{"id":"https://openalex.org/W2292022307","doi":"https://doi.org/10.1109/cdc.2015.7403281","title":"Decentralized Q-learning for weakly acyclic stochastic dynamic games","display_name":"Decentralized Q-learning for weakly acyclic stochastic dynamic games","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2292022307","doi":"https://doi.org/10.1109/cdc.2015.7403281","mag":"2292022307"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2015.7403281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2015.7403281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 54th 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/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":"Gurdal Arslan","raw_affiliation_strings":["Department of Electrical Engineering, University of Hawaii at Manoa, Honolulu, HI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Hawaii at Manoa, Honolulu, HI, USA","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 Yuksel","raw_affiliation_strings":["Department of Mathematics and Statistics, Queen's University, Kingston, Ontario, CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen's University, Kingston, Ontario, CANADA","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8234,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.80106893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6743","last_page":"6748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9979000091552734,"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/T11182","display_name":"Auction Theory and Applications","score":0.9979000091552734,"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":0.9934999942779541,"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":0.9929999709129333,"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/computer-science","display_name":"Computer science","score":0.6485121846199036},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6446996927261353},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.45543134212493896},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.45255908370018005},{"id":"https://openalex.org/keywords/dynamic-decision-making","display_name":"Dynamic decision-making","score":0.4335610270500183},{"id":"https://openalex.org/keywords/decision-maker","display_name":"Decision maker","score":0.4172181487083435},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37293463945388794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3666847348213196},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.33973586559295654},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23655325174331665},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.18378624320030212},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1651717722415924},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.1102033257484436},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.1073082983493805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6485121846199036},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6446996927261353},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45543134212493896},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.45255908370018005},{"id":"https://openalex.org/C174988536","wikidata":"https://www.wikidata.org/wiki/Q5318965","display_name":"Dynamic decision-making","level":2,"score":0.4335610270500183},{"id":"https://openalex.org/C2986080485","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision maker","level":2,"score":0.4172181487083435},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37293463945388794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3666847348213196},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.33973586559295654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23655325174331665},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.18378624320030212},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1651717722415924},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1102033257484436},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.1073082983493805},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2015.7403281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2015.7403281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 54th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1790692380","https://openalex.org/W1944059214","https://openalex.org/W1964886424","https://openalex.org/W1983009109","https://openalex.org/W2082261506","https://openalex.org/W2083737395","https://openalex.org/W2104602264","https://openalex.org/W2147750403","https://openalex.org/W2149254401","https://openalex.org/W2159206500","https://openalex.org/W2176451521","https://openalex.org/W2575731723","https://openalex.org/W3148958427","https://openalex.org/W4210491882","https://openalex.org/W4233696721","https://openalex.org/W4249485025","https://openalex.org/W6637933060","https://openalex.org/W6675811377"],"related_works":["https://openalex.org/W1517908938","https://openalex.org/W2281834912","https://openalex.org/W76510542","https://openalex.org/W1489941249","https://openalex.org/W2128528306","https://openalex.org/W3123492739","https://openalex.org/W4320486059","https://openalex.org/W2065569314","https://openalex.org/W2330582382","https://openalex.org/W2589599852"],"abstract_inverted_index":{"There":[0],"are":[1,46],"only":[2],"a":[3],"few":[4],"learning":[5,55],"algorithms":[6,83,105],"applicable":[7],"to":[8,29],"stochastic":[9,85,118],"dynamic":[10,53,86,119],"games.":[11,120],"Learning":[12],"in":[13,23,37,114],"games":[14],"is":[15,56],"generally":[16],"difficult":[17],"because":[18],"of":[19,40,52,68,117],"the":[20,38,41,50,62,66,69,73,93,100],"non-stationary":[21],"environment":[22],"which":[24],"each":[25],"decision":[26,43,63,101],"maker":[27],"aims":[28],"learn":[30],"its":[31],"optimal":[32],"decisions":[33],"with":[34],"minimal":[35],"information":[36],"presence":[39],"other":[42],"makers":[44,64,102],"who":[45],"also":[47],"learning.":[48],"In":[49,76],"case":[51],"games,":[54,87],"more":[57],"challenging":[58],"because,":[59],"while":[60],"learning,":[61],"alter":[65],"state":[67],"system":[70],"and":[71,88],"hence":[72],"future":[74],"cost.":[75],"this":[77],"paper,":[78],"we":[79],"present":[80],"decentralized":[81],"Q-learning":[82],"for":[84,92],"study":[89],"their":[90],"convergence":[91],"weakly":[94],"acyclic":[95],"case.":[96],"We":[97],"show":[98],"that":[99],"employing":[103],"these":[104],"would":[106],"eventually":[107],"be":[108],"using":[109],"equilibrium":[110],"policies":[111],"almost":[112],"surely":[113],"large":[115],"classes":[116]},"counts_by_year":[{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}