{"id":"https://openalex.org/W3085531353","doi":"https://doi.org/10.1109/tnnls.2020.3017461","title":"Off-Policy Reinforcement Learning for Tracking in Continuous-Time Systems on Two Time Scales","display_name":"Off-Policy Reinforcement Learning for Tracking in Continuous-Time Systems on Two Time Scales","publication_year":2020,"publication_date":"2020-09-09","ids":{"openalex":"https://openalex.org/W3085531353","doi":"https://doi.org/10.1109/tnnls.2020.3017461","mag":"3085531353","pmid":"https://pubmed.ncbi.nlm.nih.gov/32903187"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2020.3017461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3017461","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5102973745","display_name":"Wenqian Xue","orcid":"https://orcid.org/0000-0002-3670-3854"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]},{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenqian Xue","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033960992","display_name":"Jialu Fan","orcid":"https://orcid.org/0000-0001-7585-1166"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]},{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialu Fan","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059736491","display_name":"Victor G. Lopez","orcid":"https://orcid.org/0000-0003-3989-4091"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victor G. Lopez","raw_affiliation_strings":["UTA Research Institute, The University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"UTA Research Institute, The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396295","display_name":"Yi Jiang","orcid":"https://orcid.org/0000-0001-8927-0119"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]},{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Jiang","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042520521","display_name":"Tianyou Chai","orcid":"https://orcid.org/0000-0002-4623-1483"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]},{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyou Chai","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["UTA Research Institute, The University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"UTA Research Institute, The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102973745"],"corresponding_institution_ids":["https://openalex.org/I4391767858","https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":4.3317,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.95379582,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"32","issue":"10","first_page":"4334","last_page":"4346"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9986000061035156,"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":0.9986000061035156,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9921000003814697,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9739999771118164,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.6900767087936401},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6492831110954285},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5928894281387329},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.5298027396202087},{"id":"https://openalex.org/keywords/singular-perturbation","display_name":"Singular perturbation","score":0.5131483674049377},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4783869981765747},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.4627779424190521},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.4621385633945465},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.43069958686828613},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4277758002281189},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.426264226436615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42071208357810974},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41800838708877563},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.40634265542030334},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.374655544757843},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.27643659710884094},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1725980043411255},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.12024649977684021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1172545850276947},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08491918444633484}],"concepts":[{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.6900767087936401},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6492831110954285},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5928894281387329},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.5298027396202087},{"id":"https://openalex.org/C165160513","wikidata":"https://www.wikidata.org/wiki/Q7524249","display_name":"Singular perturbation","level":2,"score":0.5131483674049377},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4783869981765747},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.4627779424190521},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.4621385633945465},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.43069958686828613},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4277758002281189},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.426264226436615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42071208357810974},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41800838708877563},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.40634265542030334},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.374655544757843},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.27643659710884094},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1725980043411255},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.12024649977684021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1172545850276947},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08491918444633484},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2020.3017461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3017461","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:32903187","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32903187","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1460833335","display_name":null,"funder_award_id":"61533015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3474679019","display_name":null,"funder_award_id":"61991400","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4867859608","display_name":null,"funder_award_id":"61991403","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5409562055","display_name":null,"funder_award_id":"B08015","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"},{"id":"https://openalex.org/G5898287775","display_name":null,"funder_award_id":"61991404","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/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W92805021","https://openalex.org/W1515224583","https://openalex.org/W1614417283","https://openalex.org/W1972243698","https://openalex.org/W1972809999","https://openalex.org/W1983523797","https://openalex.org/W2005437559","https://openalex.org/W2010740413","https://openalex.org/W2013895638","https://openalex.org/W2014157641","https://openalex.org/W2024303516","https://openalex.org/W2037025184","https://openalex.org/W2060364523","https://openalex.org/W2081514674","https://openalex.org/W2109400094","https://openalex.org/W2113501460","https://openalex.org/W2121832485","https://openalex.org/W2121863487","https://openalex.org/W2134672787","https://openalex.org/W2140013405","https://openalex.org/W2148437632","https://openalex.org/W2148439597","https://openalex.org/W2151966330","https://openalex.org/W2314233559","https://openalex.org/W2321292752","https://openalex.org/W2524958680","https://openalex.org/W2754615637","https://openalex.org/W2762709466","https://openalex.org/W2771641782","https://openalex.org/W2772589676","https://openalex.org/W2884730950","https://openalex.org/W2885522335","https://openalex.org/W2890158047","https://openalex.org/W2913981879","https://openalex.org/W2946449871","https://openalex.org/W2966813522","https://openalex.org/W2968532797","https://openalex.org/W2982527115","https://openalex.org/W3036618640","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W6678518843"],"related_works":["https://openalex.org/W150609566","https://openalex.org/W2011339542","https://openalex.org/W2055379029","https://openalex.org/W2482034469","https://openalex.org/W2387203662","https://openalex.org/W2332818190","https://openalex.org/W1520410026","https://openalex.org/W2203843426","https://openalex.org/W2049369111","https://openalex.org/W839375016"],"abstract_inverted_index":{"This":[0],"article":[1],"applies":[2],"a":[3,16,40,50,119,127,135],"singular":[4,21],"perturbation":[5,22],"theory":[6],"to":[7,64,126],"solve":[8],"an":[9,114],"optimal":[10],"linear":[11],"quadratic":[12],"tracker":[13,42],"problem":[14,35,44,54],"for":[15,25,45,55],"continuous-time":[17],"two-time-scale":[18,33],"process.":[19],"Previously,":[20],"was":[23],"applied":[24],"system":[26,48,132],"regulation.":[27],"It":[28],"is":[29],"shown":[30],"that":[31,61],"the":[32,46,56,62,72,76,102,106,109,130],"tracking":[34],"can":[36,70],"be":[37],"separated":[38],"into":[39],"linear-quadratic":[41,51],"(LQT)":[43],"slow":[47,82],"and":[49,84,122,134],"regulator":[52],"(LQR)":[53],"fast":[57,85],"system.":[58,103],"We":[59],"prove":[60],"solutions":[63],"these":[65],"two":[66],"reduced-order":[67,81],"control":[68,78,87],"problems":[69,88],"approximate":[71],"LQT":[73,83],"solution":[74],"of":[75,108],"original":[77],"problem.":[79],"The":[80],"LQR":[86],"are":[89],"solved":[90],"by":[91],"off-policy":[92],"integral":[93],"reinforcement":[94],"learning":[95],"(IRL)":[96],"using":[97],"only":[98],"measured":[99],"data":[100],"from":[101],"To":[104],"test":[105],"effectiveness":[107],"proposed":[110],"method,":[111],"we":[112],"use":[113],"industrial":[115],"thickening":[116],"process":[117],"as":[118],"simulation":[120],"example":[121],"compare":[123],"our":[124],"method":[125,128,136],"with":[129],"known":[131],"model":[133],"without":[137],"time-scale":[138],"separation.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}