{"id":"https://openalex.org/W2109912732","doi":"https://doi.org/10.1109/tac.2009.2036333","title":"Adaptive Adversarial Multi-Armed Bandit Approach to Two-Person Zero-Sum Markov Games","display_name":"Adaptive Adversarial Multi-Armed Bandit Approach to Two-Person Zero-Sum Markov Games","publication_year":2010,"publication_date":"2010-01-20","ids":{"openalex":"https://openalex.org/W2109912732","doi":"https://doi.org/10.1109/tac.2009.2036333","mag":"2109912732"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2009.2036333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2009.2036333","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","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/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","Dept. of Computer Science & 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"]},{"raw_affiliation_string":"Dept. of Computer Science & Engineering, Sogang University, Seoul, South Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111765213","display_name":"Jiaqiao Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqiao Hu","raw_affiliation_strings":["Department of Applied Mathematics and Statistics, State University of New York, Stony Brook, NY, USA","Dept. of Appl. Math. & Stat., State Univ. of New York (SUNY), Stony Brook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Statistics, State University of New York, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I1327163397","https://openalex.org/I59553526"]},{"raw_affiliation_string":"Dept. of Appl. Math. & Stat., State Univ. of New York (SUNY), Stony Brook, NY, USA","institution_ids":["https://openalex.org/I1327163397"]}]},{"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":"M.C. Fu","raw_affiliation_strings":["School of Business and Institute of Systems Research, University of Maryland, College Park, MD, USA","Robert H. Smith School of Business; University of Maryland; College Park, MD USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Business and Institute of Systems Research, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"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":"S.I. Marcus","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Institute of Systems Research, University of Maryland, College Park, MD, USA","Dept of Electr. & Comput. Eng., Univ. of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Institute of Systems Research, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Dept of Electr. & Comput. Eng., Univ. of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5737,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.85432451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"55","issue":"2","first_page":"463","last_page":"468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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":1.0,"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":0.9988999962806702,"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":0.9983999729156494,"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/zero-sum-game","display_name":"Zero-sum game","score":0.7053253650665283},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.663862407207489},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6571382284164429},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6132854223251343},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5523074269294739},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5492019653320312},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5306764245033264},{"id":"https://openalex.org/keywords/finite-state","display_name":"Finite state","score":0.4933554232120514},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.46153223514556885},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4540553390979767},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.4292443096637726},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.42341727018356323},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4195074439048767},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4166443645954132},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4163147807121277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.38558635115623474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2579526901245117},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.18437251448631287},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16393160820007324}],"concepts":[{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.7053253650665283},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.663862407207489},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6571382284164429},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6132854223251343},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5523074269294739},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5492019653320312},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5306764245033264},{"id":"https://openalex.org/C2983497884","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite state","level":3,"score":0.4933554232120514},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.46153223514556885},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4540553390979767},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.4292443096637726},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.42341727018356323},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4195074439048767},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4166443645954132},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4163147807121277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38558635115623474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2579526901245117},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.18437251448631287},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16393160820007324},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2009.2036333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2009.2036333","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4300000071525574},{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1496590343","https://openalex.org/W1511309222","https://openalex.org/W1570963478","https://openalex.org/W1983916623","https://openalex.org/W1998498767","https://openalex.org/W2018528465","https://openalex.org/W2077902449","https://openalex.org/W2090697311","https://openalex.org/W2096229523","https://openalex.org/W2113618211","https://openalex.org/W2129512399","https://openalex.org/W2146376321","https://openalex.org/W2169194711","https://openalex.org/W6630766731"],"related_works":["https://openalex.org/W4388236136","https://openalex.org/W1050019105","https://openalex.org/W2807018115","https://openalex.org/W2107384771","https://openalex.org/W4200250224","https://openalex.org/W2126560268","https://openalex.org/W2285658092","https://openalex.org/W2014747857","https://openalex.org/W2482498454","https://openalex.org/W1598942703"],"abstract_inverted_index":{"This":[0],"technical":[1],"note":[2],"presents":[3],"a":[4,37,52],"recursive":[5],"sampling-based":[6],"algorithm":[7,20,74],"for":[8,29],"finite":[9],"horizon":[10],"two-person":[11],"zero-sum":[12],"Markov":[13],"games":[14],"(MGs)":[15],"based":[16],"on":[17],"the":[18,41,45,60,64,73,78,82],"Exp3":[19],"developed":[21],"by":[22],"Auer":[23],"et":[24],"al":[25],"<i":[26],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[27],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">.</i>":[28],"adaptive":[30],"adversarial":[31],"multi-armed":[32],"bandit":[33],"problems.":[34],"We":[35],"provide":[36],"finite-iteration":[38],"bound":[39],"to":[40,59],"equilibrium":[42,61],"value":[43,62],"of":[44,51,63,72,77,81],"induced":[46],"\u00bfsample":[47],"average":[48],"approximation":[49],"game\u00bf":[50],"given":[53,65],"MG":[54],"and":[55,69],"prove":[56],"asymptotic":[57],"convergence":[58],"MG.":[66],"The":[67],"time":[68],"space":[70,80],"complexities":[71],"are":[75],"independent":[76],"state":[79],"game.":[83]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}