{"id":"https://openalex.org/W4207021493","doi":"https://doi.org/10.1109/ssci50451.2021.9660084","title":"Population based Reinforcement Learning","display_name":"Population based Reinforcement Learning","publication_year":2021,"publication_date":"2021-12-05","ids":{"openalex":"https://openalex.org/W4207021493","doi":"https://doi.org/10.1109/ssci50451.2021.9660084"},"language":"en","primary_location":{"id":"doi:10.1109/ssci50451.2021.9660084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci50451.2021.9660084","pdf_url":null,"source":{"id":"https://openalex.org/S4363604921","display_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5026454220","display_name":"Kyle W. Pretorius","orcid":null},"institutions":[{"id":"https://openalex.org/I69552723","display_name":"University of Pretoria","ror":"https://ror.org/00g0p6g84","country_code":"ZA","type":"education","lineage":["https://openalex.org/I69552723"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Kyle W. Pretorius","raw_affiliation_strings":["University of Pretoria,Department of Computer Science,Pretoria,South Africa"],"affiliations":[{"raw_affiliation_string":"University of Pretoria,Department of Computer Science,Pretoria,South Africa","institution_ids":["https://openalex.org/I69552723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060039893","display_name":"Nelishia Pillay","orcid":"https://orcid.org/0000-0003-3902-5582"},"institutions":[{"id":"https://openalex.org/I69552723","display_name":"University of Pretoria","ror":"https://ror.org/00g0p6g84","country_code":"ZA","type":"education","lineage":["https://openalex.org/I69552723"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Nelishia Pillay","raw_affiliation_strings":["University of Pretoria,Department of Computer Science,Pretoria,South Africa"],"affiliations":[{"raw_affiliation_string":"University of Pretoria,Department of Computer Science,Pretoria,South Africa","institution_ids":["https://openalex.org/I69552723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5026454220"],"corresponding_institution_ids":["https://openalex.org/I69552723"],"apc_list":null,"apc_paid":null,"fwci":0.2513,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53215554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"518","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9993000030517578,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9993000030517578,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9962000250816345,"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":0.9120427370071411},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7474122047424316},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.742778480052948},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7038664221763611},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5538218021392822},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47312992811203003},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.4401381313800812},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4073854386806488},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32720792293548584},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.326571524143219},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12437006831169128}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9120427370071411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7474122047424316},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.742778480052948},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7038664221763611},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5538218021392822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47312992811203003},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.4401381313800812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4073854386806488},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32720792293548584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.326571524143219},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12437006831169128},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","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/ssci50451.2021.9660084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci50451.2021.9660084","pdf_url":null,"source":{"id":"https://openalex.org/S4363604921","display_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1674110665","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2171658832","https://openalex.org/W2257979135","https://openalex.org/W2596367596","https://openalex.org/W2736601468","https://openalex.org/W2778749116","https://openalex.org/W2787938642","https://openalex.org/W2894662639","https://openalex.org/W2906697496","https://openalex.org/W2950854694","https://openalex.org/W2951278471","https://openalex.org/W2951799422","https://openalex.org/W2962887844","https://openalex.org/W2963826726","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W3094215195","https://openalex.org/W3099303207","https://openalex.org/W3121109495","https://openalex.org/W3182043095","https://openalex.org/W4288359891","https://openalex.org/W4394662461","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6735641298","https://openalex.org/W6741002519","https://openalex.org/W6745661885","https://openalex.org/W6746622358","https://openalex.org/W6748839928","https://openalex.org/W6750138292","https://openalex.org/W6755459763","https://openalex.org/W6755903938","https://openalex.org/W6761920647","https://openalex.org/W6780559895","https://openalex.org/W6784509123","https://openalex.org/W6863618527"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4281847915","https://openalex.org/W2602382373","https://openalex.org/W3003615511","https://openalex.org/W4285827128","https://openalex.org/W3198113463","https://openalex.org/W2787698406","https://openalex.org/W2963844355","https://openalex.org/W4361251046","https://openalex.org/W98577079"],"abstract_inverted_index":{"Genetic":[0],"algorithms":[1],"have":[2,91],"recently":[3],"seen":[4],"an":[5],"increase":[6],"in":[7,136],"application":[8],"due":[9],"to":[10,75,83],"their":[11],"highly":[12],"scalable":[13,54],"nature.":[14],"Enabling":[15],"more":[16,53],"efficient":[17],"utilization":[18],"of":[19,62,66,95,111,124,149],"processing":[20],"power":[21],"that":[22,37,87,120,146],"has":[23],"become":[24],"readily":[25],"available.":[26],"This":[27,48],"study":[28],"introduces":[29],"Population":[30],"based":[31],"reinforcement":[32,45],"learning":[33,46],"(PBRL),":[34],"a":[35,39,42,109,126],"method":[36],"hybridizes":[38],"GA":[40],"with":[41],"policy":[43,55,67,97,129],"gradient":[44,68,98,130],"algorithm.":[47],"combination":[49],"not":[50,164],"only":[51],"enables":[52],"optimization,":[56],"but":[57],"also":[58,73,133,144],"helps":[59],"mitigate":[60],"some":[61],"the":[63,85,93,96,140,147],"common":[64],"weaknesses":[65],"algorithms.":[69],"Furthermore,":[70],"PBRL":[71,121],"is":[72,81,122,143],"extended":[74],"include":[76],"automatic":[77,150],"hyper-parameter":[78],"tuning,":[79],"which":[80],"used":[82,128],"evaluate":[84],"impact":[86],"such":[88],"tuning":[89,152],"can":[90,153],"on":[92,108],"performance":[94],"algorithm":[99],"being":[100],"used.":[101],"Experiments":[102],"comparing":[103],"these":[104],"methods":[105],"are":[106,163],"conducted":[107],"number":[110],"continuous":[112],"control":[113],"problems":[114],"simulated":[115],"by":[116],"MuJoCo.":[117],"Results":[118],"show":[119],"capable":[123],"outperforming":[125],"commonly":[127],"algorithm,":[131],"while":[132],"producing":[134],"results":[135],"nearly":[137],"one":[138],"fifth":[139],"time.":[141],"It":[142],"observed":[145],"addition":[148],"hyperparameter":[151],"be":[154],"greatly":[155],"beneficial":[156],"for":[157],"environments":[158],"where":[159],"well":[160],"tuned":[161],"hyper-parameters":[162],"known.":[165]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}