{"id":"https://openalex.org/W2345652363","doi":"https://doi.org/10.1109/tac.2016.2598476","title":"Decentralized Q-Learning for Stochastic Teams and Games","display_name":"Decentralized Q-Learning for Stochastic Teams and Games","publication_year":2016,"publication_date":"2016-08-05","ids":{"openalex":"https://openalex.org/W2345652363","doi":"https://doi.org/10.1109/tac.2016.2598476","mag":"2345652363"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2016.2598476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2016.2598476","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1506.07924","any_repository_has_fulltext":true},"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"]},{"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":["Department of Electrical Engineering, University of Hawaii at Manoa, Honolulu, HI, USA","University of hawaii"],"raw_orcid":"https://orcid.org/0000-0002-8295-1509","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Hawaii at Manoa, Honolulu, HI, USA","institution_ids":["https://openalex.org/I117965899"]},{"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's University, Kingston, Ontario, Canada","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"]},{"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":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.02081656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"62","issue":"4","first_page":"1545","last_page":"1558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9980999827384949,"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/markov-decision-process","display_name":"Markov decision process","score":0.6881559491157532},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6153470277786255},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5964437127113342},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5118800401687622},{"id":"https://openalex.org/keywords/decision-maker","display_name":"Decision maker","score":0.5037888884544373},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5009152889251709},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3986983895301819},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.37421703338623047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3262106776237488},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.2932862639427185},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2504415214061737},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22119849920272827},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.14256462454795837},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10186335444450378}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6881559491157532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6153470277786255},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5964437127113342},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5118800401687622},{"id":"https://openalex.org/C2986080485","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision maker","level":2,"score":0.5037888884544373},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5009152889251709},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3986983895301819},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.37421703338623047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3262106776237488},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2932862639427185},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2504415214061737},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22119849920272827},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.14256462454795837},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10186335444450378},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tac.2016.2598476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2016.2598476","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1506.07924","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1506.07924","pdf_url":"https://arxiv.org/pdf/1506.07924","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2345652363","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1506.07924v2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1506.07924","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1506.07924","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1506.07924","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1506.07924","pdf_url":"https://arxiv.org/pdf/1506.07924","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2345652363.pdf","grobid_xml":"https://content.openalex.org/works/W2345652363.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W585548487","https://openalex.org/W1480317510","https://openalex.org/W1534486999","https://openalex.org/W1579118835","https://openalex.org/W1605188341","https://openalex.org/W1641379095","https://openalex.org/W1812360833","https://openalex.org/W1907356258","https://openalex.org/W1944059214","https://openalex.org/W1964886424","https://openalex.org/W1967250398","https://openalex.org/W1977538586","https://openalex.org/W1983009109","https://openalex.org/W2039899015","https://openalex.org/W2067018002","https://openalex.org/W2069038223","https://openalex.org/W2069356752","https://openalex.org/W2082261506","https://openalex.org/W2083737395","https://openalex.org/W2092025421","https://openalex.org/W2102562355","https://openalex.org/W2103151730","https://openalex.org/W2104602264","https://openalex.org/W2107306424","https://openalex.org/W2117671832","https://openalex.org/W2118686230","https://openalex.org/W2119567691","https://openalex.org/W2120327309","https://openalex.org/W2142839172","https://openalex.org/W2147077179","https://openalex.org/W2147750403","https://openalex.org/W2149254401","https://openalex.org/W2154136656","https://openalex.org/W2156194062","https://openalex.org/W2157298719","https://openalex.org/W2159206500","https://openalex.org/W2167957526","https://openalex.org/W2168509539","https://openalex.org/W2171029115","https://openalex.org/W2176451521","https://openalex.org/W2575731723","https://openalex.org/W2589394640","https://openalex.org/W2888914392","https://openalex.org/W3022321359","https://openalex.org/W3148958427","https://openalex.org/W4210491882","https://openalex.org/W4233696721","https://openalex.org/W4237171445","https://openalex.org/W4244096180","https://openalex.org/W6631763790","https://openalex.org/W6638536898","https://openalex.org/W6639734652","https://openalex.org/W6644606114","https://openalex.org/W6673443209","https://openalex.org/W6675811377","https://openalex.org/W6681246212"],"related_works":["https://openalex.org/W2962990479","https://openalex.org/W1790692380","https://openalex.org/W2292022307","https://openalex.org/W3209754935","https://openalex.org/W2146327567","https://openalex.org/W3013464227","https://openalex.org/W1587826207","https://openalex.org/W2036582885","https://openalex.org/W2188793289","https://openalex.org/W2178009137","https://openalex.org/W3175375827","https://openalex.org/W328245778","https://openalex.org/W2022111686","https://openalex.org/W3173547034","https://openalex.org/W2288502617","https://openalex.org/W103885025","https://openalex.org/W2730807149","https://openalex.org/W2462044286","https://openalex.org/W256774967","https://openalex.org/W2951859429"],"abstract_inverted_index":{"There":[0],"are":[1,63,122],"only":[2,131],"a":[3],"few":[4],"learning":[5,70],"algorithms":[6,98,121,165],"applicable":[7],"to":[8,19,46,132,153,167],"stochastic":[9,21,67,100,176],"dynamic":[10,68],"teams":[11],"and":[12,86,102,136],"games":[13,31],"which":[14,41,111],"generalize":[15],"Markov":[16],"decision":[17,27,43,60,78,127,148,159],"processes":[18],"decentralized":[20,96,123],"control":[22],"problems":[23,114],"involving":[24],"possibly":[25],"self-interested":[26],"makers.":[28,160],"Learning":[29],"in":[30,40,54,124,145,172],"is":[32,71,150],"generally":[33],"difficult":[34],"because":[35],"of":[36,57,83,156,175],"the":[37,55,58,77,81,84,88,107,142,154,157],"non-stationary":[38],"environment":[39],"each":[42,126,147],"maker":[44,128,149],"aims":[45],"learn":[47],"its":[48,133],"optimal":[49],"decisions":[50,135],"with":[51],"minimal":[52],"information":[53],"presence":[56,155],"other":[59,158],"makers":[61,79],"who":[62],"also":[64],"learning.":[65],"In":[66,91],"games,":[69,101],"more":[72],"challenging":[73],"because,":[74],"while":[75],"learning,":[76],"alter":[80],"state":[82,143],"system":[85],"hence":[87],"future":[89],"cost.":[90],"this":[92],"paper,":[93],"we":[94],"present":[95],"Q-learning":[97],"for":[99,106],"study":[103],"their":[104],"convergence":[105],"weakly":[108],"acyclic":[109],"case":[110],"includes":[112],"team":[113],"as":[115,139,141],"an":[116],"important":[117],"special":[118],"case.":[119],"The":[120],"that":[125,163],"has":[129],"access":[130],"own":[134],"cost":[137],"realizations":[138],"well":[140],"transitions;":[144],"particular,":[146],"completely":[151],"oblivious":[152],"We":[161],"show":[162],"these":[164],"converge":[166],"equilibrium":[168],"policies":[169],"almost":[170],"surely":[171],"large":[173],"classes":[174],"games.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}