{"id":"https://openalex.org/W4390481162","doi":"https://doi.org/10.1109/ssci52147.2023.10371875","title":"SIGNRL: A Population-Based Reinforcement Learning Method for Continuous Control","display_name":"SIGNRL: A Population-Based Reinforcement Learning Method for Continuous Control","publication_year":2023,"publication_date":"2023-12-05","ids":{"openalex":"https://openalex.org/W4390481162","doi":"https://doi.org/10.1109/ssci52147.2023.10371875"},"language":"en","primary_location":{"id":"doi:10.1109/ssci52147.2023.10371875","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ssci52147.2023.10371875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5074426023","display_name":"Daniel F. Zambrano-Gutierrez","orcid":"https://orcid.org/0000-0002-8632-4342"},"institutions":[{"id":"https://openalex.org/I98461037","display_name":"Tecnol\u00f3gico de Monterrey","ror":"https://ror.org/03ayjn504","country_code":"MX","type":"education","lineage":["https://openalex.org/I98461037"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Daniel F. Zambrano-Gutierrez","raw_affiliation_strings":["Tecnologico de Monterrey,Monterrey,Mexico,64849"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tecnologico de Monterrey,Monterrey,Mexico,64849","institution_ids":["https://openalex.org/I98461037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093630743","display_name":"Alberto C. Molina-Porras","orcid":null},"institutions":[{"id":"https://openalex.org/I129858807","display_name":"Universidad de Guanajuato","ror":"https://ror.org/058cjye32","country_code":"MX","type":"education","lineage":["https://openalex.org/I129858807"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Alberto C. Molina-Porras","raw_affiliation_strings":["University of Guanajuato,Salamanca,Mexico,36885"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Guanajuato,Salamanca,Mexico,36885","institution_ids":["https://openalex.org/I129858807"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057731762","display_name":"Emmanuel Ovalle-Magallanes","orcid":"https://orcid.org/0000-0002-0689-520X"},"institutions":[{"id":"https://openalex.org/I129858807","display_name":"Universidad de Guanajuato","ror":"https://ror.org/058cjye32","country_code":"MX","type":"education","lineage":["https://openalex.org/I129858807"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Emmanuel Ovalle-Magallanes","raw_affiliation_strings":["University of Guanajuato,Salamanca,Mexico,36885"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Guanajuato,Salamanca,Mexico,36885","institution_ids":["https://openalex.org/I129858807"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040026225","display_name":"Iv\u00e1n Amaya","orcid":"https://orcid.org/0000-0002-8821-7137"},"institutions":[{"id":"https://openalex.org/I98461037","display_name":"Tecnol\u00f3gico de Monterrey","ror":"https://ror.org/03ayjn504","country_code":"MX","type":"education","lineage":["https://openalex.org/I98461037"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Iv\u00e1n Amaya","raw_affiliation_strings":["Tecnologico de Monterrey,Monterrey,Mexico,64849"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tecnologico de Monterrey,Monterrey,Mexico,64849","institution_ids":["https://openalex.org/I98461037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027131130","display_name":"Jos\u00e9 Carlos Ort\u00edz-Bayliss","orcid":"https://orcid.org/0000-0003-3408-2166"},"institutions":[{"id":"https://openalex.org/I98461037","display_name":"Tecnol\u00f3gico de Monterrey","ror":"https://ror.org/03ayjn504","country_code":"MX","type":"education","lineage":["https://openalex.org/I98461037"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 C. Ortiz-Bayliss","raw_affiliation_strings":["Tecnologico de Monterrey,Monterrey,Mexico,64849"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tecnologico de Monterrey,Monterrey,Mexico,64849","institution_ids":["https://openalex.org/I98461037"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043514066","display_name":"Juan Gabriel Avina\u2010Cervantes","orcid":"https://orcid.org/0000-0003-1730-3748"},"institutions":[{"id":"https://openalex.org/I129858807","display_name":"Universidad de Guanajuato","ror":"https://ror.org/058cjye32","country_code":"MX","type":"education","lineage":["https://openalex.org/I129858807"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Juan G. Avina-Cervantes","raw_affiliation_strings":["University of Guanajuato,Salamanca,Mexico,36885"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Guanajuato,Salamanca,Mexico,36885","institution_ids":["https://openalex.org/I129858807"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086193689","display_name":"Jorge M. Cruz\u2010Duarte","orcid":"https://orcid.org/0000-0003-4494-7864"},"institutions":[{"id":"https://openalex.org/I98461037","display_name":"Tecnol\u00f3gico de Monterrey","ror":"https://ror.org/03ayjn504","country_code":"MX","type":"education","lineage":["https://openalex.org/I98461037"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Jorge M. Cruz-Duarte","raw_affiliation_strings":["Tecnologico de Monterrey,Monterrey,Mexico,64849"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tecnologico de Monterrey,Monterrey,Mexico,64849","institution_ids":["https://openalex.org/I98461037"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21495822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"1443","last_page":"1448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9939000010490417,"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":0.9930999875068665,"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":0.9049558639526367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7024620771408081},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6475372910499573},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5817691087722778},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.5618499517440796},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5360522270202637},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4927263557910919},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.477260559797287},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4720761775970459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4630129039287567},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.43290066719055176},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.4222361445426941},{"id":"https://openalex.org/keywords/swarm-intelligence","display_name":"Swarm intelligence","score":0.41511833667755127},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36715614795684814},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15755006670951843}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9049558639526367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024620771408081},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6475372910499573},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5817691087722778},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.5618499517440796},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5360522270202637},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4927263557910919},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.477260559797287},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4720761775970459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4630129039287567},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.43290066719055176},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.4222361445426941},{"id":"https://openalex.org/C119487961","wikidata":"https://www.wikidata.org/wiki/Q863960","display_name":"Swarm intelligence","level":3,"score":0.41511833667755127},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36715614795684814},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15755006670951843},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci52147.2023.10371875","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ssci52147.2023.10371875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G2504829619","display_name":null,"funder_award_id":"FAP 2275","funder_id":"https://openalex.org/F4320323037","funder_display_name":"Instituto Tecnol\u00f3gico y de Estudios Superiores de Monterrey"}],"funders":[{"id":"https://openalex.org/F4320323037","display_name":"Instituto Tecnol\u00f3gico y de Estudios Superiores de Monterrey","ror":"https://ror.org/03ayjn504"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2024390895","https://openalex.org/W2048276781","https://openalex.org/W2091565802","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2275815196","https://openalex.org/W2337611563","https://openalex.org/W2736601468","https://openalex.org/W2778749116","https://openalex.org/W2890776845","https://openalex.org/W2951507724","https://openalex.org/W2963864421","https://openalex.org/W2998069546","https://openalex.org/W3004742136","https://openalex.org/W3023586494","https://openalex.org/W3081530595","https://openalex.org/W4207021493","https://openalex.org/W4233520916","https://openalex.org/W4293027896","https://openalex.org/W4384007786","https://openalex.org/W6684921986","https://openalex.org/W6734206676","https://openalex.org/W6746622358","https://openalex.org/W6780559895","https://openalex.org/W6839369694"],"related_works":["https://openalex.org/W2368605798","https://openalex.org/W2518037665","https://openalex.org/W2348524959","https://openalex.org/W2477036161","https://openalex.org/W2368049389","https://openalex.org/W2384861574","https://openalex.org/W4294565801","https://openalex.org/W2170801710","https://openalex.org/W2952704802","https://openalex.org/W2241084252"],"abstract_inverted_index":{"In":[0,43,75],"engineering":[1],"processes":[2],"that":[3,129],"require":[4],"continuous":[5,142],"control,":[6],"it":[7],"is":[8],"common":[9],"to":[10,55,66,114],"face":[11],"significant":[12],"challenges.":[13],"Addressing":[14],"these":[15],"challenges":[16],"through":[17],"explicit":[18],"modeling":[19],"can":[20],"take":[21],"much":[22],"work":[23],"and":[24,69,79,138],"effort.":[25],"For":[26],"this":[27,41,44],"reason,":[28],"Reinforcement":[29,100],"Learning":[30,101],"(RL)":[31],"has":[32],"gained":[33],"popularity":[34],"as":[35,64,109],"a":[36,95,110],"feasible":[37],"strategy":[38],"for":[39],"solving":[40],"problem.":[42],"context,":[45],"various":[46],"value-based":[47],"methodologies,":[48],"policies,":[49],"or":[50],"combinations":[51],"have":[52],"been":[53],"employed":[54],"obtain":[56],"an":[57],"optimal":[58,117],"learning":[59],"policy.":[60,118],"However,":[61],"problems":[62],"such":[63],"convergence":[65,137],"local":[67],"maxima":[68],"high":[70],"variance":[71,140],"in":[72,82,122,141],"training":[73],"persist.":[74],"addition,":[76],"computational":[77],"time":[78],"cost":[80],"increase":[81],"complex":[83],"environments,":[84],"so":[85],"more":[86],"robust":[87],"RL":[88],"methodologies":[89],"are":[90],"required.":[91],"This":[92],"paper":[93],"proposes":[94],"Swarm":[96,107],"Intelligence":[97],"Guided":[98],"Neural":[99],"(SIGNRL)":[102],"algorithm,":[103],"which":[104],"uses":[105],"Particle":[106],"Optimization":[108],"multi-agent":[111],"parameter":[112],"explorer":[113],"find":[115],"the":[116,123],"Numerical":[119],"results":[120],"obtained":[121],"OpenAI":[124],"Gym":[125],"Cart-Pole":[126],"environment":[127],"show":[128],"SIGNRL,":[130],"with":[131],"its":[132],"gradient-free":[133],"learning,":[134],"exhibits":[135],"good":[136],"lower":[139],"control":[143],"tasks.":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}