{"id":"https://openalex.org/W4285092776","doi":"https://doi.org/10.1145/3490486.3538289","title":"Fictitious Play in Markov Games with Single Controller","display_name":"Fictitious Play in Markov Games with Single Controller","publication_year":2022,"publication_date":"2022-07-12","ids":{"openalex":"https://openalex.org/W4285092776","doi":"https://doi.org/10.1145/3490486.3538289"},"language":"en","primary_location":{"id":"doi:10.1145/3490486.3538289","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3490486.3538289","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3490486.3538289","source":{"id":"https://openalex.org/S4363608973","display_name":"Proceedings of the 23rd ACM Conference on Economics and Computation","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM Conference on Economics and Computation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3490486.3538289","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081851582","display_name":"Muhammed O. Sayin","orcid":"https://orcid.org/0000-0001-5779-3986"},"institutions":[{"id":"https://openalex.org/I168864056","display_name":"Bilkent University","ror":"https://ror.org/02vh8a032","country_code":"TR","type":"education","lineage":["https://openalex.org/I168864056"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Muhammed O. Sayin","raw_affiliation_strings":["Bilkent University, Ankara, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bilkent University, Ankara, Turkey","institution_ids":["https://openalex.org/I168864056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047410441","display_name":"Kaiqing Zhang","orcid":"https://orcid.org/0000-0002-7446-7581"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaiqing Zhang","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067307504","display_name":"Asuman Ozdaglar","orcid":"https://orcid.org/0000-0002-1827-1285"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asuman Ozdaglar","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3168,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.89677078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"919","last_page":"936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9995999932289124,"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/T11031","display_name":"Game Theory and Applications","score":0.9995999932289124,"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":0.9990000128746033,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9957000017166138,"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/mathematical-economics","display_name":"Mathematical economics","score":0.7265199422836304},{"id":"https://openalex.org/keywords/markov-perfect-equilibrium","display_name":"Markov perfect equilibrium","score":0.7215906977653503},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7052676677703857},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.7026480436325073},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.6684898138046265},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.6499419212341309},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.6044926047325134},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.585014820098877},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5676496624946594},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.560754656791687},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.5103136897087097},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4773012399673462},{"id":"https://openalex.org/keywords/equilibrium-selection","display_name":"Equilibrium selection","score":0.47500574588775635},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.4689343273639679},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.45898211002349854},{"id":"https://openalex.org/keywords/zero-sum-game","display_name":"Zero-sum game","score":0.44700056314468384},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.43335890769958496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31626081466674805},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.2233678102493286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1904314160346985},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15690293908119202},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07959431409835815}],"concepts":[{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.7265199422836304},{"id":"https://openalex.org/C67091656","wikidata":"https://www.wikidata.org/wiki/Q6771328","display_name":"Markov perfect equilibrium","level":3,"score":0.7215906977653503},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7052676677703857},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.7026480436325073},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.6684898138046265},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6499419212341309},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.6044926047325134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.585014820098877},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5676496624946594},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.560754656791687},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.5103136897087097},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4773012399673462},{"id":"https://openalex.org/C164407509","wikidata":"https://www.wikidata.org/wiki/Q5384490","display_name":"Equilibrium selection","level":4,"score":0.47500574588775635},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.4689343273639679},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45898211002349854},{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.44700056314468384},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.43335890769958496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31626081466674805},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2233678102493286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1904314160346985},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15690293908119202},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07959431409835815},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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":2,"locations":[{"id":"doi:10.1145/3490486.3538289","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3490486.3538289","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3490486.3538289","source":{"id":"https://openalex.org/S4363608973","display_name":"Proceedings of the 23rd ACM Conference on Economics and Computation","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM Conference on Economics and Computation","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.bilkent.edu.tr:11693/111763","is_oa":false,"landing_page_url":"http://hdl.handle.net/11693/111763","pdf_url":null,"source":{"id":"https://openalex.org/S4306400079","display_name":"Bilkent University Institutional Repository (Bilkent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I168864056","host_organization_name":"Bilkent University","host_organization_lineage":["https://openalex.org/I168864056"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 23rd ACM Conference on Economics and Computation","raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.1145/3490486.3538289","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3490486.3538289","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3490486.3538289","source":{"id":"https://openalex.org/S4363608973","display_name":"Proceedings of the 23rd ACM Conference on Economics and Computation","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM Conference on Economics and Computation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G62546385","display_name":null,"funder_award_id":"BIDEB 2232","funder_id":"https://openalex.org/F4320322626","funder_display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu"},{"id":"https://openalex.org/G953776113","display_name":null,"funder_award_id":"2232-B","funder_id":"https://openalex.org/F4320322626","funder_display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu"}],"funders":[{"id":"https://openalex.org/F4320322626","display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu","ror":"https://ror.org/04w9kkr77"},{"id":"https://openalex.org/F4320334743","display_name":"Defence Science and Technology Agency - Singapore","ror":"https://ror.org/02rvm6b03"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285092776.pdf","grobid_xml":"https://content.openalex.org/works/W4285092776.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W606533219","https://openalex.org/W1480317510","https://openalex.org/W1542941925","https://openalex.org/W1570963478","https://openalex.org/W1907356258","https://openalex.org/W1964757264","https://openalex.org/W1967250398","https://openalex.org/W1968136409","https://openalex.org/W1981609310","https://openalex.org/W2024438722","https://openalex.org/W2059765339","https://openalex.org/W2067399933","https://openalex.org/W2076621463","https://openalex.org/W2099618002","https://openalex.org/W2118247617","https://openalex.org/W2149254401","https://openalex.org/W2167957526","https://openalex.org/W2176451521","https://openalex.org/W2492629073","https://openalex.org/W2612690371","https://openalex.org/W2787689390","https://openalex.org/W2962990479","https://openalex.org/W2991046523","https://openalex.org/W3043098219","https://openalex.org/W3205061452","https://openalex.org/W3205079722","https://openalex.org/W4212774754","https://openalex.org/W4254547512","https://openalex.org/W4256046955","https://openalex.org/W6783938360"],"related_works":["https://openalex.org/W1935632502","https://openalex.org/W2955291419","https://openalex.org/W2080682057","https://openalex.org/W3136807736","https://openalex.org/W2050089535","https://openalex.org/W4281478226","https://openalex.org/W3125790749","https://openalex.org/W2055504378","https://openalex.org/W2013767790","https://openalex.org/W2236801283"],"abstract_inverted_index":{"Certain":[0],"but":[1],"important":[2],"classes":[3,105],"of":[4,33,62,106,136,165,185,202],"strategic-form":[5,63],"games,":[6,11,57,91],"including":[7],"zero-sum":[8,187],"and":[9,90,92,142,170,189],"identical-interest":[10,151,191],"have":[12,97,108],"thefictitious-play-property":[13],"(FPP),":[14],"i.e.,":[15],"beliefs":[16],"formed":[17],"in":[18,29,88,149,153,167,180],"fictitious":[19,137],"play":[20,32,61,138],"dynamics":[21,139],"always":[22],"converge":[23],"to":[24,65,146,209],"a":[25,42,84,117,133,155,194],"Nash":[26],"equilibrium":[27,48,95,121],"(NE)":[28],"the":[30,46,59,109,159,177,183,203],"repeated":[31,60],"these":[34],"games.":[35],"Such":[36,162],"convergence":[37,145],"results":[38,179],"are":[39,76,164],"seen":[40],"as":[41,55],"(behavioral)":[43],"justification":[44,119],"for":[45,79,120,140],"game-theoretical":[47,94],"analysis.":[49],"Markov":[50],"games":[51,64,163],"(MGs),":[52],"also":[53,98],"known":[54],"stochastic":[56],"generalize":[58],"dynamic":[66],"multi-state":[67],"settings":[68],"with":[69,176,193],"Markovian":[70],"state":[71,160],"transitions.":[72,161],"In":[73,128],"particular,":[74],"MGs":[75,107,141,152,188,192],"standard":[77],"models":[78],"multi-agent":[80],"reinforcement":[81],"learning":[82,89],"--":[83],"reviving":[85],"research":[86],"area":[87],"their":[93],"analyses":[96],"been":[99],"conducted":[100],"extensively.":[101],"However,":[102],"whether":[103,114],"certain":[104],"FPP":[110,184],"or":[111,123],"not":[112],"(i.e.,":[113],"there":[115],"is":[116],"behavioral":[118],"analysis":[122],"not)":[124],"remains":[125],"largely":[126],"elusive.":[127],"this":[129],"paper,":[130],"we":[131],"study":[132],"new":[134],"variant":[135],"show":[143],"its":[144],"an":[147],"NE":[148],"n-player":[150,190],"which":[154],"single":[156,195],"player":[157],"controls":[158],"interest":[166],"communications,":[168],"control,":[169],"economics":[171],"applications.":[172],"Our":[173],"result":[174],"together":[175],"recent":[178],"[42]":[181],"establishes":[182],"two-player":[186],"controller":[196],"(standing":[197],"at":[198],"two":[199],"different":[200],"ends":[201],"MG":[204],"spectrum":[205],"from":[206],"fully":[207,210],"competitive":[208],"cooperative).":[211]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}