{"id":"https://openalex.org/W2890158047","doi":"https://doi.org/10.1109/tac.2018.2869462","title":"Dynamic Multiobjective Control for Continuous-Time Systems Using Reinforcement Learning","display_name":"Dynamic Multiobjective Control for Continuous-Time Systems Using Reinforcement Learning","publication_year":2018,"publication_date":"2018-09-21","ids":{"openalex":"https://openalex.org/W2890158047","doi":"https://doi.org/10.1109/tac.2018.2869462","mag":"2890158047"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2018.2869462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2018.2869462","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","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/A5059736491","display_name":"Victor G. Lopez","orcid":"https://orcid.org/0000-0003-3989-4091"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Victor G. Lopez","raw_affiliation_strings":["UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA"],"affiliations":[{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA"],"affiliations":[{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059736491"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8394,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.9445135,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"64","issue":"7","first_page":"2869","last_page":"2874"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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":0.9998999834060669,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9904000163078308,"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":0.7240830659866333},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.63704514503479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5772214531898499},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.5574679374694824},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.5194689631462097},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4968145191669464},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.489822119474411},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.48956331610679626},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.43462300300598145},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4291676878929138},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4118988811969757},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.40879523754119873},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2461186945438385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11816030740737915}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7240830659866333},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.63704514503479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5772214531898499},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.5574679374694824},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.5194689631462097},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4968145191669464},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.489822119474411},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.48956331610679626},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.43462300300598145},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4291676878929138},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4118988811969757},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40879523754119873},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2461186945438385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11816030740737915},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2018.2869462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2018.2869462","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4707757447","display_name":null,"funder_award_id":"61633007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7019557205","display_name":null,"funder_award_id":"ECCS-1405173","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W625996709","https://openalex.org/W1519369336","https://openalex.org/W1975025656","https://openalex.org/W1977671496","https://openalex.org/W2002260889","https://openalex.org/W2005229381","https://openalex.org/W2018737981","https://openalex.org/W2024303516","https://openalex.org/W2027968610","https://openalex.org/W2050838777","https://openalex.org/W2073990179","https://openalex.org/W2099730985","https://openalex.org/W2108715886","https://openalex.org/W2111166683","https://openalex.org/W2121863487","https://openalex.org/W2337508653","https://openalex.org/W2484646121","https://openalex.org/W2527481402","https://openalex.org/W2570494446","https://openalex.org/W2579592432","https://openalex.org/W2595382639","https://openalex.org/W2798534591","https://openalex.org/W3103506376","https://openalex.org/W3151405456","https://openalex.org/W4214717370","https://openalex.org/W4250589301","https://openalex.org/W4297981016","https://openalex.org/W6675249451"],"related_works":["https://openalex.org/W2090178682","https://openalex.org/W2203843426","https://openalex.org/W4241467429","https://openalex.org/W2001591765","https://openalex.org/W2073147994","https://openalex.org/W1588199609","https://openalex.org/W2384474142","https://openalex.org/W1550055091","https://openalex.org/W2744462909","https://openalex.org/W2049369111"],"abstract_inverted_index":{"This":[0],"paper":[1,27],"presents":[2],"an":[3],"extension":[4],"of":[5,25],"the":[6,26,29,34,49,80,89,101],"reinforcement":[7],"learning":[8],"algorithms":[9],"to":[10,37,66,99],"design":[11],"suboptimal":[12],"control":[13,41,91],"sequences":[14],"for":[15,48,73],"multiple":[16],"performance":[17,51],"functions":[18],"in":[19,70],"continuous-time":[20],"systems.":[21],"The":[22],"first":[23],"part":[24],"provides":[28],"theoretical":[30],"development":[31],"and":[32,93],"studies":[33],"required":[35],"conditions":[36],"obtain":[38],"a":[39,54,95],"state-feedback":[40],"policy":[42,55],"that":[43,60],"achieves":[44],"Pareto":[45],"optimal":[46],"results":[47],"multiobjective":[50,81,96],"vector.":[52],"Then,":[53],"iteration":[56],"algorithm":[57],"is":[58,86],"proposed":[59,90],"takes":[61],"into":[62],"account":[63],"practical":[64],"considerations":[65],"allow":[67],"its":[68],"implementation":[69],"real-time":[71],"applications":[72],"systems":[74],"with":[75],"partially":[76],"unknown":[77],"models.":[78],"Finally,":[79],"linear":[82],"quadratic":[83],"regulator":[84],"problem":[85,104],"solved":[87],"using":[88],"scheme":[92],"employing":[94],"optimization":[97,103],"software":[98],"solve":[100],"static":[102],"at":[105],"each":[106],"iteration.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}