{"id":"https://openalex.org/W2908061247","doi":"https://doi.org/10.1109/icarcv.2018.8581252","title":"Output Feedback Reinforcement Q-learning for Optimal Quadratic Tracking Control of Unknown Discrete-Time Linear Systems and Its Application","display_name":"Output Feedback Reinforcement Q-learning for Optimal Quadratic Tracking Control of Unknown Discrete-Time Linear Systems and Its Application","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2908061247","doi":"https://doi.org/10.1109/icarcv.2018.8581252","mag":"2908061247"},"language":"en","primary_location":{"id":"doi:10.1109/icarcv.2018.8581252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv.2018.8581252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","raw_type":"proceedings-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/A5023350461","display_name":"Guangyue Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guangyue Zhao","raw_affiliation_strings":["College of Automation Science and Engineering, South China University of Technology, Guangzhou, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Automation Science and Engineering, South China University of Technology, Guangzhou, P. R. China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101695016","display_name":"Weijie Sun","orcid":"https://orcid.org/0000-0003-4957-9749"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijie Sun","raw_affiliation_strings":["College of Automation Science and Engineering, South China University of Technology, Guangzhou, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Automation Science and Engineering, South China University of Technology, Guangzhou, P. R. China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044678024","display_name":"He Cai","orcid":"https://orcid.org/0000-0002-0411-1774"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Cai","raw_affiliation_strings":["College of Automation Science and Engineering, South China University of Technology, Guangzhou, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Automation Science and Engineering, South China University of Technology, Guangzhou, P. R. China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000624513","display_name":"Yunjian Peng","orcid":"https://orcid.org/0000-0002-6066-3979"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjian Peng","raw_affiliation_strings":["College of Automation Science and Engineering, South China University of Technology, Guangzhou, P. R. China"],"affiliations":[{"raw_affiliation_string":"College of Automation Science and Engineering, South China University of Technology, Guangzhou, P. R. China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023350461"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.20624627,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"750","last_page":"755"},"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":0.9656999707221985,"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":0.9498000144958496,"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":0.6886171102523804},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6498023867607117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6428120136260986},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6124083399772644},{"id":"https://openalex.org/keywords/iterative-learning-control","display_name":"Iterative learning control","score":0.5863521695137024},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.573409914970398},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5524069666862488},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5297357439994812},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5097060203552246},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.5035962462425232},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.49319857358932495},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4630710184574127},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4429703950881958},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3603127598762512},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.246618390083313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.190181165933609},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.15525949001312256}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6886171102523804},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6498023867607117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6428120136260986},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6124083399772644},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.5863521695137024},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.573409914970398},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5524069666862488},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5297357439994812},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5097060203552246},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.5035962462425232},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.49319857358932495},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4630710184574127},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4429703950881958},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3603127598762512},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.246618390083313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.190181165933609},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.15525949001312256},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icarcv.2018.8581252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv.2018.8581252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W92805021","https://openalex.org/W1573503290","https://openalex.org/W1600349401","https://openalex.org/W1601081659","https://openalex.org/W1907796993","https://openalex.org/W1972809999","https://openalex.org/W1976956127","https://openalex.org/W2005437559","https://openalex.org/W2011866373","https://openalex.org/W2013895638","https://openalex.org/W2024780670","https://openalex.org/W2121863487","https://openalex.org/W2138326839","https://openalex.org/W2151966330","https://openalex.org/W2165726932","https://openalex.org/W2484646121","https://openalex.org/W2543843511","https://openalex.org/W2580629550","https://openalex.org/W2783964454","https://openalex.org/W2798534591","https://openalex.org/W3213472335","https://openalex.org/W4214717370","https://openalex.org/W6603762378","https://openalex.org/W6643710770","https://openalex.org/W6804409665"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2043058420","https://openalex.org/W2361647908"],"abstract_inverted_index":{"In":[0],"this":[1,32],"paper,":[2],"a":[3],"novel":[4],"output":[5,68],"feedback":[6,69],"solution":[7],"based":[8],"on":[9],"the":[10,14,20,40,45,55,64,67,76,86,107,117,120],"Q-learning":[11,70],"algorithm":[12],"using":[13,54],"measured":[15],"data":[16,62],"is":[17,49,72],"proposed":[18,121],"for":[19],"linear":[21,46],"quadratic":[22],"tracking":[23,78],"(LQT)":[24],"problem":[25],"of":[26,39,63,85,119],"unknown":[27],"discrete-time":[28],"systems.":[29],"To":[30],"tackle":[31],"technical":[33],"issue,":[34],"an":[35],"augmented":[36,65,87],"system":[37,43,88],"composed":[38],"original":[41],"controlled":[42],"and":[44,59,97],"command":[47],"generator":[48],"first":[50],"constructed.":[51],"Then,":[52],"by":[53],"past":[56],"input,":[57],"output,":[58],"reference":[60],"trajectory":[61],"system,":[66],"scheme":[71],"able":[73],"to":[74,104,106,115],"learn":[75],"optimal":[77,108],"controller":[79],"online":[80],"without":[81],"requiring":[82],"any":[83],"knowledge":[84],"dynamics.":[89],"Learning":[90],"algorithms":[91,101],"including":[92],"both":[93],"policy":[94],"iteration":[95,99],"(PI)":[96],"value":[98],"(VI)":[100],"are":[102,113],"developed":[103],"converge":[105],"solution.":[109],"Finally,":[110],"simulation":[111],"results":[112],"provided":[114],"verify":[116],"effectiveness":[118],"scheme.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}