{"id":"https://openalex.org/W4391020771","doi":"https://doi.org/10.1109/cdc49753.2023.10383194","title":"Asynchronous Decentralized Q-Learning in Stochastic Games","display_name":"Asynchronous Decentralized Q-Learning in Stochastic Games","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391020771","doi":"https://doi.org/10.1109/cdc49753.2023.10383194"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd 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/A5017866507","display_name":"Bora Yongacoglu","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bora Yongacoglu","raw_affiliation_strings":["University of Toronto,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072860374","display_name":"G\u00fcrdal Arslan","orcid":"https://orcid.org/0000-0002-8295-1509"},"institutions":[{"id":"https://openalex.org/I117965899","display_name":"University of Hawai\u02bbi at M\u0101noa","ror":"https://ror.org/01wspgy28","country_code":"US","type":"education","lineage":["https://openalex.org/I117965899"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G\u00fcrdal Arslan","raw_affiliation_strings":["University of Hawaii at Manoa,Department of Electrical Engineering","Department of Electrical Engineering, University of Hawaii at Manoa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hawaii at Manoa,Department of Electrical Engineering","institution_ids":["https://openalex.org/I117965899"]},{"raw_affiliation_string":"Department of Electrical Engineering, University of Hawaii at Manoa","institution_ids":["https://openalex.org/I117965899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005401257","display_name":"Serdar Y\u00fcksel","orcid":"https://orcid.org/0000-0001-6099-5001"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Serdar Y\u00fcksel","raw_affiliation_strings":["Queen's University,Department of Mathematics and Statistics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen's University,Department of Mathematics and Statistics","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59463124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5008","last_page":"5013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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/T11031","display_name":"Game Theory and Applications","score":0.9965999722480774,"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/T11182","display_name":"Auction Theory and Applications","score":0.9965000152587891,"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/asynchronous-communication","display_name":"Asynchronous communication","score":0.812613308429718},{"id":"https://openalex.org/keywords/synchronizing","display_name":"Synchronizing","score":0.7369812726974487},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7315517663955688},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6991240382194519},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.6939270496368408},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6597047448158264},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6545620560646057},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4515022337436676},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4167078733444214},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4113895893096924},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35152584314346313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3367910087108612},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.131391704082489},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10702753067016602},{"id":"https://openalex.org/keywords/transmission","display_name":"Transmission (telecommunications)","score":0.07876774668693542}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.812613308429718},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.7369812726974487},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7315517663955688},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6991240382194519},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.6939270496368408},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6597047448158264},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6545620560646057},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4515022337436676},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4167078733444214},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4113895893096924},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35152584314346313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3367910087108612},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.131391704082489},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10702753067016602},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.07876774668693542},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd 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":30,"referenced_works":["https://openalex.org/W1519783625","https://openalex.org/W1626977535","https://openalex.org/W1907356258","https://openalex.org/W2096145798","https://openalex.org/W2120846115","https://openalex.org/W2132580642","https://openalex.org/W2176451521","https://openalex.org/W2740377041","https://openalex.org/W2962990479","https://openalex.org/W2981038142","https://openalex.org/W3122272342","https://openalex.org/W3148958427","https://openalex.org/W3169011731","https://openalex.org/W3172288035","https://openalex.org/W3209754935","https://openalex.org/W4281729939","https://openalex.org/W4287125173","https://openalex.org/W4287391791","https://openalex.org/W4319453596","https://openalex.org/W4385681682","https://openalex.org/W4386120402","https://openalex.org/W4389775604","https://openalex.org/W6631168379","https://openalex.org/W6636868823","https://openalex.org/W6675811377","https://openalex.org/W6678168664","https://openalex.org/W6679903357","https://openalex.org/W6785161469","https://openalex.org/W6791976426","https://openalex.org/W6796569726"],"related_works":["https://openalex.org/W2141223633","https://openalex.org/W96967322","https://openalex.org/W2147711412","https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W4376605461"],"abstract_inverted_index":{"Non-stationarity":[0],"is":[1],"a":[2,84],"fundamental":[3],"challenge":[4,46],"in":[5,42,56,144,149],"multi-agent":[6,19],"reinforcement":[7],"learning":[8,37],"(MARL),":[9],"where":[10],"agents":[11,22,55,64],"update":[12,119],"their":[13,69,124,127],"behaviour":[14],"as":[15],"they":[16],"learn.":[17],"In":[18,71,107],"settings,":[20],"individual":[21],"may":[23,122],"have":[24],"an":[25,76,150],"incomplete":[26],"view":[27],"of":[28,31,47,54,79,117,137,161],"the":[29,36,45,51,80,97,115,135,138,158],"actions":[30],"others,":[32],"which":[33,63,96,145],"can":[34],"complicate":[35],"process.":[38],"Many":[39],"theoretical":[40],"advances":[41],"MARL":[43,86],"avoid":[44],"non-stationarity":[48,155],"by":[49],"coordinating":[50],"policy":[52,118],"updates":[53],"various":[57],"ways,":[58],"including":[59],"synchronizing":[60],"times":[61],"at":[62,126],"are":[65,147],"allowed":[66],"to":[67,102,142],"revise":[68],"policies.":[70],"this":[72,108],"paper,":[73],"we":[74],"study":[75],"asynchronous":[77,98],"variant":[78],"decentralized":[81,139],"Q-learning":[82,140],"algorithm,":[83],"recent":[85],"algorithm":[87,99,141],"for":[88],"stochastic":[89],"games.":[90],"We":[91],"provide":[92],"sufficient":[93],"conditions":[94],"under":[95],"drives":[100],"play":[101],"equilibrium":[103],"with":[104],"high":[105],"probability.":[106],"generalization,":[109],"players":[110],"need":[111],"not":[112],"agree":[113],"on":[114],"schedule":[116],"times,":[120],"and":[121,153],"change":[123],"policies":[125],"own":[128],"separately":[129],"selected":[130,148],"times.":[131],"This":[132],"work":[133],"extends":[134],"applicability":[136],"settings":[143],"parameters":[146],"independent":[151],"manner,":[152],"tames":[154],"without":[156],"imposing":[157],"coordination":[159],"assumptions":[160],"prior":[162],"work.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}