{"id":"https://openalex.org/W2988496623","doi":"https://doi.org/10.1145/3356464.3357712","title":"Achieving cooperation through deep multiagent reinforcement learning in sequential prisoner's dilemmas","display_name":"Achieving cooperation through deep multiagent reinforcement learning in sequential prisoner's dilemmas","publication_year":2019,"publication_date":"2019-10-13","ids":{"openalex":"https://openalex.org/W2988496623","doi":"https://doi.org/10.1145/3356464.3357712","mag":"2988496623"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3356464.3357712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5082417441","display_name":"Weixun Wang","orcid":"https://orcid.org/0000-0002-2727-8948"},"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":"Weixun Wang","raw_affiliation_strings":["Tianjin University"],"affiliations":[{"raw_affiliation_string":"Tianjin University","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":"Jianye Hao","raw_affiliation_strings":["Tianjin University"],"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015495801","display_name":"Yixi Wang","orcid":"https://orcid.org/0000-0002-1182-6073"},"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":"Yixi Wang","raw_affiliation_strings":["Tianjin University"],"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070914351","display_name":"Matthew E. Taylor","orcid":"https://orcid.org/0000-0001-8946-0211"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Taylor","raw_affiliation_strings":["Washington State University"],"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.905,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.869032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":81,"max":82},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11252","display_name":"Evolution of Cooperation and Altruism in Social Systems","score":0.9993,"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":"Evolution of Cooperation and Altruism in Social Systems","score":0.9993,"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/T10462","display_name":"Reinforcement Learning Algorithms","score":0.9939,"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/T10646","display_name":"Social Preferences and Economic Behavior","score":0.9911,"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/social-dilemma","display_name":"Social dilemma","score":0.6528538},{"id":"https://openalex.org/keywords/iterated-function","display_name":"Iterated function","score":0.596967},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement Learning","score":0.549643},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"Multi-Agent Systems","score":0.509143},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"Policy Gradient","score":0.504362},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep Learning","score":0.501277}],"concepts":[{"id":"https://openalex.org/C113494165","wikidata":"https://www.wikidata.org/wiki/Q41693","display_name":"Prisoner's dilemma","level":3,"score":0.82625765},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.74341726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.70238817},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.65328765},{"id":"https://openalex.org/C187206662","wikidata":"https://www.wikidata.org/wiki/Q55607920","display_name":"Social dilemma","level":2,"score":0.6528538},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.596967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.50982445},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.43339005},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.18967906},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.15756804},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.10450077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09985468},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3356464.3357712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":16,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1979025384","https://openalex.org/W2046811520","https://openalex.org/W2063181669","https://openalex.org/W2099618002","https://openalex.org/W2119717200","https://openalex.org/W2120846115","https://openalex.org/W2124951424","https://openalex.org/W2145339207","https://openalex.org/W2147492008","https://openalex.org/W2155027007","https://openalex.org/W2169951505","https://openalex.org/W2471883051","https://openalex.org/W2551398049","https://openalex.org/W2577420768","https://openalex.org/W2769567824"],"related_works":["https://openalex.org/W4298270609","https://openalex.org/W3123768495","https://openalex.org/W2785863428","https://openalex.org/W2382058083","https://openalex.org/W2322893806","https://openalex.org/W2112744430","https://openalex.org/W2064217014","https://openalex.org/W2049403053","https://openalex.org/W2004817889","https://openalex.org/W1568183880"],"abstract_inverted_index":{"The":[0,85,105,124],"Iterated":[1],"Prisoner's":[2,49],"Dilemma":[3,50],"has":[4],"guided":[5],"research":[6],"on":[7,117],"social":[8],"dilemmas":[9],"for":[10],"decades.":[11],"However,":[12],"it":[13,90],"distinguishes":[14],"between":[15],"only":[16],"two":[17,83,132],"atomic":[18],"actions:":[19],"cooperate":[20],"and":[21,32,97,140,158],"defect.":[22],"In":[23,59],"real-world":[24],"prisoner's":[25],"dilemmas,":[26],"these":[27],"choices":[28],"are":[29],"temporally":[30],"extended":[31],"different":[33,94],"strategies":[34],"may":[35],"correspond":[36],"to":[37,53],"sequences":[38],"of":[39,43,73,82,121,126],"actions,":[40],"reflecting":[41],"grades":[42],"cooperation.":[44,123],"We":[45],"introduce":[46],"a":[47,64,100],"Sequential":[48],"(SPD)":[51],"game":[52,139],"better":[54],"capture":[55],"the":[56,71,118,137,141],"aforementioned":[57],"characteristics.":[58],"this":[60],"work,":[61],"we":[62],"propose":[63],"deep":[65],"multiagent":[66],"reinforcement-learning":[67],"approach":[68,80,128],"that":[69,148],"investigates":[70],"evolution":[72],"mutual":[74],"cooperation":[75,95,101,160],"in":[76,131],"SPD":[77,134],"games.":[78],"Our":[79],"consists":[81],"phases.":[84],"first":[86],"phase":[87,107],"is":[88,108,129],"offline:":[89],"synthesizes":[91],"policies":[92],"with":[93,161],"degrees":[96],"then":[98],"trains":[99],"degree":[102,120],"detection":[103],"network.":[104],"second":[106],"online:":[109],"an":[110],"agent":[111],"adaptively":[112],"selects":[113],"its":[114],"policy":[115],"based":[116],"detected":[119],"opponent":[122],"effectiveness":[125],"our":[127,149],"demonstrated":[130],"representative":[133],"2D":[135],"games:":[136],"Apple-Pear":[138],"Fruit":[142],"Gathering":[143],"game.":[144],"Experimental":[145],"results":[146],"show":[147],"strategy":[150],"can":[151],"avoid":[152],"being":[153],"exploited":[154],"by":[155],"exploitative":[156],"opponents":[157],"achieve":[159],"cooperative":[162],"opponents.":[163]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2988496623","counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2024-12-03T19:54:27.174637","created_date":"2019-11-22"}
