{"id":"https://openalex.org/W2024978320","doi":"https://doi.org/10.1145/2517329","title":"Achieving Socially Optimal Outcomes in Multiagent Systems with Reinforcement Social Learning","display_name":"Achieving Socially Optimal Outcomes in Multiagent Systems with Reinforcement Social Learning","publication_year":2013,"publication_date":"2013-09-01","ids":{"openalex":"https://openalex.org/W2024978320","doi":"https://doi.org/10.1145/2517329","mag":"2024978320"},"language":"en","primary_location":{"id":"doi:10.1145/2517329","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2517329","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/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","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":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ho-Fung Leung","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047509839"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.9504,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89863968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"8","issue":"3","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9983000159263611,"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":0.9976999759674072,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8450502157211304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7707414031028748},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.6400426030158997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5878204107284546},{"id":"https://openalex.org/keywords/social-learning","display_name":"Social learning","score":0.5704575181007385},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5647404193878174},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4896624684333801},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.46928226947784424},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.4151194989681244},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4110924005508423},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3960113823413849},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.17258965969085693}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8450502157211304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7707414031028748},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.6400426030158997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5878204107284546},{"id":"https://openalex.org/C79416737","wikidata":"https://www.wikidata.org/wiki/Q2305519","display_name":"Social learning","level":2,"score":0.5704575181007385},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5647404193878174},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4896624684333801},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.46928226947784424},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4151194989681244},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4110924005508423},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3960113823413849},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.17258965969085693},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2517329","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2517329","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":[{"id":"https://metadata.un.org/sdg/16","score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W3039556","https://openalex.org/W26772505","https://openalex.org/W32403112","https://openalex.org/W44964255","https://openalex.org/W92376239","https://openalex.org/W112918015","https://openalex.org/W1513468570","https://openalex.org/W1519954801","https://openalex.org/W1523200180","https://openalex.org/W1542941925","https://openalex.org/W1583863738","https://openalex.org/W1596727164","https://openalex.org/W1866363433","https://openalex.org/W1960351623","https://openalex.org/W1979025384","https://openalex.org/W1996475210","https://openalex.org/W2008658041","https://openalex.org/W2012347046","https://openalex.org/W2031616997","https://openalex.org/W2037838073","https://openalex.org/W2071351689","https://openalex.org/W2081260471","https://openalex.org/W2085366587","https://openalex.org/W2103437045","https://openalex.org/W2104602264","https://openalex.org/W2105159162","https://openalex.org/W2107544712","https://openalex.org/W2109100253","https://openalex.org/W2120327309","https://openalex.org/W2147521489","https://openalex.org/W2152614054","https://openalex.org/W2164637474","https://openalex.org/W2168163987","https://openalex.org/W2168908800","https://openalex.org/W3215907522","https://openalex.org/W4236547334"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915","https://openalex.org/W2089415692","https://openalex.org/W4294873804"],"abstract_inverted_index":{"In":[0,186],"multiagent":[1],"systems,":[2],"social":[3,120,211,247],"optimality":[4],"is":[5,192,199,214],"a":[6,32],"desirable":[7],"goal":[8],"to":[9,63,71,135],"achieve":[10],"in":[11,36,84,101,173],"terms":[12],"of":[13,18,25,34,80,139,160,169,209,220,238,245],"maximizing":[14],"the":[15,19,23,46,65,78,87,109,132,137,148,167,189,218,242,246],"global":[16],"efficiency":[17],"system.":[20],"We":[21],"study":[22],"problem":[24],"coordinating":[26],"on":[27,77,95,108,155,241],"socially":[28],"optimal":[29,180],"outcomes":[30],"among":[31,142],"population":[33,47],"agents,":[35],"which":[37,98],"each":[38,48,183],"agent":[39,44,164],"randomly":[40],"interacts":[41],"with":[42,123,225],"another":[43],"from":[45,68],"round.":[49],"Previous":[50],"work":[51,86,227],"[Hales":[52],"and":[53,57,74,105,177,196,204,229,233],"Edmonds":[54],"2003;":[55],"Matlock":[56,232],"Sen":[58,234],"2007,":[59],"2009]":[60],"mainly":[61],"resorts":[62],"modifying":[64],"interaction":[66,70],"protocol":[67],"random":[69],"tag-based":[72],"interactions":[73],"only":[75],"focus":[76],"case":[79],"symmetric":[81,203],"games.":[82,206],"Besides,":[83],"previous":[85,226],"agents\u2019":[88,149],"decision":[89],"making":[90],"processes":[91],"are":[92,250],"usually":[93,99],"based":[94,154],"evolutionary":[96,161],"learning,":[97],"results":[100],"high":[102,106],"communication":[103,140],"cost":[104],"deviation":[107],"coordination":[110],"rate.":[111],"To":[112],"solve":[113],"these":[114],"problems,":[115],"we":[116,130,145],"propose":[117,146],"an":[118],"alternative":[119],"learning":[121,150,157,175,190,212,243,248],"framework":[122,213,249],"two":[124],"major":[125],"contributions":[126],"as":[127,252],"follows.":[128],"First,":[129],"introduce":[131],"observation":[133],"mechanism":[134],"reduce":[136],"amount":[138],"required":[141],"agents.":[143],"Second,":[144],"that":[147],"strategies":[151],"should":[152],"be":[153],"reinforcement":[156],"technique":[158],"instead":[159],"learning.":[162],"Each":[163],"explicitly":[165],"keeps":[166],"record":[168],"its":[170,174,179],"current":[171],"state":[172,184],"strategy,":[176],"learn":[178],"policy":[181],"for":[182,201],"independently.":[185],"this":[187,210],"way,":[188],"performance":[191,208,244],"much":[193],"more":[194],"stable":[195],"also":[197],"it":[198],"suitable":[200],"both":[202],"asymmetric":[205],"The":[207,236],"extensively":[215],"evaluated":[216],"under":[217],"testbed":[219],"two-player":[221],"general-sum":[222],"games":[223],"comparing":[224],"[Hao":[228],"Leung":[230],"2011;":[231],"2007].":[235],"influences":[237],"different":[239],"factors":[240],"investigated":[251],"well.":[253]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}