{"id":"https://openalex.org/W2462102501","doi":"https://doi.org/10.1109/tnnls.2016.2585520","title":"Model-Free Optimal Tracking Control via Critic-Only Q-Learning","display_name":"Model-Free Optimal Tracking Control via Critic-Only Q-Learning","publication_year":2016,"publication_date":"2016-07-12","ids":{"openalex":"https://openalex.org/W2462102501","doi":"https://doi.org/10.1109/tnnls.2016.2585520","mag":"2462102501","pmid":"https://pubmed.ncbi.nlm.nih.gov/27416608"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2016.2585520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2016.2585520","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/A5012004938","display_name":"Biao Luo","orcid":"https://orcid.org/0000-0002-3353-2586"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Biao Luo","raw_affiliation_strings":["State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004057129","display_name":"Derong Liu","orcid":"https://orcid.org/0000-0003-3715-4778"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Derong Liu","raw_affiliation_strings":["School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074290686","display_name":"Tingwen Huang","orcid":"https://orcid.org/0000-0001-9610-846X"},"institutions":[{"id":"https://openalex.org/I58152225","display_name":"Texas A&M University at Qatar","ror":"https://ror.org/03vb4dm14","country_code":"QA","type":"education","lineage":["https://openalex.org/I58152225","https://openalex.org/I91045830"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Tingwen Huang","raw_affiliation_strings":["Texas A&M University at Qatar, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Texas A&M University at Qatar, Doha, Qatar","institution_ids":["https://openalex.org/I58152225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024549341","display_name":"Ding Wang","orcid":"https://orcid.org/0000-0002-7149-5712"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding Wang","raw_affiliation_strings":["State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012004938"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":37.9955,"has_fulltext":false,"cited_by_count":320,"citation_normalized_percentile":{"value":0.99863744,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"27","issue":"10","first_page":"2134","last_page":"2144"},"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":0.9697999954223633,"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"}},{"id":"https://openalex.org/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9380000233650208,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.6927698850631714},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6747557520866394},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6528103351593018},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6364281177520752},{"id":"https://openalex.org/keywords/tracking-error","display_name":"Tracking error","score":0.5747791528701782},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5641458630561829},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5214840173721313},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5027065277099609},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4989147186279297},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.48561277985572815},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.45168501138687134},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4329744279384613},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.38953882455825806},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.37515681982040405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3108014464378357},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24802762269973755}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6927698850631714},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6747557520866394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6528103351593018},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6364281177520752},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.5747791528701782},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5641458630561829},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5214840173721313},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5027065277099609},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4989147186279297},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.48561277985572815},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45168501138687134},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4329744279384613},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.38953882455825806},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.37515681982040405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3108014464378357},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24802762269973755},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2016.2585520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2016.2585520","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:27416608","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27416608","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":[{"id":"https://metadata.un.org/sdg/16","score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2139553994","display_name":null,"funder_award_id":"61374105","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G560465369","display_name":null,"funder_award_id":"U1501251","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5645280637","display_name":null,"funder_award_id":"NPRP 7-1482-1-278","funder_id":"https://openalex.org/F4320332753","funder_display_name":"Qatar National Research Fund"},{"id":"https://openalex.org/G5871946117","display_name":null,"funder_award_id":"61503377","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5945310063","display_name":null,"funder_award_id":"61273140","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6391760457","display_name":null,"funder_award_id":"61304086","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7163010157","display_name":null,"funder_award_id":"61533017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8230378891","display_name":null,"funder_award_id":"61233001","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/F4320332753","display_name":"Qatar National Research Fund","ror":"https://ror.org/01svaqq28"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":90,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W32403112","https://openalex.org/W560518094","https://openalex.org/W1484010331","https://openalex.org/W1488674906","https://openalex.org/W1559261542","https://openalex.org/W1569512666","https://openalex.org/W1599132769","https://openalex.org/W1600046456","https://openalex.org/W1601081659","https://openalex.org/W1613039631","https://openalex.org/W1614417283","https://openalex.org/W1793264465","https://openalex.org/W1863485266","https://openalex.org/W1912694276","https://openalex.org/W1945133117","https://openalex.org/W1964375638","https://openalex.org/W1968908471","https://openalex.org/W1969959431","https://openalex.org/W1970127232","https://openalex.org/W1972243698","https://openalex.org/W1972809999","https://openalex.org/W1976956127","https://openalex.org/W1982107603","https://openalex.org/W1986864433","https://openalex.org/W1987782754","https://openalex.org/W1988707322","https://openalex.org/W1991927580","https://openalex.org/W1999213690","https://openalex.org/W2003183707","https://openalex.org/W2005437559","https://openalex.org/W2011310556","https://openalex.org/W2011694027","https://openalex.org/W2012451615","https://openalex.org/W2013895638","https://openalex.org/W2014729048","https://openalex.org/W2017570421","https://openalex.org/W2019478222","https://openalex.org/W2020047580","https://openalex.org/W2020688906","https://openalex.org/W2027197837","https://openalex.org/W2027648864","https://openalex.org/W2032704188","https://openalex.org/W2041866840","https://openalex.org/W2045283962","https://openalex.org/W2052305027","https://openalex.org/W2052399669","https://openalex.org/W2052838496","https://openalex.org/W2056657713","https://openalex.org/W2060605484","https://openalex.org/W2060686658","https://openalex.org/W2081758070","https://openalex.org/W2087063454","https://openalex.org/W2089171752","https://openalex.org/W2089904313","https://openalex.org/W2094627939","https://openalex.org/W2097253853","https://openalex.org/W2098035803","https://openalex.org/W2105004188","https://openalex.org/W2107726111","https://openalex.org/W2118458590","https://openalex.org/W2118686230","https://openalex.org/W2120249358","https://openalex.org/W2121196039","https://openalex.org/W2121825831","https://openalex.org/W2121863487","https://openalex.org/W2124477018","https://openalex.org/W2131570030","https://openalex.org/W2132858840","https://openalex.org/W2138131694","https://openalex.org/W2147750403","https://openalex.org/W2148439597","https://openalex.org/W2151966330","https://openalex.org/W2156629001","https://openalex.org/W2158625202","https://openalex.org/W2165726932","https://openalex.org/W2187015862","https://openalex.org/W2211091785","https://openalex.org/W2316629923","https://openalex.org/W2487144912","https://openalex.org/W2489526136","https://openalex.org/W2540288303","https://openalex.org/W2610686804","https://openalex.org/W2767784613","https://openalex.org/W3009585715","https://openalex.org/W4214717370","https://openalex.org/W4233696721","https://openalex.org/W4307347247","https://openalex.org/W6600556750","https://openalex.org/W6635798015"],"related_works":["https://openalex.org/W2996812256","https://openalex.org/W2525543468","https://openalex.org/W2026490863","https://openalex.org/W2366743900","https://openalex.org/W2389929639","https://openalex.org/W2369313712","https://openalex.org/W2380496977","https://openalex.org/W2351548249","https://openalex.org/W2099967431","https://openalex.org/W2360915094"],"abstract_inverted_index":{"Model-free":[0],"control":[1,9,32,51,129],"is":[2,44,68,78,92,106,130,146,167],"an":[3],"important":[4],"and":[5,56,75,159,171],"promising":[6],"topic":[7],"in":[8,16],"fields,":[10],"which":[11,46],"has":[12],"attracted":[13],"extensive":[14],"attention":[15],"the":[17,28,48,60,65,72,87,89,96,100,103,109,117,122,125,134,139,142,173],"past":[18],"few":[19],"years.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"aim":[25],"to":[26,94,169],"solve":[27],"model-free":[29],"optimal":[30,49,127],"tracking":[31,50,61,128],"problem":[33],"of":[34,102,111,141],"nonaffine":[35],"nonlinear":[36],"discrete-time":[37],"systems.":[38],"A":[39],"critic-only":[40,163],"Q-learning":[41,66,97],"(CoQL)":[42],"method":[43,91,105,145,154],"developed,":[45],"learns":[47,155],"from":[52,121],"real":[53],"system":[54],"data,":[55],"thus":[57,165],"avoids":[58],"solving":[59],"Hamilton-Jacobi-Bellman":[62],"equation.":[63],"First,":[64],"algorithm":[67],"proposed":[69],"based":[70,132],"on":[71,133],"augmented":[73],"system,":[74],"its":[76],"convergence":[77,101],"established.":[79],"Using":[80],"only":[81],"one":[82],"neural":[83,112],"network":[84,113],"for":[85],"approximating":[86],"Q-function,":[88],"CoQL":[90,104,123,144,153],"developed":[93,143,152],"implement":[95],"algorithm.":[98],"Furthermore,":[99],"proved":[107],"with":[108,156,161],"consideration":[110],"approximation":[114],"error.":[115],"With":[116],"convergent":[118],"Q-function":[119],"obtained":[120],"method,":[124],"adaptive":[126],"designed":[131],"gradient":[135],"descent":[136],"scheme.":[137],"Finally,":[138],"effectiveness":[140],"demonstrated":[147],"through":[148],"simulation":[149],"studies.":[150],"The":[151],"off-policy":[157],"data":[158],"implements":[160],"a":[162],"structure,":[164],"it":[166],"easy":[168],"realize":[170],"overcome":[172],"inadequate":[174],"exploration":[175],"problem.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":34},{"year":2022,"cited_by_count":33},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":46},{"year":2019,"cited_by_count":43},{"year":2018,"cited_by_count":34},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}