{"id":"https://openalex.org/W7162632842","doi":"https://doi.org/10.1002/cav.70121","title":"MADECM: A Curiosity\u2010Augmented Evolutionary Algorithm for Multi\u2010Agent Policy Diversity Optimization","display_name":"MADECM: A Curiosity\u2010Augmented Evolutionary Algorithm for Multi\u2010Agent Policy Diversity Optimization","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7162632842","doi":"https://doi.org/10.1002/cav.70121"},"language":"en","primary_location":{"id":"doi:10.1002/cav.70121","is_oa":false,"landing_page_url":"https://doi.org/10.1002/cav.70121","pdf_url":null,"source":{"id":"https://openalex.org/S100062975","display_name":"Computer Animation and Virtual Worlds","issn_l":"1546-4261","issn":["1546-4261","1546-427X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Animation and Virtual Worlds","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/A5074471394","display_name":"Jianyang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I156292868","display_name":"Dalian University of Foreign Languages","ror":"https://ror.org/008a8z393","country_code":"CN","type":"education","lineage":["https://openalex.org/I156292868"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyang Wu","raw_affiliation_strings":["Dalian University  Dalian China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University  Dalian China","institution_ids":["https://openalex.org/I4210092944","https://openalex.org/I156292868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137251394","display_name":"Yv Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yv Fu","raw_affiliation_strings":["Key Laboratory of Social Computing and Cognitive Intelligence, Ministry of Education Dalian University of Technology  Dalian China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Social Computing and Cognitive Intelligence, Ministry of Education Dalian University of Technology  Dalian China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137233716","display_name":"Xinning Wang","orcid":"https://orcid.org/0009-0003-5643-3892"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinning Wang","raw_affiliation_strings":["Key Laboratory of Social Computing and Cognitive Intelligence, Ministry of Education Dalian University of Technology  Dalian China"],"raw_orcid":"https://orcid.org/0009-0003-5643-3892","affiliations":[{"raw_affiliation_string":"Key Laboratory of Social Computing and Cognitive Intelligence, Ministry of Education Dalian University of Technology  Dalian China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137281388","display_name":"Xin Yang","orcid":"https://orcid.org/0000-0002-8046-722X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Yang","raw_affiliation_strings":["Key Laboratory of Social Computing and Cognitive Intelligence, Ministry of Education Dalian University of Technology  Dalian China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Social Computing and Cognitive Intelligence, Ministry of Education Dalian University of Technology  Dalian China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5137281388"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":{"value":3040,"currency":"USD","value_usd":3040},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94673019,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"3","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":0.8084999918937683,"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":0.8084999918937683,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.04780000075697899,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.0203000009059906,"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/novelty","display_name":"Novelty","score":0.6985999941825867},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6735000014305115},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6600000262260437},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.6211000084877014},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.5206000208854675},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5177000164985657},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46129998564720154},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4377000033855438},{"id":"https://openalex.org/keywords/diversification","display_name":"Diversification (marketing strategy)","score":0.4020000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8432000279426575},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.6985999941825867},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6735000014305115},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6600000262260437},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.6211000084877014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5699999928474426},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4666000008583069},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C180916674","wikidata":"https://www.wikidata.org/wiki/Q3711935","display_name":"Diversification (marketing strategy)","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C2776319702","wikidata":"https://www.wikidata.org/wiki/Q2141158","display_name":"Stigmergy","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C199505168","wikidata":"https://www.wikidata.org/wiki/Q3267529","display_name":"Evolutionary robotics","level":3,"score":0.305400013923645},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28220000863075256},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/cav.70121","is_oa":false,"landing_page_url":"https://doi.org/10.1002/cav.70121","pdf_url":null,"source":{"id":"https://openalex.org/S100062975","display_name":"Computer Animation and Virtual Worlds","issn_l":"1546-4261","issn":["1546-4261","1546-427X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Animation and Virtual Worlds","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5281628966331482}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2039522160","https://openalex.org/W2168405694","https://openalex.org/W3166816823","https://openalex.org/W3175917212","https://openalex.org/W4283021706","https://openalex.org/W4287757595","https://openalex.org/W4401417008"],"related_works":[],"abstract_inverted_index":{"ABSTRACT":[0],"Multi\u2010agent":[1],"reinforcement":[2],"learning":[3],"(MARL)":[4],"often":[5],"suffers":[6],"from":[7],"low":[8],"sample":[9],"efficiency":[10],"and":[11,21,61,102,116,121,125,155],"limited":[12],"behavioral":[13],"diversity,":[14],"leading":[15],"to":[16,52,67],"policy":[17,103],"homogenization,":[18],"insufficient":[19],"exploration,":[20],"reduced":[22],"robustness.":[23],"To":[24],"address":[25],"these":[26,164],"challenges,":[27],"we":[28],"propose":[29],"MADECM,":[30,149],"a":[31,86,91],"curiosity\u2010augmented":[32],"evolutionary":[33,43],"framework":[34],"built":[35],"upon":[36],"MADDPG":[37],"that":[38,138],"integrates":[39],"curiosity\u2010driven":[40],"updates":[41],"with":[42,85],"quality\u2010diversity":[44,87],"optimization.":[45],"MADECM":[46,81,107,139],"employs":[47],"random":[48],"network":[49],"distillation":[50],"(RND)":[51],"estimate":[53],"the":[54,63,96,109],"novelty":[55,65,153],"of":[56,99,148,151],"each":[57],"agent's":[58],"local":[59],"observations":[60],"uses":[62],"resulting":[64],"signal":[66],"dynamically":[68],"allocate":[69],"additional":[70],"update":[71],"frequencies,":[72],"thereby":[73],"emphasizing":[74],"exploration\u2010relevant":[75],"experience":[76],"during":[77],"training.":[78],"In":[79],"addition,":[80],"combines":[82],"population\u2010based":[83],"diversification":[84],"(QD)":[88],"archive":[89],"through":[90],"staged":[92,156],"optimization":[93],"procedure,":[94],"enabling":[95],"joint":[97],"improvement":[98],"task":[100],"return":[101],"diversity.":[104],"We":[105],"evaluate":[106],"on":[108,126],"multi\u2010agent":[110],"particle":[111],"environment":[112],"(MPE),":[113],"including":[114],"Spread":[115],"Reference,":[117],"which":[118,131],"capture":[119],"cooperative":[120],"partially":[122],"observable":[123],"dynamics,":[124],"google":[127],"research":[128],"football":[129],"(GRF),":[130],"emphasizes":[132],"long\u2010horizon":[133],"sequential":[134],"decision\u2010making.":[135],"Results":[136],"show":[137],"consistently":[140],"outperforms":[141],"strong":[142],"MADDPG\u2010based":[143],"baselines.":[144],"The":[145],"modular":[146],"design":[147],"consisting":[150],"RND\u2010based":[152],"estimation":[154],"QD":[157],"optimization,":[158],"further":[159],"supports":[160],"consistent":[161],"generalization":[162],"across":[163],"structurally":[165],"distinct":[166],"environments":[167],"without":[168],"task\u2010specific":[169],"hyperparameter":[170],"tuning.":[171]},"counts_by_year":[],"updated_date":"2026-05-29T06:26:23.687440","created_date":"2026-05-29T00:00:00"}
