{"id":"https://openalex.org/W3092557414","doi":"https://doi.org/10.1137/21m1426675","title":"Fictitious Play in Zero-Sum Stochastic Games","display_name":"Fictitious Play in Zero-Sum Stochastic Games","publication_year":2022,"publication_date":"2022-07-13","ids":{"openalex":"https://openalex.org/W3092557414","doi":"https://doi.org/10.1137/21m1426675","mag":"3092557414"},"language":"en","primary_location":{"id":"doi:10.1137/21m1426675","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m1426675","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"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 Control and 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/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":["Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Turkey, 06800"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Turkey, 06800","institution_ids":["https://openalex.org/I168864056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045020084","display_name":"Francesca Parise","orcid":"https://orcid.org/0000-0003-0650-4392"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francesca Parise","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Cornell University, Ithaca, NY 14853 USA"],"raw_orcid":"https://orcid.org/0000-0003-0650-4392","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Cornell University, Ithaca, NY 14853 USA","institution_ids":["https://openalex.org/I205783295"]}]},{"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":["Department of Electrical Engineering and Computer Science, Massachusetts Institute of Tech-nology, Cambridge, MA 02139 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Tech-nology, Cambridge, MA 02139 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":3.7458,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.93516856,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"60","issue":"4","first_page":"2095","last_page":"2114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9958000183105469,"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":0.9958000183105469,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9926000237464905,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9912999868392944,"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/mathematics","display_name":"Mathematics","score":0.8133732080459595},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6833887100219727},{"id":"https://openalex.org/keywords/zero-sum-game","display_name":"Zero-sum game","score":0.5051942467689514},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.4539295732975006},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.41399139165878296},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.38616490364074707},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35717087984085083},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.2260919213294983}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.8133732080459595},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6833887100219727},{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.5051942467689514},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.4539295732975006},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.41399139165878296},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.38616490364074707},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35717087984085083},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.2260919213294983},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1137/21m1426675","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m1426675","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"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 Control and Optimization","raw_type":"journal-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/167980","is_oa":false,"landing_page_url":"https://dspace.mit.edu/handle/1721.1/167980","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Society for Industrial & Applied Mathematics (SIAM)","raw_type":"Article"},{"id":"pmh:oai:repository.bilkent.edu.tr:11693/111622","is_oa":false,"landing_page_url":"http://hdl.handle.net/11693/111622","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":"SIAM Journal on Control and Optimization","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G6843335018","display_name":null,"funder_award_id":"W911NF-18-1-0407","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"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":47,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W594357522","https://openalex.org/W1496590343","https://openalex.org/W1542941925","https://openalex.org/W1570425181","https://openalex.org/W1575538511","https://openalex.org/W1960239420","https://openalex.org/W1964757264","https://openalex.org/W1964886424","https://openalex.org/W1967250398","https://openalex.org/W1993801612","https://openalex.org/W1997949764","https://openalex.org/W2029191936","https://openalex.org/W2060284899","https://openalex.org/W2070214254","https://openalex.org/W2075700780","https://openalex.org/W2083737395","https://openalex.org/W2097498347","https://openalex.org/W2118247617","https://openalex.org/W2121863487","https://openalex.org/W2124666512","https://openalex.org/W2126776273","https://openalex.org/W2147750403","https://openalex.org/W2149152713","https://openalex.org/W2149254401","https://openalex.org/W2153304927","https://openalex.org/W2156008353","https://openalex.org/W2159206500","https://openalex.org/W2167957526","https://openalex.org/W2176451521","https://openalex.org/W2524852791","https://openalex.org/W2575731723","https://openalex.org/W2787689390","https://openalex.org/W2949201811","https://openalex.org/W2962990479","https://openalex.org/W2963111827","https://openalex.org/W2988569019","https://openalex.org/W2991046523","https://openalex.org/W3006976375","https://openalex.org/W3035454135","https://openalex.org/W3043098219","https://openalex.org/W3104337597","https://openalex.org/W3123619424","https://openalex.org/W3125104281","https://openalex.org/W4206530644","https://openalex.org/W4233696721","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2739681863","https://openalex.org/W3170723600","https://openalex.org/W4287122294","https://openalex.org/W2039187327","https://openalex.org/W1877069894","https://openalex.org/W4287644830","https://openalex.org/W3092557414","https://openalex.org/W3125477855","https://openalex.org/W1994737592","https://openalex.org/W2237993507"],"abstract_inverted_index":{"We":[0,92],"present":[1],"a":[2,46,82,118],"novel":[3],"variant":[4],"of":[5,62,68,75,87,104,123],"fictitious":[6,11],"play":[7,12],"dynamics":[8,29,71],"combining":[9],"classical":[10],"with":[13],"$Q$-learning":[14],"for":[15],"stochastic":[16,26,126],"games":[17],"and":[18,38,44,99,108],"analyze":[19],"its":[20],"convergence":[21],"properties":[22],"in":[23,95],"two-player":[24],"zero-sum":[25,125],"games.":[27],"Our":[28],"involves":[30],"players":[31],"forming":[32],"beliefs":[33,59,77,89,113],"on":[34,78,90,114],"the":[35,52,69,76,88,97,112,124],"opponent":[36,63],"strategy":[37],"their":[39,58],"own":[40],"continuation":[41,54],"payoff":[42,106],"($Q$-function),":[43],"playing":[45],"greedy":[47],"best":[48],"response":[49],"by":[50],"using":[51],"estimated":[53],"payoffs.":[55],"Players":[56],"update":[57,74,86],"from":[60],"observations":[61],"actions.":[64],"A":[65],"key":[66],"property":[67],"learning":[70],"is":[72],"that":[73,94],"$Q$-functions":[79],"occurs":[80],"at":[81],"slower":[83],"timescale":[84],"than":[85],"strategies.":[91],"show":[93],"both":[96],"model-based":[98],"model-free":[100],"cases":[101],"(without":[102],"knowledge":[103],"player":[105],"functions":[107],"state":[109],"transition":[110],"probabilities),":[111],"strategies":[115],"converge":[116],"to":[117],"stationary":[119],"mixed":[120],"Nash":[121],"equilibrium":[122],"game.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7}],"updated_date":"2026-07-04T07:58:01.006859","created_date":"2025-10-10T00:00:00"}