{"id":"https://openalex.org/W4391019857","doi":"https://doi.org/10.1109/cdc49753.2023.10383787","title":"A Multi-Agent Reinforcement Learning Approach to Promote Cooperation in Evolutionary Games on Networks with Environmental Feedback","display_name":"A Multi-Agent Reinforcement Learning Approach to Promote Cooperation in Evolutionary Games on Networks with Environmental Feedback","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391019857","doi":"https://doi.org/10.1109/cdc49753.2023.10383787"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383787","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc49753.2023.10383787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-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/A5100665419","display_name":"Tuo Zhang","orcid":"https://orcid.org/0000-0001-5396-918X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tuo Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029706579","display_name":"Harsh Gupta","orcid":"https://orcid.org/0000-0003-4667-3377"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harsh Gupta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093745160","display_name":"Kumar Suprabhat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar Suprabhat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038355992","display_name":"Leonardo Stella","orcid":"https://orcid.org/0000-0002-2670-9873"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leonardo Stella","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100665419"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1224,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85298365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2196","last_page":"2201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9955000281333923,"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/T11764","display_name":"Evolution and Genetic Dynamics","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.683935284614563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6330122351646423},{"id":"https://openalex.org/keywords/social-dilemma","display_name":"Social dilemma","score":0.535744845867157},{"id":"https://openalex.org/keywords/altruism","display_name":"Altruism (biology)","score":0.5287014245986938},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.48971202969551086},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.48947417736053467},{"id":"https://openalex.org/keywords/evolutionary-game-theory","display_name":"Evolutionary game theory","score":0.48877426981925964},{"id":"https://openalex.org/keywords/shared-resource","display_name":"Shared resource","score":0.44681575894355774},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4391191899776459},{"id":"https://openalex.org/keywords/reciprocal-altruism","display_name":"Reciprocal altruism","score":0.42401015758514404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3982080817222595},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.39613479375839233},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.383171021938324},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.2537824511528015},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.2282373011112213},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1811079978942871},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1301746666431427},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.1267593801021576},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12219178676605225},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10927963256835938},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10870113968849182}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.683935284614563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6330122351646423},{"id":"https://openalex.org/C187206662","wikidata":"https://www.wikidata.org/wiki/Q55607920","display_name":"Social dilemma","level":2,"score":0.535744845867157},{"id":"https://openalex.org/C2780279448","wikidata":"https://www.wikidata.org/wiki/Q2559380","display_name":"Altruism (biology)","level":2,"score":0.5287014245986938},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.48971202969551086},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.48947417736053467},{"id":"https://openalex.org/C20249471","wikidata":"https://www.wikidata.org/wiki/Q2298789","display_name":"Evolutionary game theory","level":3,"score":0.48877426981925964},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.44681575894355774},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4391191899776459},{"id":"https://openalex.org/C119838172","wikidata":"https://www.wikidata.org/wiki/Q429787","display_name":"Reciprocal altruism","level":2,"score":0.42401015758514404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3982080817222595},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.39613479375839233},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.383171021938324},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.2537824511528015},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.2282373011112213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1811079978942871},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1301746666431427},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1267593801021576},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12219178676605225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10927963256835938},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10870113968849182},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383787","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc49753.2023.10383787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1192553058","https://openalex.org/W1415442047","https://openalex.org/W1967829443","https://openalex.org/W1995622844","https://openalex.org/W2021563785","https://openalex.org/W2026069625","https://openalex.org/W2034923450","https://openalex.org/W2040301417","https://openalex.org/W2062663664","https://openalex.org/W2079460424","https://openalex.org/W2143367059","https://openalex.org/W2161526268","https://openalex.org/W2162420711","https://openalex.org/W2501105983","https://openalex.org/W2549525793","https://openalex.org/W2804723336","https://openalex.org/W2900409824","https://openalex.org/W2949913545","https://openalex.org/W3006462484","https://openalex.org/W3102974627","https://openalex.org/W3152977840","https://openalex.org/W3197975701","https://openalex.org/W4200280039","https://openalex.org/W4285204631","https://openalex.org/W4310705874","https://openalex.org/W6682338155","https://openalex.org/W6684389335"],"related_works":["https://openalex.org/W2122882980","https://openalex.org/W2132654772","https://openalex.org/W2732483096","https://openalex.org/W2140977991","https://openalex.org/W1966263378","https://openalex.org/W2140133017","https://openalex.org/W1659812159","https://openalex.org/W1992976504","https://openalex.org/W1970878291","https://openalex.org/W2019575624"],"abstract_inverted_index":{"A":[0],"prominent":[1],"feature":[2],"of":[3,9,35,62,68,106,115,133,141,145,156],"biological":[4],"organization":[5],"in":[6,22,32,43,94],"many":[7],"species":[8],"social":[10],"animals":[11],"is":[12,110,130,162,172,183],"the":[13,33,60,65,69,77,82,92,95,104,107,113,126,142,146,167,186],"ability":[14],"to":[15,185],"achieve":[16],"cooperation.":[17],"However,":[18],"despite":[19],"its":[20],"predominance":[21],"natural":[23],"evolution,":[24],"cooperative":[25],"behaviors":[26],"come":[27],"at":[28],"a":[29,100,123,131,138,154,173],"cost,":[30],"typically":[31],"form":[34],"do":[36],"ut":[37],"des":[38],"mechanisms":[39],"(e.g.,":[40],"reciprocal":[41],"altruism":[42],"vampire":[44],"bats)":[45],"with":[46,190],"given":[47],"thresholds":[48],"for":[49],"sharing":[50],"resources":[51],"or":[52],"communication":[53],"efforts.":[54],"In":[55,89],"this":[56,181],"paper,":[57],"we":[58,136,152,165,178],"investigate":[59],"conditions":[61],"cooperation":[63,161],"through":[64,112],"evolutionary":[66],"dynamics":[67,79],"prisoner's":[70],"dilemma":[71],"(PD)":[72],"game":[73,189],"as":[74,76,122],"well":[75],"learning":[78,86],"resulting":[80],"from":[81],"corresponding":[83,168],"multi-agent":[84],"reinforcement":[85],"(MARL)":[87],"model.":[88],"both":[90],"cases,":[91],"interactions":[93],"population":[96],"are":[97],"captured":[98],"by":[99],"regular":[101],"network":[102],"and":[103,177],"impact":[105],"players'":[108],"actions":[109],"reflected":[111],"evolution":[114],"an":[116],"environmental":[117,191],"resource,":[118],"which":[119,160,171],"also":[120],"acts":[121],"feedback":[124],"on":[125],"dynamics.":[127],"The":[128],"following":[129],"list":[132],"contributions:":[134],"i)":[135],"provide":[137],"full":[139],"characterization":[140],"stability":[143],"properties":[144],"networked":[147,187],"feedback-evolving":[148],"PD":[149,188],"game;":[150],"ii)":[151],"determine":[153],"set":[155],"threshold":[157],"values":[158],"below":[159],"promoted;":[163],"iii)":[164],"develop":[166],"cross-learning":[169],"model,":[170,176],"stateless":[174],"MARL":[175],"show":[179],"that":[180],"model":[182],"equivalent":[184],"feedback.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}