{"id":"https://openalex.org/W2592981353","doi":"https://doi.org/10.1109/jas.2017.7510466","title":"An adaptive strategy via reinforcement learning for the prisoner dilemma game","display_name":"An adaptive strategy via reinforcement learning for the prisoner dilemma game","publication_year":2017,"publication_date":"2017-03-11","ids":{"openalex":"https://openalex.org/W2592981353","doi":"https://doi.org/10.1109/jas.2017.7510466","mag":"2592981353"},"language":"en","primary_location":{"id":"doi:10.1109/jas.2017.7510466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jas.2017.7510466","pdf_url":null,"source":{"id":"https://openalex.org/S2484288132","display_name":"IEEE/CAA Journal of Automatica Sinica","issn_l":"2329-9266","issn":["2329-9266","2329-9274"],"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/CAA Journal of Automatica Sinica","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/A5101452675","display_name":"Lei Xue","orcid":"https://orcid.org/0000-0002-2510-1188"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xue","raw_affiliation_strings":["Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, School of Automation, Southeast University, Nanjing 210096, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, School of Automation, Southeast University, Nanjing 210096, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019248683","display_name":"Changyin Sun","orcid":"https://orcid.org/0000-0001-9269-334X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyin Sun","raw_affiliation_strings":["Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, School of Automation, Southeast University, Nanjing 210096, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, School of Automation, Southeast University, Nanjing 210096, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038037619","display_name":"Donald C. Wunsch","orcid":"https://orcid.org/0000-0002-9726-9051"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donald Wunsch","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO 65409, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO 65409, USA","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080737555","display_name":"Yingjiang Zhou","orcid":"https://orcid.org/0000-0002-4481-3746"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingjiang Zhou","raw_affiliation_strings":["College of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210023, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061560652","display_name":"Fang Yu","orcid":"https://orcid.org/0000-0001-8100-8001"},"institutions":[{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Yu","raw_affiliation_strings":["Institute of Logistics Science and Engineering, Shanghai Maritime University, Shanghai 210096, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Logistics Science and Engineering, Shanghai Maritime University, Shanghai 210096, China","institution_ids":["https://openalex.org/I96733725"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.0326,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.98979741,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"5","issue":"1","first_page":"301","last_page":"310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9998000264167786,"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":0.9998000264167786,"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/T10482","display_name":"Mathematical and Theoretical Epidemiology and Ecology Models","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9853000044822693,"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":0.7601712942123413},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6905494928359985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5610224604606628},{"id":"https://openalex.org/keywords/prisoners-dilemma","display_name":"Prisoner's dilemma","score":0.5496712923049927},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.5301595330238342},{"id":"https://openalex.org/keywords/adaptive-learning","display_name":"Adaptive learning","score":0.49323076009750366},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.45716726779937744},{"id":"https://openalex.org/keywords/evolution-strategy","display_name":"Evolution strategy","score":0.4452741742134094},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36214888095855713},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3429507315158844},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.3324577212333679},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.18385794758796692},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.177967369556427},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.15707537531852722}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7601712942123413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6905494928359985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5610224604606628},{"id":"https://openalex.org/C113494165","wikidata":"https://www.wikidata.org/wiki/Q41693","display_name":"Prisoner's dilemma","level":3,"score":0.5496712923049927},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.5301595330238342},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.49323076009750366},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.45716726779937744},{"id":"https://openalex.org/C207002847","wikidata":"https://www.wikidata.org/wiki/Q2912857","display_name":"Evolution strategy","level":3,"score":0.4452741742134094},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36214888095855713},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3429507315158844},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3324577212333679},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.18385794758796692},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.177967369556427},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.15707537531852722},{"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":[{"id":"doi:10.1109/jas.2017.7510466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jas.2017.7510466","pdf_url":null,"source":{"id":"https://openalex.org/S2484288132","display_name":"IEEE/CAA Journal of Automatica Sinica","issn_l":"2329-9266","issn":["2329-9266","2329-9274"],"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/CAA Journal of Automatica Sinica","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1972801537","https://openalex.org/W1976060020","https://openalex.org/W1983523909","https://openalex.org/W1983859759","https://openalex.org/W1987725948","https://openalex.org/W1992195122","https://openalex.org/W1997418576","https://openalex.org/W2013061598","https://openalex.org/W2025490132","https://openalex.org/W2027020357","https://openalex.org/W2044330174","https://openalex.org/W2062663664","https://openalex.org/W2067539801","https://openalex.org/W2082568135","https://openalex.org/W2089684487","https://openalex.org/W2101579790","https://openalex.org/W2108383324","https://openalex.org/W2117556320","https://openalex.org/W2120593719","https://openalex.org/W2126075450","https://openalex.org/W2126580421","https://openalex.org/W2129786343","https://openalex.org/W2153007531","https://openalex.org/W2153029769","https://openalex.org/W2163574479","https://openalex.org/W2165702661","https://openalex.org/W2169258361","https://openalex.org/W2489526136"],"related_works":["https://openalex.org/W3124059960","https://openalex.org/W3213853984","https://openalex.org/W4380049051","https://openalex.org/W2382058083","https://openalex.org/W3169566952","https://openalex.org/W2067015114","https://openalex.org/W3090164891","https://openalex.org/W2129990955","https://openalex.org/W1593266056","https://openalex.org/W3043795202"],"abstract_inverted_index":{"The":[0,162],"iterated":[1],"prisoner's":[2],"dilemma":[3],"(IPD)":[4],"is":[5,66,88,141],"an":[6],"ideal":[7],"model":[8],"for":[9,68,167],"analyzing":[10],"interactions":[11],"between":[12],"agents":[13,50,129],"in":[14,22,33,45,92,158],"complex":[15,47],"networks.":[16],"It":[17],"has":[18,136],"attracted":[19],"wide":[20],"interest":[21],"the":[23,29,70,75,80,93,114,118,125,146,159,172],"development":[24],"of":[25,31,43,79,113,171],"novel":[26],"strategies":[27,56,157],"since":[28],"success":[30],"tit-for-tat":[32],"Axelrod's":[34],"tournament.":[35],"This":[36],"paper":[37],"studies":[38,83],"a":[39,151],"new":[40],"adaptive":[41,71,115,128,147,173],"strategy":[42,72,148],"IPD":[44],"different":[46],"networks,":[48],"where":[49],"can":[51,121,149],"learn":[52],"and":[53,104,133],"adapt":[54],"their":[55],"through":[57],"reinforcement":[58],"learning":[59,64],"method.":[60],"A":[61],"temporal":[62],"difference":[63],"method":[65],"applied":[67],"designing":[69],"to":[73,90,109,143],"optimize":[74],"decision":[76],"making":[77],"process":[78],"agents.":[81],"Previous":[82],"indicated":[84],"that":[85],"mutual":[86,119,138],"cooperation":[87,120],"hard":[89],"emerge":[91],"IPD.":[94],"Therefore,":[95],"three":[96],"examples":[97],"which":[98],"based":[99],"on":[100],"square":[101,160],"lattice":[102],"network":[103,106],"scale-free":[105,131],"are":[107,165],"provided":[108],"show":[110],"two":[111],"features":[112],"strategy.":[116,174],"First,":[117],"be":[122],"achieved":[123],"by":[124],"group":[126],"with":[127,155],"under":[130],"network,":[132],"once":[134],"evolution":[135],"converged":[137],"cooperation,":[139],"it":[140],"unlikely":[142],"shift.":[144],"Secondly,":[145],"earn":[150],"better":[152],"payoff":[153],"compared":[154],"other":[156],"network.":[161],"analytical":[163],"properties":[164],"discussed":[166],"verifying":[168],"evolutionary":[169],"stability":[170]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":7}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}