{"id":"https://openalex.org/W4290717511","doi":"https://doi.org/10.1109/tnnls.2022.3195357","title":"Model-Free Q-Learning for the Tracking Problem of Linear Discrete-Time Systems","display_name":"Model-Free Q-Learning for the Tracking Problem of Linear Discrete-Time Systems","publication_year":2022,"publication_date":"2022-08-08","ids":{"openalex":"https://openalex.org/W4290717511","doi":"https://doi.org/10.1109/tnnls.2022.3195357","pmid":"https://pubmed.ncbi.nlm.nih.gov/38379236"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3195357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3195357","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/A5057956810","display_name":"Chun Li","orcid":"https://orcid.org/0000-0002-0912-649X"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Li","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-0912-649X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022740106","display_name":"Jinliang Ding","orcid":"https://orcid.org/0000-0003-3735-0672"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinliang Ding","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0003-3735-0672","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","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":["University of Texas at Arlington Research Institute, University of Texas at Arlington, Fort Worth, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-4074-1615","affiliations":[{"raw_affiliation_string":"University of Texas at Arlington Research Institute, University of Texas at Arlington, Fort Worth, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyou Chai","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-4623-1483","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4485,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93522599,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"35","issue":"3","first_page":"3191","last_page":"3201"},"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9635999798774719,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/iterative-learning-control","display_name":"Iterative learning control","score":0.7436118721961975},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6389956474304199},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6365790367126465},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6137082576751709},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5936017036437988},{"id":"https://openalex.org/keywords/precondition","display_name":"Precondition","score":0.526443600654602},{"id":"https://openalex.org/keywords/system-dynamics","display_name":"System dynamics","score":0.48117002844810486},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.45409271121025085},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4520476162433624},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.43128687143325806},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.30892127752304077},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2877008318901062},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16140079498291016}],"concepts":[{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.7436118721961975},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6389956474304199},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6365790367126465},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6137082576751709},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5936017036437988},{"id":"https://openalex.org/C192465680","wikidata":"https://www.wikidata.org/wiki/Q1413450","display_name":"Precondition","level":2,"score":0.526443600654602},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.48117002844810486},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45409271121025085},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4520476162433624},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.43128687143325806},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.30892127752304077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2877008318901062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16140079498291016},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2022.3195357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3195357","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:38379236","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38379236","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/G5789780205","display_name":null,"funder_award_id":"61988101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5925348479","display_name":null,"funder_award_id":"61733005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7394171745","display_name":null,"funder_award_id":"62161160338","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W560518094","https://openalex.org/W1614417283","https://openalex.org/W1969959431","https://openalex.org/W1976956127","https://openalex.org/W1977458621","https://openalex.org/W1983523797","https://openalex.org/W2005437559","https://openalex.org/W2013895638","https://openalex.org/W2139780556","https://openalex.org/W2144456461","https://openalex.org/W2148439597","https://openalex.org/W2165726932","https://openalex.org/W2249513906","https://openalex.org/W2333120204","https://openalex.org/W2430619152","https://openalex.org/W2484646121","https://openalex.org/W2548277951","https://openalex.org/W2585299106","https://openalex.org/W2605603065","https://openalex.org/W2740197008","https://openalex.org/W2768933283","https://openalex.org/W2771641782","https://openalex.org/W2790958326","https://openalex.org/W2884356520","https://openalex.org/W2898521339","https://openalex.org/W2907217398","https://openalex.org/W2912832158","https://openalex.org/W2914172002","https://openalex.org/W2921889099","https://openalex.org/W2999863957","https://openalex.org/W3000451313","https://openalex.org/W3035621227","https://openalex.org/W3036186095","https://openalex.org/W3037849017","https://openalex.org/W3049644873","https://openalex.org/W3101006515","https://openalex.org/W3114263192","https://openalex.org/W3128521811","https://openalex.org/W3155402581","https://openalex.org/W3156587271","https://openalex.org/W3163501229","https://openalex.org/W3214717328","https://openalex.org/W4206037914","https://openalex.org/W4213367573","https://openalex.org/W4239074664"],"related_works":["https://openalex.org/W2294916142","https://openalex.org/W1581362285","https://openalex.org/W1988458526","https://openalex.org/W2953046944","https://openalex.org/W2185407019","https://openalex.org/W2368102490","https://openalex.org/W2367100904","https://openalex.org/W2043058420","https://openalex.org/W2356674317","https://openalex.org/W2151337373"],"abstract_inverted_index":{"In":[0,82,132],"this":[1],"article,":[2],"a":[3,27,43,63,68,152,207],"model-free":[4],"Q-learning":[5,32,56],"algorithm":[6,203],"is":[7,34,191,204],"proposed":[8,59,106,137,195,202],"to":[9,76,177,182],"solve":[10],"the":[11,31,39,48,58,72,77,90,93,100,105,117,121,124,128,136,139,147,155,159,166,184,188,194,198,201],"tracking":[12,25,40,74,130,161,172],"problem":[13,41],"of":[14,30,67,89,92,120,135,154,200],"linear":[15],"discrete-time":[16],"systems":[17],"with":[18,47],"completely":[19],"unknown":[20],"system":[21,96,122,157],"dynamics.":[22],"To":[23],"eliminate":[24,171],"errors,":[26],"performance":[28,60],"index":[29,61],"approach":[33,107,190],"formulated,":[35],"which":[36,163],"can":[37,108,143,170],"transform":[38],"into":[42,193],"regulation":[44],"one.":[45],"Compared":[46],"existing":[49],"adaptive":[50],"dynamic":[51],"programming":[52],"(ADP)":[53],"methods":[54],"and":[55,71,97,127,158],"approaches,":[57],"adds":[62],"product":[64],"term":[65],"composed":[66],"gain":[69],"matrix":[70],"reference":[73,129,160],"trajectory":[75],"control":[78,101,125,141,168,186],"input":[79,142],"quadratic":[80],"form.":[81],"addition,":[83],"without":[84],"requiring":[85],"any":[86],"prior":[87],"knowledge":[88],"dynamics":[91],"original":[94],"controlled":[95,156],"command":[98],"generator,":[99],"policy":[102,169],"obtained":[103,167],"by":[104,111,146,206],"be":[109,144],"deduced":[110],"an":[112],"iterative":[113,148],"technique":[114],"relying":[115],"on":[116],"online":[118],"information":[119],"state,":[123],"input,":[126],"trajectory.":[131],"each":[133],"iteration":[134],"method,":[138],"desired":[140],"updated":[145],"criteria":[149],"derived":[150],"from":[151],"precondition":[153],"trajectory,":[162],"ensures":[164],"that":[165],"errors":[173],"in":[174],"theory.":[175],"Moreover,":[176],"effectively":[178],"use":[179],"less":[180],"data":[181],"obtain":[183],"optimal":[185],"policy,":[187],"off-policy":[189],"introduced":[192],"algorithm.":[196],"Finally,":[197],"effectiveness":[199],"verified":[205],"numerical":[208],"simulation.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}