{"id":"https://openalex.org/W3013464227","doi":"https://doi.org/10.1109/ieeeconf44664.2019.9049021","title":"Decentralized Q-Learning with Constant Aspirations in Stochastic Games","display_name":"Decentralized Q-Learning with Constant Aspirations in Stochastic Games","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3013464227","doi":"https://doi.org/10.1109/ieeeconf44664.2019.9049021","mag":"3013464227"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf44664.2019.9049021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf44664.2019.9049021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 53rd Asilomar Conference on Signals, Systems, and Computers","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/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":"Bora Yongacoglu","raw_affiliation_strings":["Department of Mathematics and Statistics, Queen\u2019s University, Kingston, Canada","Department of Mathematics and Statistics, Queen's University, Kingston, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen\u2019s University, Kingston, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen's University, Kingston, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"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/I1331384533","display_name":"University of Hawaii System","ror":"https://ror.org/03tzaeb71","country_code":"US","type":"education","lineage":["https://openalex.org/I1331384533"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gurdal Arslan","raw_affiliation_strings":["University of Hawaii"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hawaii","institution_ids":["https://openalex.org/I1331384533"]}]},{"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\u2019s University, Kingston, Canada","Department of Mathematics and Statistics, Queen's University, Kingston, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen\u2019s University, Kingston, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen's University, Kingston, Canada","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":0.1446,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62071289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"4","issue":null,"first_page":"1744","last_page":"1749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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":0.9986000061035156,"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/T11182","display_name":"Auction Theory and Applications","score":0.998199999332428,"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/T11031","display_name":"Game Theory and Applications","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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7687140703201294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6814003586769104},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5764390230178833},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.5605759024620056},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4988718032836914},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49023205041885376},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.485922247171402},{"id":"https://openalex.org/keywords/information-structure","display_name":"Information structure","score":0.44537192583084106},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.4366210997104645},{"id":"https://openalex.org/keywords/complete-information","display_name":"Complete information","score":0.417804479598999},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41473403573036194},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.4104504883289337},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.2757043242454529},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2560473084449768},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.22154486179351807},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21368035674095154},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09649461507797241},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.09512794017791748}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7687140703201294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6814003586769104},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5764390230178833},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5605759024620056},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4988718032836914},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49023205041885376},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.485922247171402},{"id":"https://openalex.org/C2779954242","wikidata":"https://www.wikidata.org/wiki/Q6031227","display_name":"Information structure","level":2,"score":0.44537192583084106},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.4366210997104645},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.417804479598999},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41473403573036194},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.4104504883289337},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.2757043242454529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2560473084449768},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.22154486179351807},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21368035674095154},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09649461507797241},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.09512794017791748},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf44664.2019.9049021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf44664.2019.9049021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 53rd Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1513468570","https://openalex.org/W1519783625","https://openalex.org/W1641379095","https://openalex.org/W1907356258","https://openalex.org/W1990631055","https://openalex.org/W2010654234","https://openalex.org/W2064219063","https://openalex.org/W2069356752","https://openalex.org/W2092025421","https://openalex.org/W2104602264","https://openalex.org/W2120846115","https://openalex.org/W2142839172","https://openalex.org/W2145067550","https://openalex.org/W2147750403","https://openalex.org/W2150339816","https://openalex.org/W2154136656","https://openalex.org/W2176451521","https://openalex.org/W2548493877","https://openalex.org/W2570514057","https://openalex.org/W2788115019","https://openalex.org/W2962990479","https://openalex.org/W2963747324","https://openalex.org/W2972782056","https://openalex.org/W3011120880","https://openalex.org/W3012335515","https://openalex.org/W3102463202","https://openalex.org/W3124542930","https://openalex.org/W4233696721","https://openalex.org/W4244096180","https://openalex.org/W6630520071","https://openalex.org/W6631168379","https://openalex.org/W6639734652","https://openalex.org/W6675811377","https://openalex.org/W6678168664","https://openalex.org/W6681246212","https://openalex.org/W6681342480","https://openalex.org/W6749032143","https://openalex.org/W6767800324","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2100092929","https://openalex.org/W2165271310","https://openalex.org/W3121310648","https://openalex.org/W4232850892","https://openalex.org/W3122908176","https://openalex.org/W2005440647","https://openalex.org/W2031205992","https://openalex.org/W1275367343","https://openalex.org/W3124981661","https://openalex.org/W1718458636"],"abstract_inverted_index":{"In":[0,18,58],"decentralized":[1,62,101,123],"stochastic":[2,69,105,116],"control,":[3],"coordination":[4],"among":[5],"control":[6,56,63],"agents":[7],"is":[8,65,79],"typically":[9],"required":[10],"in":[11,71,104,118,122,135,153],"order":[12],"to":[13,42,53],"achieve":[14],"acceptable":[15],"system":[16],"performance.":[17],"practice,":[19],"pertinent":[20],"information":[21,93],"about":[22],"the":[23,25,28,74,86,96,127,136,154,160,166],"system-in":[24],"form":[26,155],"of":[27,37,100,156,162],"cost":[29,158],"function,":[30],"state":[31,167],"transition":[32],"probabilities,":[33],"and":[34,47,81,130,148,165],"past":[35],"actions":[36,87],"other":[38,90],"agents-is":[39],"often":[40],"unavailable":[41],"some":[43],"or":[44],"all":[45],"agents,":[46],"this":[48,59],"serves":[49],"as":[50,67],"an":[51],"obstacle":[52],"finding":[54],"optimal":[55],"policies.":[57],"paper,":[60],"a":[61,68,110],"problem":[64],"modelled":[66],"game":[70,76],"which":[72,119],"(i)":[73],"specific":[75],"being":[77],"played":[78],"unknown,":[80],"(ii)":[82],"players":[83,120],"never":[84],"observe":[85],"used":[88],"by":[89],"agents.":[91],"This":[92,107],"structure":[94],"exacerbates":[95],"already":[97],"difficult":[98],"challenge":[99],"policy":[102,124],"evaluation":[103,125],"games.":[106],"paper":[108],"presents":[109],"two-timescale":[111],"reinforcement":[112],"learning":[113],"algorithm":[114,140],"for":[115],"games,":[117],"engage":[121],"during":[126],"finer":[128],"timescale":[129],"update":[131],"their":[132],"baseline":[133],"policies":[134],"coarser":[137],"timescale.":[138],"The":[139],"presented":[141],"here":[142],"comes":[143],"with":[144],"provable":[145],"convergence":[146],"guarantees":[147],"uses":[149],"only":[150],"local":[151,157,163],"information,":[152],"readings,":[159],"history":[161],"actions,":[164],"information.":[168]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}