{"id":"https://openalex.org/W2053241734","doi":"https://doi.org/10.1145/2644819","title":"Multiagent Reinforcement Social Learning toward Coordination in Cooperative Multiagent Systems","display_name":"Multiagent Reinforcement Social Learning toward Coordination in Cooperative Multiagent Systems","publication_year":2014,"publication_date":"2014-12-19","ids":{"openalex":"https://openalex.org/W2053241734","doi":"https://doi.org/10.1145/2644819","mag":"2053241734"},"language":"en","primary_location":{"id":"doi:10.1145/2644819","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2644819","pdf_url":null,"source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-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/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["Massachusetts Institute of Technology Shenzhen University, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Shenzhen University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022683388","display_name":"Ho-fung Leung","orcid":"https://orcid.org/0000-0003-4914-2934"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ho-Fung Leung","raw_affiliation_strings":["The Chinese University of Hong Kong, Shatin, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100633973","display_name":"Zhong Ming","orcid":"https://orcid.org/0000-0001-9310-3460"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Ming","raw_affiliation_strings":["Shenzhen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.0267,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.97584862,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"9","issue":"4","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social 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":0.7453346252441406},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6647859811782837},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5685250759124756},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5563164949417114},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.528105616569519},{"id":"https://openalex.org/keywords/coordination-game","display_name":"Coordination game","score":0.4878425598144531},{"id":"https://openalex.org/keywords/cooperative-learning","display_name":"Cooperative learning","score":0.46555429697036743},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45734381675720215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44315841794013977},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.4371088743209839},{"id":"https://openalex.org/keywords/social-learning","display_name":"Social learning","score":0.4160052239894867},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.23593172430992126},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2163386344909668},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.14370715618133545},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0938434898853302}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7453346252441406},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6647859811782837},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5685250759124756},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5563164949417114},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.528105616569519},{"id":"https://openalex.org/C107257861","wikidata":"https://www.wikidata.org/wiki/Q656316","display_name":"Coordination game","level":2,"score":0.4878425598144531},{"id":"https://openalex.org/C51672120","wikidata":"https://www.wikidata.org/wiki/Q303446","display_name":"Cooperative learning","level":3,"score":0.46555429697036743},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45734381675720215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44315841794013977},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.4371088743209839},{"id":"https://openalex.org/C79416737","wikidata":"https://www.wikidata.org/wiki/Q2305519","display_name":"Social learning","level":2,"score":0.4160052239894867},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.23593172430992126},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2163386344909668},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.14370715618133545},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0938434898853302},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C88610354","wikidata":"https://www.wikidata.org/wiki/Q1813494","display_name":"Teaching method","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2644819","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2644819","pdf_url":null,"source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W92376239","https://openalex.org/W112918015","https://openalex.org/W137071854","https://openalex.org/W178386168","https://openalex.org/W1557517019","https://openalex.org/W1560074431","https://openalex.org/W1974738471","https://openalex.org/W2012347046","https://openalex.org/W2012615693","https://openalex.org/W2030251535","https://openalex.org/W2038900621","https://openalex.org/W2085366587","https://openalex.org/W2091257550","https://openalex.org/W2096145798","https://openalex.org/W2097866252","https://openalex.org/W2104602264","https://openalex.org/W2107544712","https://openalex.org/W2107726111","https://openalex.org/W2108449787","https://openalex.org/W2108892923","https://openalex.org/W2131850879","https://openalex.org/W2145067550","https://openalex.org/W2164470020","https://openalex.org/W2169826194","https://openalex.org/W2955831086"],"related_works":["https://openalex.org/W4210735314","https://openalex.org/W3125290436","https://openalex.org/W2766907483","https://openalex.org/W2097226409","https://openalex.org/W3125633875","https://openalex.org/W4280496625","https://openalex.org/W2184851736","https://openalex.org/W3151419234","https://openalex.org/W1535719876","https://openalex.org/W3038567666"],"abstract_inverted_index":{"Most":[0],"previous":[1],"works":[2],"on":[3,20,141,186],"coordination":[4,64,127],"in":[5,29,36,66,93,129],"cooperative":[6,33,67,176],"multiagent":[7,63],"systems":[8],"study":[9],"the":[10,30,40,62,91,105,108,142,179,182,187,196],"problem":[11],"of":[12,32,79,107,138,144,161,164,171,181],"how":[13],"two":[14,135],"(or":[15],"more)":[16],"players":[17],"can":[18,44,122,148],"coordinate":[19],"Pareto-optimal":[21],"Nash":[22],"equilibrium(s)":[23],"through":[24,101],"fixed":[25,203],"and":[26,47,55,153,174,178],"repeated":[27,102,200],"interactions":[28,41,103,201],"context":[31],"games.":[34],"However,":[35],"practical":[37],"complex":[38],"environments,":[39],"between":[42],"agents":[43,80,109,121],"be":[45],"sparse,":[46],"each":[48,82,94,146],"agent's":[49],"interacting":[50],"partners":[51],"may":[52],"change":[53],"frequently":[54],"randomly.":[56],"To":[57],"this":[58],"end,":[59],"we":[60],"investigate":[61],"problems":[65],"environments":[68],"under":[69,168],"a":[70,76,117,124,131,169],"social":[71,111],"learning":[72,159,188,197],"framework.":[73],"We":[74,133],"consider":[75],"large":[77],"population":[78,92],"where":[81],"agent":[83,87,97,147],"interacts":[84],"with":[85,104],"another":[86],"randomly":[88],"chosen":[89],"from":[90,195],"round.":[95],"Each":[96],"learns":[98],"its":[99],"policy":[100,128],"rest":[106],"via":[110],"learning.":[112],"It":[113],"is":[114,166,191],"not":[115],"clear":[116],"priori":[118],"if":[119],"all":[120],"learn":[123],"consistent":[125],"optimal":[126],"such":[130],"situation.":[132],"distinguish":[134],"different":[136],"types":[137,163],"learners":[139,165],"depending":[140],"amount":[143],"information":[145,183],"perceive:":[149],"individual":[150],"action":[151,155],"learner":[152,156],"joint":[154],".":[157],"The":[158],"performance":[160,189],"both":[162],"evaluated":[167],"number":[170],"challenging":[172],"deterministic":[173],"stochastic":[175],"games,":[177],"influence":[180],"sharing":[184],"degree":[185],"also":[190],"investigated\u2014a":[192],"key":[193],"difference":[194],"framework":[198],"involving":[199],"among":[202],"agents.":[204]},"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},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}