{"id":"https://openalex.org/W4406611653","doi":"https://doi.org/10.1109/smc54092.2024.10831366","title":"An Evolutionary Framework with Improved Variance-Stabilized Multi-Objective Proximal Policy Optimization and NSGA-II","display_name":"An Evolutionary Framework with Improved Variance-Stabilized Multi-Objective Proximal Policy Optimization and NSGA-II","publication_year":2024,"publication_date":"2024-10-06","ids":{"openalex":"https://openalex.org/W4406611653","doi":"https://doi.org/10.1109/smc54092.2024.10831366"},"language":"en","primary_location":{"id":"doi:10.1109/smc54092.2024.10831366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5057935426","display_name":"Jing Bi","orcid":"https://orcid.org/0000-0002-4610-0141"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Bi","raw_affiliation_strings":["Beijing University of Technology,College of Computer,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,College of Computer,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113392699","display_name":"C. X. Yue","orcid":"https://orcid.org/0009-0008-4006-0880"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caiheng Yue","raw_affiliation_strings":["Beijing University of Technology,College of Computer,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,College of Computer,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070546858","display_name":"Haitao Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Yuan","raw_affiliation_strings":["Beihang University,School of Automation Science and Electrical Engineering,Beijing,China,100191"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Automation Science and Electrical Engineering,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040087091","display_name":"Jiahui Zhai","orcid":"https://orcid.org/0000-0002-0443-2690"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahui Zhai","raw_affiliation_strings":["Beijing University of Technology,College of Computer,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,College of Computer,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360704","display_name":"Jia Zhang","orcid":"https://orcid.org/0000-0003-2148-0923"},"institutions":[{"id":"https://openalex.org/I178169726","display_name":"Southern Methodist University","ror":"https://ror.org/042tdr378","country_code":"US","type":"education","lineage":["https://openalex.org/I178169726"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia Zhang","raw_affiliation_strings":["Southern Methodist University,Dept. of Computer Science,Dallas,TX,USA,75275"],"affiliations":[{"raw_affiliation_string":"Southern Methodist University,Dept. of Computer Science,Dallas,TX,USA,75275","institution_ids":["https://openalex.org/I178169726"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081318069","display_name":"MengChu Zhou","orcid":"https://orcid.org/0000-0002-5408-8752"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"MengChu Zhou","raw_affiliation_strings":["New Jersey Institute of Technology,Dept. of Electrical and Computer Engineering,Newark,NJ,USA,07102"],"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology,Dept. of Electrical and Computer Engineering,Newark,NJ,USA,07102","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5057935426"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24016424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3733","last_page":"3738"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8912000060081482,"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":0.8912000060081482,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.8044999837875366,"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/T11182","display_name":"Auction Theory and Applications","score":0.7730000019073486,"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/variance","display_name":"Variance (accounting)","score":0.6269473433494568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5588494539260864},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.47999829053878784},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.46087533235549927},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.427262544631958},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2754025459289551},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.13228121399879456}],"concepts":[{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6269473433494568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5588494539260864},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.47999829053878784},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.46087533235549927},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.427262544631958},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2754025459289551},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.13228121399879456},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc54092.2024.10831366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10831366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":22,"referenced_works":["https://openalex.org/W1501017499","https://openalex.org/W1998379075","https://openalex.org/W2062061003","https://openalex.org/W2102577361","https://openalex.org/W2110373411","https://openalex.org/W2126105956","https://openalex.org/W2507341542","https://openalex.org/W2944766483","https://openalex.org/W3008690002","https://openalex.org/W3013525469","https://openalex.org/W3112578794","https://openalex.org/W3180532788","https://openalex.org/W3217244108","https://openalex.org/W4211006166","https://openalex.org/W4226249635","https://openalex.org/W4290973640","https://openalex.org/W4312963428","https://openalex.org/W4317794990","https://openalex.org/W4319342019","https://openalex.org/W4390905219","https://openalex.org/W4390905594","https://openalex.org/W4394015662"],"related_works":["https://openalex.org/W4318426920","https://openalex.org/W2055791821","https://openalex.org/W2751605210","https://openalex.org/W2977596624","https://openalex.org/W2162013778","https://openalex.org/W2145877535","https://openalex.org/W2153873031","https://openalex.org/W570431388","https://openalex.org/W2637862190","https://openalex.org/W2611723089"],"abstract_inverted_index":{"Multi-objective":[0,77],"optimization":[1],"algorithms":[2,15,180],"are":[3,16],"essential":[4],"for":[5,82,124],"addressing":[6],"real-world":[7],"challenges":[8],"characterized":[9],"by":[10,86,117],"conflicting":[11],"objectives.":[12],"Although":[13],"conventional":[14],"effective":[17],"in":[18],"exploring":[19],"solution":[20,26,114,122,134],"spaces":[21],"and":[22,28,53,65,97,103,131,151],"generating":[23],"non-dominated":[24],"solutions,":[25,155],"quality":[27,150],"dynamic":[29],"adaptability":[30],"of":[31,60,145,154],"true":[32,161],"Pareto":[33,162],"fronts":[34],"need":[35],"to":[36,100],"be":[37],"improved.":[38],"This":[39,110],"work":[40,73,93,111],"proposes":[41],"a":[42],"multi-objective":[43,169,178],"algorithm":[44,50],"that":[45,172],"integrates":[46],"Non-dominated":[47],"sorting":[48],"genetic":[49],"II":[51],"(NSGA-II)":[52],"Multi-Objective":[54],"Reinforcement":[55],"Learning":[56],"(N-MORL).":[57],"N-MORL":[58,147,173],"consists":[59],"two":[61],"parts":[62],"including":[63],"upstream":[64,70],"downstream":[66,125],"components.":[67],"In":[68],"the":[69,75,120,128,133,141,149,152,160,175,185],"component,":[71],"this":[72,92],"improves":[74,106],"Variance-stabilized":[76],"Proximal":[78],"Policy":[79],"Optimization":[80],"(VMPPO)":[81],"enhanced":[83],"convergence":[84,143],"stability":[85],"adjusting":[87],"its":[88],"iteration":[89],"mechanism.":[90],"Additionally,":[91],"optimizes":[94],"variance":[95],"networks":[96],"action":[98],"sampling":[99,108],"balance":[101],"exploration":[102,129],"exploitation,":[104],"which":[105],"experience":[107],"efficiency.":[109],"adopts":[112],"high-quality":[113,182],"sets":[115],"yielded":[116],"MORL":[118],"as":[119],"initial":[121,137],"set":[123],"NSGA-II,":[126],"guiding":[127],"space":[130],"increasing":[132],"number.":[135],"High-quality":[136],"solutions":[138,183],"significantly":[139],"accelerate":[140],"iterative":[142],"speed":[144],"N-MORL.":[146],"provides":[148],"number":[153],"better":[156],"covering":[157],"or":[158],"approaching":[159],"front.":[163],"Experimental":[164],"results":[165],"with":[166,184],"five":[167],"benchmark":[168],"functions":[170],"demonstrate":[171],"outperforms":[174],"other":[176],"three":[177],"evolutionary":[179],"regarding":[181],"same":[186],"iterations.":[187]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
