal":[103],"original":[107],"MDP":[108],"limit.":[112],"As":[113],"a":[114,133],"sequel":[115],"previous":[118],"work,":[119],"idea":[121],"is":[122],"further":[123],"two-person":[127],"zero-sum":[128],"games":[130],"(MGs),":[131],"providing":[132],"equilibrium":[138,153],"SAA":[144],"game\u201d":[145],"asymptotic":[148],"true":[152],"value.":[154],"The":[155],"MGs":[160],"can":[161],"be":[162],"used":[163],"breaking":[165],"curse":[167],"dimensionality.":[169]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}