{"id":"https://openalex.org/W4225889670","doi":"https://doi.org/10.1109/cdc45484.2021.9682998","title":"Efficient Episodic Learning of Nonstationary and Unknown Zero-Sum Games Using Expert Game Ensembles","display_name":"Efficient Episodic Learning of Nonstationary and Unknown Zero-Sum Games Using Expert Game Ensembles","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W4225889670","doi":"https://doi.org/10.1109/cdc45484.2021.9682998"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9682998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9682998","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-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/A5049094147","display_name":"Yunian Pan","orcid":"https://orcid.org/0000-0002-7277-3657"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yunian Pan","raw_affiliation_strings":["New York University,Tandon School of Engineering,Department of Electrical and Computer Engineering,Brooklyn,NY,USA,11201"],"affiliations":[{"raw_affiliation_string":"New York University,Tandon School of Engineering,Department of Electrical and Computer Engineering,Brooklyn,NY,USA,11201","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081500464","display_name":"Quanyan Zhu","orcid":"https://orcid.org/0000-0002-0008-2953"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quanyan Zhu","raw_affiliation_strings":["New York University,Tandon School of Engineering,Department of Electrical and Computer Engineering,Brooklyn,NY,USA,11201"],"affiliations":[{"raw_affiliation_string":"New York University,Tandon School of Engineering,Department of Electrical and Computer Engineering,Brooklyn,NY,USA,11201","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049094147"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.3047,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54591105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1669","last_page":"1676"},"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":0.9930999875068665,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6958604454994202},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.6479842066764832},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.5726438760757446},{"id":"https://openalex.org/keywords/zero-sum-game","display_name":"Zero-sum game","score":0.5197374820709229},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.5028902888298035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4919678866863251},{"id":"https://openalex.org/keywords/normal-form-game","display_name":"Normal-form game","score":0.49003922939300537},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.4768710732460022},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.4757023751735687},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.46754589676856995},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.4128727316856384},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41232356429100037},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3794381320476532},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.357089638710022},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.3034902513027191},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20037761330604553},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.15315145254135132}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6958604454994202},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.6479842066764832},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.5726438760757446},{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.5197374820709229},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.5028902888298035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4919678866863251},{"id":"https://openalex.org/C155930848","wikidata":"https://www.wikidata.org/wiki/Q1069099","display_name":"Normal-form game","level":4,"score":0.49003922939300537},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.4768710732460022},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.4757023751735687},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.46754589676856995},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.4128727316856384},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41232356429100037},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3794381320476532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.357089638710022},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.3034902513027191},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20037761330604553},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.15315145254135132},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc45484.2021.9682998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9682998","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W102212266","https://openalex.org/W1480398149","https://openalex.org/W1570963478","https://openalex.org/W2009551863","https://openalex.org/W2067064328","https://openalex.org/W2168342951","https://openalex.org/W2971648973","https://openalex.org/W3035312163","https://openalex.org/W3115274232","https://openalex.org/W3124603229","https://openalex.org/W3158420576","https://openalex.org/W4287078737","https://openalex.org/W4297748926","https://openalex.org/W6604092932","https://openalex.org/W6769467942","https://openalex.org/W6785511337","https://openalex.org/W7071879600"],"related_works":["https://openalex.org/W3028528379","https://openalex.org/W4293772331","https://openalex.org/W2208861692","https://openalex.org/W1826220400","https://openalex.org/W2910530315","https://openalex.org/W1514842472","https://openalex.org/W2391693198","https://openalex.org/W2039104542","https://openalex.org/W2286377751","https://openalex.org/W1600141987"],"abstract_inverted_index":{"Game":[0],"theory":[1],"provides":[2],"essential":[3],"analysis":[4,131],"in":[5,35],"many":[6],"applications":[7],"of":[8,14,38,53,56,97,103],"strategic":[9],"interactions.":[10],"However,":[11],"the":[12,80,94,101,104,117,155,159,165],"question":[13],"how":[15],"to":[16,111,146],"construct":[17],"a":[18,36,113,137,143],"game":[19,58,83,98,141],"model":[20],"and":[21,47,65,77,100,132,148,157,164],"what":[22],"is":[23,26,109,125],"its":[24],"fidelity":[25],"seldom":[27],"addressed.":[28],"In":[29],"this":[30,123],"work,":[31],"we":[32],"consider":[33],"learning":[34,90,102],"class":[37],"repeated":[39],"zero-sum":[40],"games":[41],"with":[42],"unknown,":[43],"time-varying":[44],"payoff":[45],"matrix,":[46],"noisy":[48],"feedbacks,":[49],"by":[50],"making":[51],"use":[52,136],"an":[54,88],"ensemble":[55],"benchmark":[57],"models.":[59],"These":[60],"models":[61,99],"can":[62],"be":[63],"pre-trained":[64],"collected":[66],"dynamically":[67],"during":[68],"sequential":[69],"plays.":[70],"They":[71],"serve":[72],"as":[73,142],"prior":[74],"side":[75],"information":[76],"imperfectly":[78],"underpin":[79],"unknown":[81],"true":[82],"model.":[84],"We":[85,120,135,152],"propose":[86],"OFULinMat,":[87],"episodic":[89],"algorithm":[91,108,124],"that":[92,122],"integrates":[93],"adaptive":[95],"estimation":[96],"strategies.":[105],"The":[106],"proposed":[107],"shown":[110],"achieve":[112],"sublinear":[114],"bound":[115],"on":[116],"saddle-point":[118],"regret.":[119],"show":[121],"provably":[126],"efficient":[127],"through":[128],"both":[129],"theoretical":[130],"numerical":[133],"examples.":[134],"dynamic":[138],"honeypot":[139],"allocation":[140],"case":[144],"study":[145],"illustrate":[147],"corroborate":[149],"our":[150,162],"results.":[151],"also":[153],"discuss":[154],"relationship":[156],"highlight":[158],"difference":[160],"between":[161],"framework":[163],"classical":[166],"adversarial":[167],"multi-armed":[168],"bandit":[169],"framework.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}