{"id":"https://openalex.org/W3089472105","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207570","title":"Maximum Entropy Reinforcement Learning with Evolution Strategies","display_name":"Maximum Entropy Reinforcement Learning with Evolution Strategies","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3089472105","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207570","mag":"3089472105"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.lib.uts.edu.au/bitstream/10453/147810/3/2DAE8B16-91EC-4D0A-A30E-6F996F2A7790%20%20%20am%20Combined%20.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085669660","display_name":"Longxiang Shi","orcid":"https://orcid.org/0000-0003-4334-1182"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Longxiang Shi","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103196339","display_name":"Shijian Li","orcid":"https://orcid.org/0000-0001-5846-3065"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijian Li","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100610894","display_name":"Zheng Qian","orcid":"https://orcid.org/0000-0002-2657-6361"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qian Zheng","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000798681","display_name":"Longbing Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Longbing Cao","raw_affiliation_strings":["Advanced Analytics Institute, University of Technology Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Advanced Analytics Institute, University of Technology Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069283448","display_name":"Yang Long","orcid":"https://orcid.org/0000-0001-7600-3396"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Yang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084291326","display_name":"Gang Pan","orcid":"https://orcid.org/0000-0002-4049-6181"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Pan","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5085669660"],"corresponding_institution_ids":["https://openalex.org/I168879160"],"apc_list":null,"apc_paid":null,"fwci":0.8155,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79457384,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9966999888420105,"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":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9056607484817505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6613696813583374},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.655684232711792},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5947009325027466},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5772845149040222},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5648442506790161},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5504148006439209},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5064531564712524},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4960401952266693},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.4494568407535553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4464617371559143},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3445334732532501},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23957234621047974},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23579543828964233}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9056607484817505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6613696813583374},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.655684232711792},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5947009325027466},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5772845149040222},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5648442506790161},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5504148006439209},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5064531564712524},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4960401952266693},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.4494568407535553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4464617371559143},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3445334732532501},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23957234621047974},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23579543828964233},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/147810","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/147810","pdf_url":"https://opus.lib.uts.edu.au/bitstream/10453/147810/3/2DAE8B16-91EC-4D0A-A30E-6F996F2A7790%20%20%20am%20Combined%20.pdf","source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:opus.lib.uts.edu.au:10453/147810","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/147810","pdf_url":"https://opus.lib.uts.edu.au/bitstream/10453/147810/3/2DAE8B16-91EC-4D0A-A30E-6F996F2A7790%20%20%20am%20Combined%20.pdf","source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G199942753","display_name":null,"funder_award_id":"2017YFB1002503","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3775886161","display_name":null,"funder_award_id":"61925603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G466649759","display_name":null,"funder_award_id":"2017Y","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7429600474","display_name":null,"funder_award_id":"2017YFB1","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8340078520","display_name":null,"funder_award_id":"2017YF","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8823009050","display_name":null,"funder_award_id":"2017YFB","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3089472105.pdf","grobid_xml":"https://content.openalex.org/works/W3089472105.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W64088143","https://openalex.org/W181733065","https://openalex.org/W1771410628","https://openalex.org/W2000191307","https://openalex.org/W2012392077","https://openalex.org/W2012587148","https://openalex.org/W2098774185","https://openalex.org/W2104733512","https://openalex.org/W2107464055","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2137104525","https://openalex.org/W2149479912","https://openalex.org/W2155007355","https://openalex.org/W2155772159","https://openalex.org/W2158782408","https://openalex.org/W2167117957","https://openalex.org/W2173248099","https://openalex.org/W2594103415","https://openalex.org/W2596367596","https://openalex.org/W2767002724","https://openalex.org/W2778749116","https://openalex.org/W2781726626","https://openalex.org/W2785542505","https://openalex.org/W2787938642","https://openalex.org/W2890326782","https://openalex.org/W2891563122","https://openalex.org/W2894662639","https://openalex.org/W2898585845","https://openalex.org/W2904998808","https://openalex.org/W2949561945","https://openalex.org/W2951226321","https://openalex.org/W2951799422","https://openalex.org/W2963537813","https://openalex.org/W2963849886","https://openalex.org/W2963864421","https://openalex.org/W2964161785","https://openalex.org/W3030498244","https://openalex.org/W4205513846","https://openalex.org/W4288418822","https://openalex.org/W4293415974","https://openalex.org/W4294206209","https://openalex.org/W6638018090","https://openalex.org/W6653435097","https://openalex.org/W6674884181","https://openalex.org/W6675999342","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6734517396","https://openalex.org/W6735641298","https://openalex.org/W6740471745","https://openalex.org/W6745515306","https://openalex.org/W6746622358","https://openalex.org/W6747473740","https://openalex.org/W6748398410","https://openalex.org/W6748839928","https://openalex.org/W6750322874","https://openalex.org/W6754109048","https://openalex.org/W6754787993","https://openalex.org/W6755459763","https://openalex.org/W6755903938","https://openalex.org/W6763761074","https://openalex.org/W6764808195","https://openalex.org/W6780559895","https://openalex.org/W6903351479"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2130703626","https://openalex.org/W4312713068","https://openalex.org/W3041490575","https://openalex.org/W2970690932","https://openalex.org/W4321135767"],"abstract_inverted_index":{"Evolution":[0],"strategies":[1,24,94],"(ES)":[2],"have":[3],"recently":[4],"raised":[5],"attention":[6],"in":[7,46,61,130,147],"solving":[8,62],"challenging":[9],"tasks":[10],"with":[11,92],"low":[12,31],"computation":[13],"costs":[14],"and":[15,43,95,125,142],"high":[16,136],"scalability.":[17],"However,":[18],"it":[19],"is":[20,50,123],"well-known":[21,159],"that":[22],"evolution":[23,93,114],"reinforcement":[25,90],"learning":[26,91],"(RL)":[27],"methods":[28,37,60,154],"suffer":[29],"from":[30],"stability.":[32],"Without":[33],"careful":[34],"consideration,":[35],"ES":[36,59,74],"are":[38,44],"sensitive":[39],"to":[40,76,85],"local":[41],"optima":[42],"unstable":[45],"learning.":[47,79],"Therefore,":[48],"there":[49],"an":[51,97],"urgent":[52],"need":[53],"for":[54,102,127],"improving":[55],"the":[56,78,87,119,158],"stability":[57,137],"of":[58,157],"RL":[63,153],"problems.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68,81],"propose":[69,82],"a":[70,83,108],"simple":[71],"yet":[72],"efficient":[73,98,124],"method":[75,101],"stabilize":[77],"Specifically,":[80],"framework":[84],"incorporate":[86],"maximum":[88,112],"entropy":[89,99,113],"derive":[96],"calculation":[100],"linear":[103],"policies.":[104],"We":[105],"further":[106],"present":[107],"practical":[109],"algorithm":[110,134],"called":[111],"policy":[115,128],"search":[116,129],"based":[117],"on":[118,155],"proposed":[120],"framework,":[121],"which":[122],"stable":[126],"continuous":[131],"control.":[132],"Our":[133],"shows":[135],"across":[138],"different":[139],"random":[140],"seeds":[141],"can":[143],"obtain":[144],"comparable":[145],"results":[146],"performance":[148],"against":[149],"some":[150],"existing":[151],"derivative-free":[152],"several":[156],"benchmark":[160],"MuJoCo":[161],"robotic":[162],"control":[163],"tasks.":[164]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}