{"id":"https://openalex.org/W4401414841","doi":"https://doi.org/10.1109/cec60901.2024.10611794","title":"A Reinforcement Learning Method Based on Natural Evolution Strategies","display_name":"A Reinforcement Learning Method Based on Natural Evolution Strategies","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4401414841","doi":"https://doi.org/10.1109/cec60901.2024.10611794"},"language":"en","primary_location":{"id":"doi:10.1109/cec60901.2024.10611794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec60901.2024.10611794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Congress on Evolutionary Computation (CEC)","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/A5110794793","display_name":"Koki Kimura","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Koki Kimura","raw_affiliation_strings":["Tokyo Institute of Technology,Yokohama,Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology,Yokohama,Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085725359","display_name":"Isao Ono","orcid":"https://orcid.org/0009-0008-2110-9853"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Isao Ono","raw_affiliation_strings":["Tokyo Institute of Technology,Yokohama,Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology,Yokohama,Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110794793"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65441898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"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":0.9926000237464905,"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":0.9909999966621399,"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":0.7880004644393921},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6979888081550598},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5540934801101685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45385369658470154},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41051578521728516},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12463533878326416},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09546405076980591}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7880004644393921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6979888081550598},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5540934801101685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45385369658470154},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41051578521728516},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12463533878326416},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09546405076980591},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cec60901.2024.10611794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec60901.2024.10611794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Congress on Evolutionary Computation (CEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1994286308","https://openalex.org/W2136495462","https://openalex.org/W2158782408","https://openalex.org/W2166160300","https://openalex.org/W2171677813","https://openalex.org/W2596367596","https://openalex.org/W2736601468","https://openalex.org/W2890326782","https://openalex.org/W2963864421","https://openalex.org/W3034606848","https://openalex.org/W3127770912","https://openalex.org/W3198249268","https://openalex.org/W4297964528","https://openalex.org/W4377695283","https://openalex.org/W6638018090","https://openalex.org/W6684921986","https://openalex.org/W6735641298","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6750322874","https://openalex.org/W6754787993"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,128,173],"reinforcement":[4],"learning":[5],"(RL)":[6],"method":[7,132,175,207,227,266],"based":[8],"on":[9,79],"Natural":[10],"Evolution":[11],"Strategies":[12],"(NES).":[13],"In":[14,138,158,223],"RL,":[15],"an":[16,19,33,231,268],"agent":[17],"learns":[18],"action":[20],"strategy":[21],"(policy)":[22],"that":[23,43,86,95,116,133,204,246],"maximizes":[24],"the":[25,45,59,96,124,142,162,183,187,192,205,216,220,225,250,255,261,264],"expected":[26,46],"cumulative":[27,47],"reward":[28,48,233,270],"by":[29],"repeatedly":[30],"interacting":[31],"with":[32,70,107,176],"environment.":[34],"Derivative-Free":[35],"(DFO)-based":[36],"RL":[37,63,72,131],"methods":[38,73],"search":[39],"for":[40],"policy":[41],"parameters":[42,121],"maximize":[44],"using":[49,198],"DFO":[50,174],"methods.":[51,64],"Augmented":[52],"Random":[53],"Search":[54],"(ARS)":[55],"is":[56,94,115,247],"one":[57,248],"of":[58,98,110,145,153,156,182,234,249,271],"most":[60,251],"promising":[61],"DFO-based":[62,130],"ARS":[65,87,102,117,209,238],"reportedly":[66],"showed":[67,203,214],"competitive":[68],"results":[69],"state-of-the-art":[71],"such":[74],"as":[75,172],"PPO":[76],"and":[77,191,213],"SAC":[78],"MuJoCo":[80,200,256],"locomotion":[81,201,257],"tasks.":[82],"However,":[83],"we":[84,147,165],"believe":[85],"has":[88,118],"two":[89,136],"problems.":[90,137],"The":[91,112],"first":[92,143],"problem":[93,114,144],"performance":[97,218],"state":[99,149],"normalization":[100,150],"in":[101,105,210,219,229,241,244,254,260],"could":[103],"deteriorate":[104],"environments":[106],"early":[108,154],"termination":[109,155],"episodes.":[111,157],"second":[113],"many":[119],"user":[120,163],"sensitive":[122],"to":[123,140,160,167],"performance.":[125],"We":[126],"propose":[127,148,166],"new":[129],"addresses":[134],"these":[135],"order":[139,159],"address":[141],"ARS,":[146],"taking":[151],"account":[152],"reduce":[161],"parameters,":[164],"employ":[168],"Exponential":[169],"NES":[170],"(xNES)":[171],"three":[177],"techniques:":[178],"controlling":[179],"excessive":[180],"shrinkage":[181],"step":[184],"size,":[185],"fixing":[186],"normalized":[188],"transformation":[189],"matrix,":[190],"antithetic":[193],"variates":[194],"method.":[195],"Numerical":[196],"experiments":[197],"six":[199],"tasks":[202,212,253],"proposed":[206,226,265],"outperformed":[208],"five":[211],"almost":[215],"same":[217,262],"other":[221],"task.":[222],"particular,":[224],"succeeded":[228],"achieving":[230],"average":[232,269],"about":[235,239,273],"9,500":[236],"while":[237],"6,000":[240,272],"400,000":[242],"episodes":[243],"Humanoid-v4":[245],"difficult":[252],"ones.":[258],"Furthermore,":[259],"task,":[263],"reached":[267],"four":[274],"times":[275],"faster":[276],"than":[277],"ARS.":[278]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}