{"id":"https://openalex.org/W3187600255","doi":"https://doi.org/10.1155/2021/5300189","title":"Diversity Evolutionary Policy Deep Reinforcement Learning","display_name":"Diversity Evolutionary Policy Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3187600255","doi":"https://doi.org/10.1155/2021/5300189","mag":"3187600255","pmid":"https://pubmed.ncbi.nlm.nih.gov/34394336"},"language":"en","primary_location":{"id":"doi:10.1155/2021/5300189","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/5300189","pdf_url":"https://downloads.hindawi.com/journals/cin/2021/5300189.pdf","source":{"id":"https://openalex.org/S72372694","display_name":"Computational Intelligence and Neuroscience","issn_l":"1687-5265","issn":["1687-5265","1687-5273"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Intelligence and Neuroscience","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://downloads.hindawi.com/journals/cin/2021/5300189.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039856426","display_name":"Jian Liu","orcid":"https://orcid.org/0000-0002-0470-924X"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian Liu","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou 221116, China","School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China"],"raw_orcid":"https://orcid.org/0000-0002-0470-924X","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou 221116, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102420954","display_name":"Liming Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liming Feng","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou 221116, China","School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou 221116, China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5039856426"],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":{"value":2550,"currency":"USD","value_usd":2550},"apc_paid":{"value":2550,"currency":"USD","value_usd":2550},"fwci":1.0427,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81273231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"2021","issue":"1","first_page":"5300189","last_page":"5300189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9890999794006348,"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":0.9890999794006348,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9491000175476074,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9289000034332275,"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/diversity","display_name":"Diversity (politics)","score":0.7645124197006226},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7511509656906128},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5514954328536987},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48015445470809937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40657156705856323},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.3483240306377411},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.27042677998542786},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.23488053679466248},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1562122106552124},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.12662675976753235},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.08174395561218262}],"concepts":[{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.7645124197006226},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7511509656906128},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5514954328536987},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48015445470809937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40657156705856323},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.3483240306377411},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27042677998542786},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.23488053679466248},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1562122106552124},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.12662675976753235},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.08174395561218262}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057766","descriptor_name":"Policy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057766","descriptor_name":"Policy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057766","descriptor_name":"Policy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1155/2021/5300189","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/5300189","pdf_url":"https://downloads.hindawi.com/journals/cin/2021/5300189.pdf","source":{"id":"https://openalex.org/S72372694","display_name":"Computational Intelligence and Neuroscience","issn_l":"1687-5265","issn":["1687-5265","1687-5273"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Intelligence and Neuroscience","raw_type":"journal-article"},{"id":"pmid:34394336","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34394336","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational intelligence and neuroscience","raw_type":null},{"id":"pmh:oai:doaj.org/article:dc902d43057e4d99a0e70bd4cf7df1e0","is_oa":false,"landing_page_url":"https://doaj.org/article/dc902d43057e4d99a0e70bd4cf7df1e0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Intelligence and Neuroscience, Vol 2021 (2021)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8357468","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8357468","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Comput Intell Neurosci","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1155/2021/5300189","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/5300189","pdf_url":"https://downloads.hindawi.com/journals/cin/2021/5300189.pdf","source":{"id":"https://openalex.org/S72372694","display_name":"Computational Intelligence and Neuroscience","issn_l":"1687-5265","issn":["1687-5265","1687-5273"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Intelligence and Neuroscience","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G201592743","display_name":null,"funder_award_id":"61906198","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G3777148327","display_name":null,"funder_award_id":"BK20190622","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8417803886","display_name":null,"funder_award_id":"61906198","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8481198762","display_name":null,"funder_award_id":"BK20190622","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3187600255.pdf","grobid_xml":"https://content.openalex.org/works/W3187600255.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W341879454","https://openalex.org/W1496929357","https://openalex.org/W1540706608","https://openalex.org/W1771410628","https://openalex.org/W1901616594","https://openalex.org/W2041246019","https://openalex.org/W2050215344","https://openalex.org/W2056561256","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2151965738","https://openalex.org/W2236741694","https://openalex.org/W2366097241","https://openalex.org/W2372578164","https://openalex.org/W2389483157","https://openalex.org/W2517600007","https://openalex.org/W2541451878","https://openalex.org/W2594726847","https://openalex.org/W2746553466","https://openalex.org/W2796394805","https://openalex.org/W2919115771","https://openalex.org/W2919979744","https://openalex.org/W2982316857","https://openalex.org/W3014974411","https://openalex.org/W4238961266","https://openalex.org/W6629795882","https://openalex.org/W6638018090"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","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":{"The":[0,160],"reinforcement":[1,30,72],"learning":[2,31,73],"algorithms":[3],"based":[4],"on":[5,174],"policy":[6,59,70],"gradient":[7,15,60,116],"may":[8],"fall":[9],"into":[10,150],"local":[11,151],"optimal":[12,152],"due":[13,153],"to":[14,35,65,154,194],"disappearance":[16,156],"during":[17,114],"the":[18,25,29,37,43,78,86,93,96,99,104,111,115,120,124,129,132,138,146,155,158,163,180,183],"update":[19],"process,":[20],"which":[21,141],"in":[22,40,47,95,137,142,162,179],"turn":[23,143],"affects":[24],"exploration":[26],"ability":[27],"of":[28,85,92,107,131,148,157,185],"agent.":[32],"In":[33],"order":[34],"solve":[36],"above":[38],"problem,":[39],"this":[41],"paper,":[42],"cross-entropy":[44],"method":[45],"(CEM)":[46],"evolution":[48],"policy,":[49],"maximum":[50,79],"mean":[51,80],"difference":[52],"(MMD),":[53],"and":[54,103,123],"twin":[55],"delayed":[56],"deep":[57,71],"deterministic":[58],"algorithm":[61],"(TD3)":[62],"are":[63],"combined":[64],"propose":[66],"a":[67,83,189],"diversity":[68,136],"evolutionary":[69],"(DEPRL)":[74],"algorithm.":[75],"By":[76],"using":[77],"discrepancy":[81],"as":[82,128],"measure":[84],"distance":[87,100,125],"between":[88,101,126],"different":[89],"policies,":[90,140],"some":[91],"policies":[94,108,127],"population":[97,133],"maximize":[98],"them":[102],"previous":[105],"generation":[106],"while":[109],"maximizing":[110],"cumulative":[112,121],"return":[113,184],"update.":[117],"Furthermore,":[118],"combining":[119],"returns":[122],"fitness":[130],"encourages":[134],"more":[135],"offspring":[139],"can":[144],"reduce":[145],"risk":[147],"falling":[149],"gradient.":[159],"results":[161],"MuJoCo":[164],"test":[165],"environment":[166],"show":[167],"that":[168],"DEPRL":[169,186],"has":[170],"achieved":[171,188],"excellent":[172],"performance":[173],"continuous":[175],"control":[176],"tasks;":[177],"especially":[178],"Ant-v2":[181],"environment,":[182],"ultimately":[187],"nearly":[190],"20%":[191],"improvement":[192],"compared":[193],"TD3.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
