{"id":"https://openalex.org/W4384008425","doi":"https://doi.org/10.1145/3583131.3590441","title":"A Two-Stage Multi-Objective Evolutionary Reinforcement Learning Framework for Continuous Robot Control","display_name":"A Two-Stage Multi-Objective Evolutionary Reinforcement Learning Framework for Continuous Robot Control","publication_year":2023,"publication_date":"2023-07-12","ids":{"openalex":"https://openalex.org/W4384008425","doi":"https://doi.org/10.1145/3583131.3590441"},"language":"en","primary_location":{"id":"doi:10.1145/3583131.3590441","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583131.3590441","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583131.3590441","source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3583131.3590441","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103052358","display_name":"Hai-Long Tran","orcid":"https://orcid.org/0009-0005-3577-7623"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hai-Long Tran","raw_affiliation_strings":["Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0009-0005-3577-7623","affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043602638","display_name":"L. Doan","orcid":"https://orcid.org/0009-0004-6338-7916"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Long Doan","raw_affiliation_strings":["George Mason University, Fairfax, Virginia, United States of America"],"raw_orcid":"https://orcid.org/0009-0004-6338-7916","affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, Virginia, United States of America","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081219326","display_name":"Ngoc Hoang Luong","orcid":"https://orcid.org/0000-0002-6768-1950"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I4387930302","display_name":"University of Information Technology","ror":"https://ror.org/05kdc4973","country_code":null,"type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I4387930302"]},{"id":"https://openalex.org/I47265099","display_name":"Ho Chi Minh City University of Technology","ror":"https://ror.org/04qva2324","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I47265099"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Ngoc Hoang Luong","raw_affiliation_strings":["University of Information Technology (UIT), VNU-HCM, Ho Chi Minh City, Vietnam","Vietnam National University - Ho Chi Minh City (VNU-HCM), Ho Chi Minh City, Vietnam","University of Information Technology (UIT), VNU-HCM, Ho Chi Minh City, Vietnam Vietnam National University - Ho Chi Minh City (VNU-HCM), Ho Chi Minh City, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-6768-1950","affiliations":[{"raw_affiliation_string":"University of Information Technology (UIT), VNU-HCM, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I47265099","https://openalex.org/I123565023"]},{"raw_affiliation_string":"Vietnam National University - Ho Chi Minh City (VNU-HCM), Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]},{"raw_affiliation_string":"University of Information Technology (UIT), VNU-HCM, Ho Chi Minh City, Vietnam Vietnam National University - Ho Chi Minh City (VNU-HCM), Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023","https://openalex.org/I4387930302"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072105691","display_name":"Hu\u1ef3nh Th\u1ecb Thanh B\u00ecnh","orcid":"https://orcid.org/0000-0003-1976-6113"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Huynh Thi Thanh Binh","raw_affiliation_strings":["Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0000-0003-1976-6113","affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8254,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70048309,"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":"577","last_page":"585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9991000294685364,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9944999814033508,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8781756162643433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6664836406707764},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.6546569466590881},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5948838591575623},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5653519630432129},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5533139109611511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5449525117874146},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.5268610715866089},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5103551745414734},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.5035561919212341},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4482821524143219},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43479830026626587},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.43349379301071167},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4163265824317932},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18094229698181152},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1251349151134491}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8781756162643433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664836406707764},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.6546569466590881},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5948838591575623},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5653519630432129},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5533139109611511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5449525117874146},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.5268610715866089},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5103551745414734},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.5035561919212341},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4482821524143219},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43479830026626587},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.43349379301071167},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4163265824317932},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18094229698181152},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1251349151134491},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583131.3590441","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583131.3590441","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583131.3590441","source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3583131.3590441","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583131.3590441","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583131.3590441","source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320318839","display_name":"T\u1eadp \u0111o\u00e0n Vingroup - C\u00f4ng ty CP","ror":null},{"id":"https://openalex.org/F4320328994","display_name":"Qu\u1ef9 \u0110\u1ed5i m\u1edbi s\u00e1ng t\u1ea1o Vingroup","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384008425.pdf","grobid_xml":"https://content.openalex.org/works/W4384008425.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1619458041","https://openalex.org/W1988210060","https://openalex.org/W2081298389","https://openalex.org/W2107770641","https://openalex.org/W2126105956","https://openalex.org/W2158782408","https://openalex.org/W2186820913","https://openalex.org/W2345009882","https://openalex.org/W2625286567","https://openalex.org/W2706811522","https://openalex.org/W2951278471","https://openalex.org/W2962975462","https://openalex.org/W3099303207","https://openalex.org/W3119912425","https://openalex.org/W4225709924"],"related_works":["https://openalex.org/W3035117390","https://openalex.org/W2147463381","https://openalex.org/W1997381757","https://openalex.org/W3174049743","https://openalex.org/W2162974421","https://openalex.org/W1991985286","https://openalex.org/W2088622475","https://openalex.org/W2134493171","https://openalex.org/W4239294646","https://openalex.org/W2380755212"],"abstract_inverted_index":{"Real-world":[0],"continuous":[1,65],"control":[2,53,67],"problems":[3],"often":[4],"require":[5],"optimizing":[6],"for":[7,54,63,136,149,171],"multiple":[8],"conflicting":[9],"objectives.":[10],"Various":[11],"works":[12],"in":[13,39,86,140],"multi-objective":[14,40,52,64,115,155,173],"reinforcement":[15],"learning":[16],"have":[17,42,168],"been":[18,44,169],"conducted":[19],"to":[20,48,107,111],"tackle":[21],"such":[22],"issues":[23],"and":[24,92,126,144,184],"obtained":[25],"impressive":[26],"performance.":[27],"At":[28],"the":[29,74,77,88,93,103,108,113,141,154,172,189],"same":[30],"time,":[31],"evolutionary":[32],"algorithms":[33],"(EAs),":[34],"which":[35,167],"are":[36],"extensively":[37],"used":[38],"optimization,":[41],"recently":[43],"demonstrated":[45],"their":[46],"competitiveness":[47],"RL":[49,96],"algorithms,":[50],"including":[51],"environments":[55],"with":[56],"discrete":[57],"action":[58],"spaces.":[59],"However,":[60],"using":[61],"EAs":[62],"robot":[66,164],"is":[68],"still":[69],"an":[70,127],"under-explored":[71],"topic.":[72],"For":[73],"single-objective":[75],"setting,":[76],"Proximal":[78],"Distilled":[79],"Evolutionary":[80],"Reinforcement":[81],"Learning":[82],"(PDERL)":[83],"framework":[84,117],"succeeds":[85],"combining":[87],"robustness":[89],"of":[90,95,105,122,196],"EA":[91],"efficiency":[94],"methods.":[97],"In":[98,130],"this":[99],"work,":[100],"we":[101],"bring":[102],"strengths":[104],"PDERL":[106,116],"multiobjective":[109],"realm":[110],"create":[112],"novel":[114],"called":[118],"MOPDERL":[119,132,160,179],"that":[120,147,178],"consists":[121],"a":[123],"warm-up":[124,142],"stage":[125],"evolution":[128,156],"stage.":[129,157],"particular,":[131],"collaboratively":[133],"optimizes":[134],"policies":[135],"each":[137],"separate":[138],"objective":[139],"stage,":[143],"then":[145],"exchanges":[146],"knowledge":[148],"further":[150],"policy":[151],"improvement":[152],"during":[153],"We":[158],"benchmark":[159],"on":[161],"six":[162,197],"MuJoCo":[163],"locomotion":[165],"environments,":[166],"modified":[170],"context.":[174],"The":[175],"results":[176],"show":[177],"produces":[180],"better-quality":[181],"Pareto":[182],"fronts":[183],"higher":[185],"metric":[186],"scores":[187],"than":[188],"state-of-the-art":[190],"PGMORL":[191],"algorithm":[192],"across":[193],"five":[194],"out":[195],"environments.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}