{"id":"https://openalex.org/W3111119344","doi":"https://doi.org/10.1109/tac.2021.3121228","title":"Decentralized Learning for Optimality in Stochastic Dynamic Teams and Games With Local Control and Global State Information","display_name":"Decentralized Learning for Optimality in Stochastic Dynamic Teams and Games With Local Control and Global State Information","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3111119344","doi":"https://doi.org/10.1109/tac.2021.3121228","mag":"3111119344"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2021.3121228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2021.3121228","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/1903.05812","any_repository_has_fulltext":true},"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":true,"raw_author_name":"Bora Yongacoglu","raw_affiliation_strings":["Department of Mathematics and Statistics, Queen’s University, Kingston, ON, Canada","[Mathematics and Statistics, Queen's University, Kingston, Canada, K7L 3N6 (e-mail: 1bmy@queensu.ca)]"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen’s University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"[Mathematics and Statistics, Queen's University, Kingston, Canada, K7L 3N6 (e-mail: 1bmy@queensu.ca)]","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/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, Honolulu, HI, USA","[Electrical Engineering, University Of Hawaii at Manoa, Honolulu, HI, United States of America, 96822 (e-mail: gurdal@hawaii.edu)]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Hawaii, Honolulu, HI, USA","institution_ids":["https://openalex.org/I1331384533"]},{"raw_affiliation_string":"[Electrical Engineering, University Of Hawaii at Manoa, Honolulu, HI, United States of America, 96822 (e-mail: gurdal@hawaii.edu)]","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, ON, Canada","[Mathematics and Statistics, Queen's University, Kingston, Ontario, Canada, K7l3N6 (e-mail: yuksel@mast.queensu.ca)]"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Queen’s University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]},{"raw_affiliation_string":"[Mathematics and Statistics, Queen's University, Kingston, Ontario, Canada, K7l3N6 (e-mail: yuksel@mast.queensu.ca)]","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017866507"],"corresponding_institution_ids":["https://openalex.org/I204722609"],"apc_list":null,"apc_paid":null,"fwci":0.6998,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.750278,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"67","issue":"10","first_page":"5230","last_page":"5245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9987000226974487,"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":0.678174614906311},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.677294135093689},{"id":"https://openalex.org/keywords/stateless-protocol","display_name":"Stateless protocol","score":0.6039824485778809},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5048630833625793},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.47911524772644043},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4747893214225769},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.46921077370643616},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.42473796010017395},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.41106724739074707},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.3837777376174927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.271198570728302},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.2507995367050171},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.20047956705093384},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16923058032989502},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.12410971522331238},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11835372447967529}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.678174614906311},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.677294135093689},{"id":"https://openalex.org/C103613024","wikidata":"https://www.wikidata.org/wiki/Q230924","display_name":"Stateless protocol","level":3,"score":0.6039824485778809},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5048630833625793},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.47911524772644043},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4747893214225769},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.46921077370643616},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.42473796010017395},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.41106724739074707},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3837777376174927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.271198570728302},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.2507995367050171},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.20047956705093384},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16923058032989502},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.12410971522331238},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11835372447967529},{"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.2021.3121228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2021.3121228","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:1903.05812","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.05812","pdf_url":"https://arxiv.org/pdf/1903.05812","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":null,"raw_type":"text"},{"id":"mag:3111119344","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1903.05812.pdf","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.1903.05812","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.05812","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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.05812","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.05812","pdf_url":"https://arxiv.org/pdf/1903.05812","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":null,"raw_type":"text"},"sustainable_development_goals":[],"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":false,"pdf":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W1481080069","https://openalex.org/W1513468570","https://openalex.org/W1519783625","https://openalex.org/W1542941925","https://openalex.org/W1560074431","https://openalex.org/W1641379095","https://openalex.org/W1907356258","https://openalex.org/W1944059214","https://openalex.org/W1964886424","https://openalex.org/W1973039793","https://openalex.org/W1990631055","https://openalex.org/W1994908596","https://openalex.org/W1996013982","https://openalex.org/W2005228957","https://openalex.org/W2010654234","https://openalex.org/W2024612830","https://openalex.org/W2032200533","https://openalex.org/W2046679951","https://openalex.org/W2050124350","https://openalex.org/W2064219063","https://openalex.org/W2064882565","https://openalex.org/W2067018002","https://openalex.org/W2069356752","https://openalex.org/W2085366587","https://openalex.org/W2092025421","https://openalex.org/W2094364653","https://openalex.org/W2096145798","https://openalex.org/W2097498347","https://openalex.org/W2104602264","https://openalex.org/W2108449787","https://openalex.org/W2108892923","https://openalex.org/W2118994458","https://openalex.org/W2120327309","https://openalex.org/W2120846115","https://openalex.org/W2142839172","https://openalex.org/W2145067550","https://openalex.org/W2147492008","https://openalex.org/W2147750403","https://openalex.org/W2150339816","https://openalex.org/W2154136656","https://openalex.org/W2156194062","https://openalex.org/W2176451521","https://openalex.org/W2283268383","https://openalex.org/W2312609093","https://openalex.org/W2466211196","https://openalex.org/W2539833354","https://openalex.org/W2548493877","https://openalex.org/W2563286983","https://openalex.org/W2570514057","https://openalex.org/W2730807149","https://openalex.org/W2740377041","https://openalex.org/W2774971480","https://openalex.org/W2943950724","https://openalex.org/W2962990479","https://openalex.org/W2963747324","https://openalex.org/W2991046523","https://openalex.org/W3011120880","https://openalex.org/W3012335515","https://openalex.org/W3124542930","https://openalex.org/W4210491882","https://openalex.org/W4233696721","https://openalex.org/W4240204763","https://openalex.org/W4244096180","https://openalex.org/W4254299531","https://openalex.org/W6601295022","https://openalex.org/W6630520071","https://openalex.org/W6631168379","https://openalex.org/W6633472260","https://openalex.org/W6636868823","https://openalex.org/W6672070530","https://openalex.org/W6674705169","https://openalex.org/W6675811377","https://openalex.org/W6678168664","https://openalex.org/W6681246212","https://openalex.org/W6681342480","https://openalex.org/W6684470913","https://openalex.org/W6719729129","https://openalex.org/W6740914062","https://openalex.org/W6742529797","https://openalex.org/W6749032143","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W3209754935","https://openalex.org/W3013464227","https://openalex.org/W2962990479","https://openalex.org/W1790692380","https://openalex.org/W2292022307","https://openalex.org/W2972782056","https://openalex.org/W2575731723","https://openalex.org/W2120846115","https://openalex.org/W2104602264","https://openalex.org/W1542941925","https://openalex.org/W2895808298","https://openalex.org/W3207697547","https://openalex.org/W2773499228","https://openalex.org/W2901992463","https://openalex.org/W2730807149","https://openalex.org/W1608293404","https://openalex.org/W1504490632","https://openalex.org/W2618299181","https://openalex.org/W2288502617","https://openalex.org/W2782016344"],"abstract_inverted_index":{"Stochastic":[0],"dynamic":[1,138],"teams":[2,51,139],"and":[3,11,52,100,140],"games":[4],"are":[5,89,115],"rich":[6],"models":[7],"for":[8,15],"decentralized":[9],"systems":[10],"challenging":[12],"testing":[13],"grounds":[14],"multiagent":[16],"learning.":[17],"Previous":[18],"work":[19],"that":[20,62],"guaranteed":[21],"team":[22,47,131],"optimality":[23,132],"assumed":[24],"stateless":[25],"dynamics,":[26],"or":[27,32],"an":[28,40],"explicit":[29],"coordination":[30],"mechanism,":[31],"joint-control":[33],"sharing.":[34],"In":[35],"this":[36,87],"article,":[37],"we":[38],"present":[39],"algorithm":[41,57,88],"with":[42],"guarantees":[43,127],"of":[44,66,108,121,128],"convergence":[45,129],"to":[46,72,106,118,124,130],"optimal":[48],"policies":[49],"in":[50,136],"common":[53,141],"interest":[54,142],"games.":[55,143],"The":[56,111],"is":[58],"a":[59,64],"two-timescale":[60],"method":[61],"uses":[63],"variant":[65],"Q-learning":[67],"on":[68,81],"the":[69,78,82,116,119],"finer":[70],"timescale":[71],"perform":[73],"policy":[74,79],"evaluation":[75],"while":[76],"exploring":[77],"space":[80],"coarser":[83],"timescale.":[84],"Agents":[85],"following":[86],"\u201cindependent":[90],"learners\u201d:":[91],"they":[92],"use":[93],"only":[94],"local":[95,97],"controls,":[96],"cost":[98],"realizations,":[99],"global":[101],"state":[102],"information,":[103],"without":[104],"access":[105],"controls":[107],"other":[109],"agents.":[110],"results":[112],"presented":[113],"here":[114],"first,":[117],"best":[120],"our":[122],"knowledge,":[123],"give":[125],"formal":[126],"using":[133],"independent":[134],"learners":[135],"stochastic":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}