{"id":"https://openalex.org/W4393207142","doi":"https://doi.org/10.1109/tnnls.2024.3379207","title":"Optimal Learning Output Tracking Control: A Model-Free Policy Optimization Method With Convergence Analysis","display_name":"Optimal Learning Output Tracking Control: A Model-Free Policy Optimization Method With Convergence Analysis","publication_year":2024,"publication_date":"2024-03-26","ids":{"openalex":"https://openalex.org/W4393207142","doi":"https://doi.org/10.1109/tnnls.2024.3379207","pmid":"https://pubmed.ncbi.nlm.nih.gov/38530722"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3379207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3379207","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/A5050013410","display_name":"Mingduo Lin","orcid":"https://orcid.org/0000-0002-7456-2183"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingduo Lin","raw_affiliation_strings":["School of Systems Science, Beijing Normal University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Systems Science, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074387543","display_name":"Bo Zhao","orcid":"https://orcid.org/0000-0002-7684-7342"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]},{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zhao","raw_affiliation_strings":["School of Systems Science, Beijing Normal University, Beijing, China","Ministry of Education, Key Laboratory of Industrial Internet of Things and Networked Control, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Systems Science, Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]},{"raw_affiliation_string":"Ministry of Education, Key Laboratory of Industrial Internet of Things and Networked Control, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004057129","display_name":"Derong Liu","orcid":"https://orcid.org/0000-0003-3715-4778"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Derong Liu","raw_affiliation_strings":["School of System Design and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen, China","Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"School of System Design and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050013410"],"corresponding_institution_ids":["https://openalex.org/I25254941"],"apc_list":null,"apc_paid":null,"fwci":2.6703,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90321862,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"36","issue":"3","first_page":"5574","last_page":"5585"},"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":0.961899995803833,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9513999819755554,"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":0.8536345958709717},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6795225143432617},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.6564423441886902},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6517540812492371},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6471103429794312},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5779518485069275},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5722975134849548},{"id":"https://openalex.org/keywords/iterative-learning-control","display_name":"Iterative learning control","score":0.5712292194366455},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5600641965866089},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5032755732536316},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.43756601214408875},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42115119099617004},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4199589788913727},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.39771634340286255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3039482533931732},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24278250336647034},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24257498979568481},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16833972930908203}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8536345958709717},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6795225143432617},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.6564423441886902},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6517540812492371},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6471103429794312},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5779518485069275},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5722975134849548},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.5712292194366455},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5600641965866089},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5032755732536316},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.43756601214408875},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42115119099617004},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4199589788913727},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.39771634340286255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3039482533931732},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24278250336647034},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24257498979568481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16833972930908203},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3379207","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3379207","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:38530722","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38530722","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/G3554015320","display_name":null,"funder_award_id":"4212038","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G6927519788","display_name":null,"funder_award_id":"61973330","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8816108514","display_name":null,"funder_award_id":"62073085","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/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W181733065","https://openalex.org/W1968908471","https://openalex.org/W1972243698","https://openalex.org/W1976956127","https://openalex.org/W1983089547","https://openalex.org/W2013895638","https://openalex.org/W2048687352","https://openalex.org/W2165726932","https://openalex.org/W2462102501","https://openalex.org/W2484646121","https://openalex.org/W2561946193","https://openalex.org/W2561952445","https://openalex.org/W2570494446","https://openalex.org/W2779055119","https://openalex.org/W2921889099","https://openalex.org/W2944734899","https://openalex.org/W2963248893","https://openalex.org/W2997434542","https://openalex.org/W3098412154","https://openalex.org/W3114263192","https://openalex.org/W3154507809","https://openalex.org/W3156587271","https://openalex.org/W3163501229","https://openalex.org/W3166923021","https://openalex.org/W3176881123","https://openalex.org/W3193590406","https://openalex.org/W3209135762","https://openalex.org/W4214717370","https://openalex.org/W4280590612","https://openalex.org/W4282946979","https://openalex.org/W4283727098","https://openalex.org/W4285131360","https://openalex.org/W4290717511","https://openalex.org/W4308634128","https://openalex.org/W4385732480","https://openalex.org/W6679257226","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6754297394","https://openalex.org/W6802758289"],"related_works":["https://openalex.org/W1859185863","https://openalex.org/W4307691181","https://openalex.org/W4285537323","https://openalex.org/W1932159282","https://openalex.org/W2964126589","https://openalex.org/W3016225735","https://openalex.org/W4388052800","https://openalex.org/W2808418668","https://openalex.org/W1518875602","https://openalex.org/W3105579180"],"abstract_inverted_index":{"Optimal":[0],"learning":[1,22,35],"output":[2],"tracking":[3,28],"control":[4,18,29,82],"(OLOTC)":[5],"in":[6,14,105],"a":[7,63,106,109],"model-free":[8,27,65,107,110,140],"manner":[9],"has":[10,30],"received":[11],"increasing":[12],"attention":[13],"both":[15],"the":[16,20,26,72,89,94,98,120,129,133,144,151,167,170],"intelligent":[17],"and":[19,36,132,156],"reinforcement":[21],"(RL)":[23],"communities.":[24],"Although":[25],"been":[31],"achieved":[32],"via":[33,97],"off-policy":[34],"Q-learning,":[37],"another":[38],"popular":[39],"RL":[40],"idea":[41],"of":[42,93,122,128,139,154,169],"direct":[43],"policy":[44,66,83,112],"learning,":[45],"with":[46,150],"its":[47],"easy-to-implement":[48],"feature,":[49],"is":[50,84,116,148],"still":[51],"rarely":[52],"considered.":[53],"To":[54,101],"fill":[55],"this":[56,58,103],"gap,":[57],"article":[59],"aims":[60],"to":[61,70,86,118,143,165],"develop":[62],"novel":[64],"optimization":[67],"(PO)":[68],"algorithm":[69,104,115,142],"achieve":[71],"OLOTC":[73],"for":[74],"unknown":[75],"linear":[76],"discrete-time":[77],"(DT)":[78],"systems.":[79],"The":[80,136],"iterative":[81],"parameterized":[85],"directly":[87],"improve":[88],"discounted":[90,123],"value":[91,124,146],"function":[92,125,147],"augmented":[95],"system":[96],"gradient-based":[99],"method.":[100,172],"implement":[102],"manner,":[108],"two-point":[111],"gradient":[113,121],"(PG)":[114],"designed":[117],"approximate":[119],"by":[126],"virtue":[127],"sampled":[130],"states":[131],"reference":[134],"trajectories.":[135],"global":[137],"convergence":[138],"PO":[141],"optimal":[145],"demonstrated":[149],"sufficient":[152],"quantity":[153],"samples":[155],"proper":[157],"conditions.":[158],"Finally,":[159],"numerical":[160],"simulation":[161],"results":[162],"are":[163],"provided":[164],"validate":[166],"effectiveness":[168],"present":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}