{"id":"https://openalex.org/W2578029466","doi":"https://doi.org/10.3233/978-1-61499-672-9-533","title":"Socially-Aware Multiagent Learning: Towards Socially Optimal Outcomes","display_name":"Socially-Aware Multiagent Learning: Towards Socially Optimal Outcomes","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2578029466","doi":"https://doi.org/10.3233/978-1-61499-672-9-533","mag":"2578029466"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-672-9-533","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-672-9-533","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","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/A5100451509","display_name":"Xiaohong Li","orcid":"https://orcid.org/0000-0002-0752-6764"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Xiaohong","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767827","display_name":"Chengwei Zhang","orcid":"https://orcid.org/0000-0002-1921-9032"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang Chengwei","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Jianye","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tuyls Karl","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tuyls Karl","raw_affiliation_strings":["University of Liverpool, Liverpool, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Liverpool, Liverpool, United Kingdom","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460982","display_name":"Siqi Chen","orcid":"https://orcid.org/0000-0003-0218-4803"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Siqi","raw_affiliation_strings":["Southwest University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001714538","display_name":"Zhiyong Feng","orcid":"https://orcid.org/0000-0001-5322-222X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhiyong","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0444,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79450121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9828000068664551,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9812999963760376,"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/psychology","display_name":"Psychology","score":0.4591921865940094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3802133798599243},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.3345484733581543}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4591921865940094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3802133798599243},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3345484733581543}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/978-1-61499-672-9-533","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-672-9-533","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W82142180","https://openalex.org/W1192553058","https://openalex.org/W1519783625","https://openalex.org/W1540725368","https://openalex.org/W1542941925","https://openalex.org/W1560074431","https://openalex.org/W1607392272","https://openalex.org/W1996013982","https://openalex.org/W2031098375","https://openalex.org/W2103437045","https://openalex.org/W2152835608","https://openalex.org/W3105048218"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"multiagent":[1,136],"systems":[2],"the":[3,25,33,65,74,81,127,143],"capability":[4],"of":[5,17,84,102,110,129],"learning":[6,82,108,137],"is":[7,30,92,170],"important":[8],"for":[9,98],"an":[10,151],"agent":[11,153],"to":[12,37,94],"behave":[13],"appropriately":[14],"in":[15,123],"face":[16],"unknown":[18],"opponents":[19,175],"and":[20,90,118,168],"a":[21,56,99,134],"dynamic":[22],"environment.":[23],"From":[24],"system":[26,88],"designer's":[27],"perspective,":[28],"it":[29],"desirable":[31],"if":[32],"agents":[34],"can":[35,154],"learn":[36],"coordinate":[38],"towards":[39],"socially":[40],"optimal":[41],"outcomes,":[42],"while":[43],"also":[44,169],"avoiding":[45],"being":[46],"exploited":[47],"by":[48,69,176],"selfish":[49],"opponents.":[50],"To":[51],"this":[52],"end,":[53],"we":[54,131],"propose":[55,133],"novel":[57],"gradient":[58],"ascent":[59],"based":[60,141],"algorithm":[61,68],"(SA-IGA)":[62],"which":[63],"augments":[64],"basic":[66],"gradient-ascent":[67],"incorporating":[70],"social":[71,157],"awareness":[72],"into":[73],"policy":[75],"update":[76,145],"process.":[77],"We":[78],"theoretically":[79],"analyze":[80],"dynamics":[83,97,109],"SA-IGA":[85,91],"using":[86],"dynamical":[87],"theory,":[89],"shown":[93],"have":[95],"linear":[96],"wide":[100],"range":[101],"games":[103,113],"including":[104],"symmetric":[105],"games.":[106],"The":[107],"two":[111],"representative":[112],"(the":[114],"prisoner's":[115],"dilemma":[116],"game":[117],"coordination":[119],"game)":[120],"are":[121],"analyzed":[122],"detail.":[124],"Based":[125],"on":[126,142],"idea":[128],"SA-IGA,":[130],"further":[132],"practical":[135],"algorithm,":[138],"called":[139],"SA-PGA,":[140],"Q-learning":[144],"rule.":[146],"Simulation":[147],"results":[148],"show":[149],"that":[150],"SA-PGA":[152],"achieve":[155],"higher":[156],"welfare":[158],"than":[159],"previous":[160],"social-optimality":[161],"oriented":[162],"Conditional":[163],"Joint":[164],"Action":[165],"Learner":[166],"(CJAL)":[167],"robust":[171],"against":[172],"individually":[173],"rational":[174],"reaching":[177],"Nash":[178],"equilibrium":[179],"solutions.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2017-01-26T00:00:00"}
