{"id":"https://openalex.org/W4412081721","doi":"https://doi.org/10.1109/tnse.2025.3586602","title":"Non-Cooperative Multi-Agent Reinforcement Learning Exploiting Population Dynamics","display_name":"Non-Cooperative Multi-Agent Reinforcement Learning Exploiting Population Dynamics","publication_year":2025,"publication_date":"2025-07-07","ids":{"openalex":"https://openalex.org/W4412081721","doi":"https://doi.org/10.1109/tnse.2025.3586602"},"language":"en","primary_location":{"id":"doi:10.1109/tnse.2025.3586602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnse.2025.3586602","pdf_url":null,"source":{"id":"https://openalex.org/S2484352698","display_name":"IEEE Transactions on Network Science and Engineering","issn_l":"2327-4697","issn":["2327-4697","2334-329X"],"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 Transactions on Network Science and Engineering","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/A5101870134","display_name":"Junling Li","orcid":"https://orcid.org/0000-0002-7104-7100"},"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":true,"raw_author_name":"Junling Li","raw_affiliation_strings":["National Mobile Communications Research Laboratory, School of Information Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"National Mobile Communications Research Laboratory, School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396851","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-0896-4555"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079616969","display_name":"Shuqi Ke","orcid":"https://orcid.org/0000-0002-2467-6502"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuqi Ke","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062346297","display_name":"Jianwei Huang","orcid":"https://orcid.org/0000-0001-6631-1096"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Huang","raw_affiliation_strings":["Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network, School of Science and Engineering, Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China","School of Science and Engineering, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network, and CSIJRI Joint Research Centre on Smart Energy Storage, The Chinese University of Hong Kong, Shenzhen, Guangdong, P.R. China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network, School of Science and Engineering, Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"School of Science and Engineering, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network, and CSIJRI Joint Research Centre on Smart Energy Storage, The Chinese University of Hong Kong, Shenzhen, Guangdong, P.R. China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120790454","display_name":"Nan Chen","orcid":"https://orcid.org/0000-0003-0014-4461"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Nan Chen","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, Hong Kong","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100773343","display_name":"Xuemin Shen","orcid":"https://orcid.org/0000-0002-4140-287X"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xuemin Shen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101870134"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":7.0539,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97019965,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"684","last_page":"700"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10482","display_name":"Mathematical and Theoretical Epidemiology and Ecology Models","score":0.7148000001907349,"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"}},"topics":[{"id":"https://openalex.org/T10482","display_name":"Mathematical and Theoretical Epidemiology and Ecology Models","score":0.7148000001907349,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6979323029518127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5892277956008911},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.48471522331237793},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.43911564350128174},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.4206874370574951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34039610624313354},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.16902577877044678}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6979323029518127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5892277956008911},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.48471522331237793},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.43911564350128174},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.4206874370574951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34039610624313354},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16902577877044678},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tnse.2025.3586602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnse.2025.3586602","pdf_url":null,"source":{"id":"https://openalex.org/S2484352698","display_name":"IEEE Transactions on Network Science and Engineering","issn_l":"2327-4697","issn":["2327-4697","2334-329X"],"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 Transactions on Network Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1542941925","https://openalex.org/W2002373723","https://openalex.org/W2031098375","https://openalex.org/W2036103676","https://openalex.org/W2048584272","https://openalex.org/W2064437312","https://openalex.org/W2070963703","https://openalex.org/W2082261506","https://openalex.org/W2094364653","https://openalex.org/W2096145798","https://openalex.org/W2111698226","https://openalex.org/W2122131925","https://openalex.org/W2969525674","https://openalex.org/W2991046523","https://openalex.org/W3011182939","https://openalex.org/W3017748691","https://openalex.org/W3082622020","https://openalex.org/W3090573937","https://openalex.org/W3095660705","https://openalex.org/W3105649577","https://openalex.org/W3118825529","https://openalex.org/W3134827906","https://openalex.org/W3135602726","https://openalex.org/W3139596528","https://openalex.org/W3158805953","https://openalex.org/W3171715134","https://openalex.org/W3179332103","https://openalex.org/W3210857146","https://openalex.org/W4205812024","https://openalex.org/W4206030629","https://openalex.org/W4285107918","https://openalex.org/W4285202992","https://openalex.org/W4285411993","https://openalex.org/W4361852490","https://openalex.org/W4380078504","https://openalex.org/W4387914688","https://openalex.org/W4392607680","https://openalex.org/W4396523522","https://openalex.org/W4402263009","https://openalex.org/W4404177804","https://openalex.org/W4404238472","https://openalex.org/W4405755397"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Non-cooperative":[0],"multi-agent":[1],"reinforcement":[2],"learning":[3,13],"(MARL)":[4],"faces":[5],"significant":[6,129],"challenges":[7],"due":[8],"to":[9,73,120],"non-stationarity":[10],"and":[11,68,99,113,144],"non-unique":[12],"goals.":[14],"While":[15],"equilibrium-based":[16],"analysis":[17],"frameworks":[18],"effectively":[19],"address":[20],"these":[21,79],"challenges,":[22],"existing":[23,121],"approaches":[24],"suffer":[25],"from":[26],"high":[27],"computational":[28,97],"complexity":[29,76,98],"as":[30],"the":[31,75,83],"number":[32,84],"of":[33,77,85],"agents":[34],"increases.":[35],"To":[36],"overcome":[37],"this":[38],"limitation,":[39],"we":[40],"propose":[41],"a":[42,93],"population":[43,56,61,88],"game-based":[44],"Q-learning":[45],"(Pop-Q)":[46],"algorithm":[47,91,127],"that":[48,105],"computes":[49],"Nash":[50],"equilibrium":[51,100],"(NE)":[52],"policies":[53],"through":[54],"efficient":[55],"dynamics.":[57],"Our":[58],"approach":[59],"represents":[60],"evolution":[62],"using":[63],"ordinary":[64],"differential":[65],"equations":[66],"(ODEs)":[67],"introduces":[69],"two":[70],"key":[71],"mechanisms":[72],"reduce":[74],"solving":[78],"ODEs.":[80],"By":[81],"adjusting":[82],"iterations":[86],"in":[87,110,116,132],"dynamics,":[89],"our":[90],"enables":[92],"controllable":[94],"tradeoff":[95],"between":[96],"accuracy.":[101],"Experimental":[102],"results":[103],"demonstrate":[104],"Pop-Q":[106],"achieves":[107],"competitive":[108],"performance":[109,115],"two-agent":[111],"settings":[112],"superior":[114],"three-agent":[117],"environments":[118],"compared":[119],"equilibriumbased":[122],"MARL":[123],"algorithms.":[124],"The":[125],"proposed":[126],"has":[128],"potential":[130],"applications":[131],"modern":[133],"systems":[134],"requiring":[135],"decentralized":[136],"coordination,":[137],"including":[138],"intelligent":[139],"traffic":[140],"systems,":[141],"warehouse":[142],"automation,":[143],"unmanned":[145],"aerial":[146],"vehicle":[147],"(UAV)":[148],"swarm-aided":[149],"communication":[150],"networks.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}