{"id":"https://openalex.org/W4401415886","doi":"https://doi.org/10.1109/icra57147.2024.10610814","title":"Phasic Diversity Optimization for Population-Based Reinforcement Learning","display_name":"Phasic Diversity Optimization for Population-Based Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401415886","doi":"https://doi.org/10.1109/icra57147.2024.10610814"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610814","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610814","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 Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5072206949","display_name":"Jingcheng Jiang","orcid":"https://orcid.org/0009-0005-3801-5333"},"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":"Jingcheng Jiang","raw_affiliation_strings":["Dalian University of Technology,Key Laboratory of Social Computing and Cognitive Intelligence,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,Key Laboratory of Social Computing and Cognitive Intelligence,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004540162","display_name":"Haiyin Piao","orcid":"https://orcid.org/0000-0002-8519-4750"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyin Piao","raw_affiliation_strings":["Northwestern Polytechnical University,School of Electronics and Information,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Electronics and Information,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100610555","display_name":"Yu Fu","orcid":"https://orcid.org/0009-0009-1451-4057"},"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":"Yu Fu","raw_affiliation_strings":["Dalian University of Technology,Key Laboratory of Social Computing and Cognitive Intelligence,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,Key Laboratory of Social Computing and Cognitive Intelligence,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082131030","display_name":"Yihang Hao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihang Hao","raw_affiliation_strings":["Yangzhou Collaborative Innovation Research Institute Co., Ltd,Yangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yangzhou Collaborative Innovation Research Institute Co., Ltd,Yangzhou,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112573325","display_name":"Chuanlu Jiang","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":"Chuanlu Jiang","raw_affiliation_strings":["Dalian University of Technology,Key Laboratory of Social Computing and Cognitive Intelligence,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,Key Laboratory of Social Computing and Cognitive Intelligence,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079553918","display_name":"Ziqi Wei","orcid":"https://orcid.org/0000-0001-9402-8386"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqi Wei","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088751649","display_name":"Xin Yang","orcid":"https://orcid.org/0000-0001-6252-1061"},"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":"Xin Yang","raw_affiliation_strings":["Dalian University of Technology,Key Laboratory of Social Computing and Cognitive Intelligence,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,Key Laboratory of Social Computing and Cognitive Intelligence,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"272","last_page":"278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9886999726295471,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7921943664550781},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.6485943794250488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6114347577095032},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.46754732728004456},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4274429380893707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36460167169570923},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1324940323829651},{"id":"https://openalex.org/keywords/demography","display_name":"Demography","score":0.06059962511062622}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7921943664550781},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.6485943794250488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6114347577095032},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.46754732728004456},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4274429380893707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36460167169570923},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1324940323829651},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.06059962511062622},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/icra57147.2024.10610814","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610814","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 Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W758372786","https://openalex.org/W1583837637","https://openalex.org/W2138779671","https://openalex.org/W2158782408","https://openalex.org/W2168405694","https://openalex.org/W2607662938","https://openalex.org/W2736601468","https://openalex.org/W2787800669","https://openalex.org/W2807841289","https://openalex.org/W2998655286","https://openalex.org/W3004082694","https://openalex.org/W3103787556","https://openalex.org/W3175917212","https://openalex.org/W3196699797","https://openalex.org/W4221160466","https://openalex.org/W4234228486","https://openalex.org/W4287757595","https://openalex.org/W4300799055","https://openalex.org/W4304194242","https://openalex.org/W4309483453","https://openalex.org/W4317584379","https://openalex.org/W4382239238","https://openalex.org/W4383346238","https://openalex.org/W4394662461","https://openalex.org/W6692846177","https://openalex.org/W6747473740","https://openalex.org/W6748594472","https://openalex.org/W6748603076","https://openalex.org/W6748839928","https://openalex.org/W6763022557","https://openalex.org/W6771739536","https://openalex.org/W6773329755","https://openalex.org/W6774499834","https://openalex.org/W6783140480","https://openalex.org/W6789083056","https://openalex.org/W6797779983","https://openalex.org/W6799873116","https://openalex.org/W6810855250"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Reviewing":[0],"the":[1,35,38,42,51,58,65,91,104,108,125,142,145,159],"previous":[2],"work":[3],"of":[4,45,60,85,112,144,152],"diversity":[5,8,26,56,79,115,122],"Reinforcement":[6],"Learning,":[7],"is":[9],"often":[10],"obtained":[11],"via":[12,99],"an":[13,120],"augmented":[14],"loss":[15],"function,":[16],"which":[17],"requires":[18],"a":[19,71,87,134],"balance":[20],"between":[21,53],"reward":[22,46,77,113],"and":[23,55,78,114,155,164],"diversity.":[24],"Generally,":[25],"optimization":[27,123],"algorithms":[28,32],"use":[29,119],"Multi-armed":[30],"Bandits":[31],"to":[33,118,140],"select":[34],"coefficient":[36],"in":[37,107,124,158],"pre-defined":[39],"space.":[40],"However,":[41],"dynamic":[43],"distribution":[44],"signals":[47],"for":[48,137],"MABs":[49],"or":[50],"conflict":[52],"quality":[54],"limits":[57],"performance":[59,97,129,176],"these":[61],"methods.":[62],"We":[63,148],"introduce":[64,149],"Phasic":[66],"Diversity":[67],"Optimization":[68],"(PDO)":[69],"algorithm,":[70],"Population-Based":[72],"Training":[73],"framework":[74],"that":[75,170],"separates":[76],"training":[80],"into":[81],"distinct":[82],"phases":[83],"instead":[84],"optimizing":[86],"multi-objective":[88],"function.":[89],"In":[90],"auxiliary":[92,126],"phase,":[93],"agents":[94,106,139],"with":[95],"poor":[96],"diversified":[98],"determinants":[100],"will":[101],"not":[102],"replace":[103],"better":[105,175],"archive.":[109],"The":[110,167],"decoupling":[111],"allows":[116],"us":[117],"aggressive":[121],"phase":[127],"without":[128],"degradation.":[130],"Furthermore,":[131],"we":[132],"construct":[133],"dogfight":[135,163],"scenario":[136],"aerial":[138],"demonstrate":[141],"practicality":[143],"PDO":[146,153],"algorithm.":[147],"two":[150],"implementations":[151],"archive":[154],"conduct":[156],"tests":[157],"newly":[160],"proposed":[161,172],"adversarial":[162],"MuJoCo":[165],"simulations.":[166],"results":[168],"show":[169],"our":[171],"algorithm":[173],"achieves":[174],"than":[177],"baselines.":[178]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
