{"id":"https://openalex.org/W7117745245","doi":"https://doi.org/10.1109/tase.2025.3649942","title":"Evolution-Guided Q-Learning for Optimal Regulation of Unknown Continuous-Time Systems","display_name":"Evolution-Guided Q-Learning for Optimal Regulation of Unknown Continuous-Time Systems","publication_year":2025,"publication_date":"2025-12-31","ids":{"openalex":"https://openalex.org/W7117745245","doi":"https://doi.org/10.1109/tase.2025.3649942"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2025.3649942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3649942","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-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/A5121621285","display_name":"Ding Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding Wang","raw_affiliation_strings":["School of Information Science and Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing Laboratory of Smart Environmental Protection, and Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7149-5712","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing Laboratory of Smart Environmental Protection, and Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111328634","display_name":"Qinna Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinna Hu","raw_affiliation_strings":["School of Information Science and Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing Laboratory of Smart Environmental Protection, and Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing Laboratory of Smart Environmental Protection, and Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050909116","display_name":"Zeqiang Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeqiang Yuan","raw_affiliation_strings":["School of Information Science and Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing Laboratory of Smart Environmental Protection, and Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing Laboratory of Smart Environmental Protection, and Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121687909","display_name":"Ao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ao Liu","raw_affiliation_strings":["School of Information Science and Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing Laboratory of Smart Environmental Protection, and Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing Laboratory of Smart Environmental Protection, and Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121689211","display_name":"Junfei Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfei Qiao","raw_affiliation_strings":["School of Information Science and Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing Laboratory of Smart Environmental Protection, and Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0950-7900","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing Laboratory of Smart Environmental Protection, and Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0909,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86073732,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"23","issue":null,"first_page":"2035","last_page":"2044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9891999959945679,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9891999959945679,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0038999998942017555,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.00139999995008111,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7153000235557556},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.6198999881744385},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.5831000208854675},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.47609999775886536},{"id":"https://openalex.org/keywords/premature-convergence","display_name":"Premature convergence","score":0.4390000104904175},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.41429999470710754},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.38420000672340393}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7153000235557556},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.7106000185012817},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.6198999881744385},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.5831000208854675},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5457000136375427},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C58758708","wikidata":"https://www.wikidata.org/wiki/Q7240233","display_name":"Premature convergence","level":3,"score":0.4390000104904175},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3357999920845032},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2025.3649942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3649942","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5101017355918884,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1638800125","display_name":null,"funder_award_id":"62473012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3929591211","display_name":null,"funder_award_id":"62021003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4217685252","display_name":null,"funder_award_id":"Grant 2021ZD0112302","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G4553196225","display_name":null,"funder_award_id":"62222301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G679485329","display_name":null,"funder_award_id":"2021ZD0112302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G890763551","display_name":null,"funder_award_id":"2021ZD0112301","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"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1662782209","https://openalex.org/W1988523476","https://openalex.org/W1991927580","https://openalex.org/W2059025276","https://openalex.org/W2081514674","https://openalex.org/W2145339207","https://openalex.org/W2249513906","https://openalex.org/W2314983263","https://openalex.org/W2885582368","https://openalex.org/W2955358943","https://openalex.org/W3036186095","https://openalex.org/W3038828093","https://openalex.org/W3105407549","https://openalex.org/W3196262453","https://openalex.org/W3204719635","https://openalex.org/W3205613298","https://openalex.org/W4200329055","https://openalex.org/W4205172873","https://openalex.org/W4205939747","https://openalex.org/W4214821607","https://openalex.org/W4283727098","https://openalex.org/W4295832240","https://openalex.org/W4315648720","https://openalex.org/W4319996361","https://openalex.org/W4377145631","https://openalex.org/W4377224182","https://openalex.org/W4385732480","https://openalex.org/W4385833430","https://openalex.org/W4388087652","https://openalex.org/W4388579564","https://openalex.org/W4389262616","https://openalex.org/W4391326570","https://openalex.org/W4392173832","https://openalex.org/W4396629508","https://openalex.org/W4396780859","https://openalex.org/W4400579206","https://openalex.org/W4403058898","https://openalex.org/W4403579936","https://openalex.org/W4404237407","https://openalex.org/W4407128815","https://openalex.org/W4407212638","https://openalex.org/W4407366786","https://openalex.org/W4408971077","https://openalex.org/W4409581531","https://openalex.org/W4413978352"],"related_works":[],"abstract_inverted_index":{"In":[0],"practical":[1],"applications,":[2],"it":[3],"is":[4,29,51,69,86,120],"challenging":[5],"to":[6,34,71,88,106],"obtain":[7],"accurate":[8],"system":[9,60],"models,":[10],"which":[11],"limits":[12],"the":[13,36,45,48,58,63,94,112,116],"applicability":[14],"of":[15,40,98,111],"model-based":[16],"control":[17],"methods.":[18],"To":[19],"address":[20],"this":[21,32],"issue,":[22],"an":[23,66,79],"evolution-guided":[24],"iterative":[25],"Q-learning":[26,64],"(EIQL)":[27],"approach":[28],"developed":[30,87],"in":[31],"paper":[33],"solve":[35],"optimal":[37],"regulation":[38],"problem":[39],"continuous-time":[41],"(CT)":[42],"systems.":[43],"Incorporating":[44],"data-driven":[46],"mechanism,":[47],"offline":[49],"data-set":[50],"utilized":[52],"for":[53],"learning,":[54],"eliminating":[55],"dependence":[56],"on":[57,122],"exact":[59],"model.":[61],"Within":[62],"structure,":[65],"actor-critic":[67],"framework":[68],"employed":[70],"facilitate":[72],"policy":[73],"improvement":[74],"and":[75,92,109,129],"Q-function":[76],"updating.":[77],"Specifically,":[78],"improved":[80],"particle":[81],"swarm":[82],"optimization":[83],"(PSO)":[84],"algorithm":[85],"mitigate":[89],"gradient":[90],"vanishing":[91],"overcome":[93],"premature":[95],"convergence":[96,110],"issue":[97],"standard":[99],"PSO.":[100],"Additionally,":[101],"theoretical":[102],"analyses":[103],"are":[104],"conducted":[105],"establish":[107],"monotonicity":[108],"designed":[113],"Q-function.":[114],"Finally,":[115],"constructed":[117],"EIQL":[118],"method":[119],"validated":[121],"real-world":[123],"physical":[124],"systems,":[125],"demonstrating":[126],"its":[127],"effectiveness":[128],"advantages":[130],"over":[131],"conventional":[132],"approaches.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-31T00:00:00"}