{"id":"https://openalex.org/W2965612550","doi":"https://doi.org/10.24963/ijcai.2019/295","title":"A Restart-based Rank-1 Evolution Strategy for Reinforcement Learning","display_name":"A Restart-based Rank-1 Evolution Strategy for Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965612550","doi":"https://doi.org/10.24963/ijcai.2019/295","mag":"2965612550"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/295","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/295","pdf_url":"https://www.ijcai.org/proceedings/2019/0295.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0295.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100704822","display_name":"Zefeng Chen","orcid":"https://orcid.org/0000-0001-7654-8425"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zefeng Chen","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056123187","display_name":"Yuren Zhou","orcid":"https://orcid.org/0000-0002-0497-0835"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuren Zhou","raw_affiliation_strings":["Engineering Research Institute, Guangzhou College of South China University of Technology","School of Data and Computer Science, Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Research Institute, Guangzhou College of South China University of Technology","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083554243","display_name":"Xiaoyu He","orcid":"https://orcid.org/0000-0003-4460-2460"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-yu He","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017720652","display_name":"Siyu Jiang","orcid":"https://orcid.org/0000-0002-0718-2279"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Jiang","raw_affiliation_strings":["School of Software Engineering, South China University of Technology","School of Data and Computer Science, Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056123187"],"corresponding_institution_ids":["https://openalex.org/I157773358","https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":1.1607,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.84350033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2130","last_page":"2136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9988999962806702,"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":0.9950000047683716,"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":0.9510126709938049},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7245311737060547},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6703351736068726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6281588077545166},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5927209258079529},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5611770153045654},{"id":"https://openalex.org/keywords/evolution-strategy","display_name":"Evolution strategy","score":0.5185161828994751},{"id":"https://openalex.org/keywords/local-optimum","display_name":"Local optimum","score":0.47108352184295654},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4213918447494507},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.41257938742637634},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.23478269577026367},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11684653162956238},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10897600650787354}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9510126709938049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245311737060547},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6703351736068726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6281588077545166},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5927209258079529},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5611770153045654},{"id":"https://openalex.org/C207002847","wikidata":"https://www.wikidata.org/wiki/Q2912857","display_name":"Evolution strategy","level":3,"score":0.5185161828994751},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.47108352184295654},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4213918447494507},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.41257938742637634},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.23478269577026367},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11684653162956238},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10897600650787354},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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:10.24963/ijcai.2019/295","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/295","pdf_url":"https://www.ijcai.org/proceedings/2019/0295.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/295","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/295","pdf_url":"https://www.ijcai.org/proceedings/2019/0295.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3131683276","display_name":null,"funder_award_id":"61673403","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3851559966","display_name":null,"funder_award_id":"61773410","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965612550.pdf","grobid_xml":"https://content.openalex.org/works/W2965612550.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W135283623","https://openalex.org/W1605438009","https://openalex.org/W1674110665","https://openalex.org/W1980287119","https://openalex.org/W1990304494","https://openalex.org/W2038794597","https://openalex.org/W2081547991","https://openalex.org/W2099397840","https://openalex.org/W2112036188","https://openalex.org/W2137104525","https://openalex.org/W2145339207","https://openalex.org/W2166160300","https://openalex.org/W2462548332","https://openalex.org/W2523246573","https://openalex.org/W2596367596","https://openalex.org/W2766293931","https://openalex.org/W2779171599","https://openalex.org/W2779977383","https://openalex.org/W2888451463","https://openalex.org/W2963157343","https://openalex.org/W2963373786","https://openalex.org/W2964025389","https://openalex.org/W4213261160","https://openalex.org/W4214717370","https://openalex.org/W4230563027"],"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/W2962839548","https://openalex.org/W3138923328","https://openalex.org/W2965612550"],"abstract_inverted_index":{"Evolution":[0],"strategies":[1,25,58],"have":[2,6],"been":[3],"demonstrated":[4],"to":[5,10,59,104,134,158],"the":[7,34,41,86,91,96,105,121,124,129,137,153,168,171],"strong":[8],"ability":[9],"roughly":[11],"train":[12],"deep":[13,29],"neural":[14,87],"networks":[15],"and":[16,55,94,128,148],"well":[17],"accomplish":[18],"reinforcement":[19,30,60,82,165],"learning":[20,31,61],"tasks.":[21],"However,":[22],"existing":[23],"evolution":[24,57,79],"designed":[26],"specially":[27],"for":[28,81,164],"only":[32],"involve":[33],"plain":[35],"variants":[36],"which":[37,108],"can":[38],"not":[39],"realize":[40],"adaptation":[42,122],"of":[43,52,113,123,126,139,170],"mutation":[44,92],"strength":[45,93],"or":[46,159],"other":[47],"advanced":[48,54],"techniques.":[49],"The":[50],"research":[51],"applying":[53],"effective":[56],"in":[62,100],"an":[63,110],"efficient":[64],"way":[65,102],"is":[66,109,156],"still":[67],"a":[68,76,101],"gap.":[69],"To":[70],"this":[71,73],"end,":[72],"paper":[74],"proposes":[75],"restart-based":[77],"rank-1":[78],"strategy":[80],"learning.":[83],"When":[84],"training":[85],"network,":[88],"it":[89],"adapts":[90],"updates":[95],"principal":[97],"search":[98],"direction":[99],"similar":[103],"momentum":[106],"method,":[107],"ameliorated":[111],"version":[112],"stochastic":[114],"gradient":[115],"ascent.":[116],"Besides,":[117],"two":[118],"mechanisms,":[119],"i.e.,":[120],"number":[125],"elitists":[127],"restart":[130],"procedure,":[131],"are":[132],"integrated":[133],"deal":[135],"with":[136,161],"issue":[138],"local":[140],"optima.":[141],"Experimental":[142],"results":[143],"on":[144],"classic":[145],"control":[146],"problems":[147],"Atari":[149],"games":[150],"show":[151],"that":[152],"proposed":[154,172],"algorithm":[155],"superior":[157],"competitive":[160],"state-of-the-art":[162],"algorithms":[163],"learning,":[166],"demonstrating":[167],"effectiveness":[169],"algorithm.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}