{"id":"https://openalex.org/W2525486061","doi":"https://doi.org/10.1080/00207721.2016.1236423","title":"Model-Free control performance improvement using virtual reference feedback tuning and reinforcement Q-learning","display_name":"Model-Free control performance improvement using virtual reference feedback tuning and reinforcement Q-learning","publication_year":2016,"publication_date":"2016-09-29","ids":{"openalex":"https://openalex.org/W2525486061","doi":"https://doi.org/10.1080/00207721.2016.1236423","mag":"2525486061"},"language":"en","primary_location":{"id":"doi:10.1080/00207721.2016.1236423","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207721.2016.1236423","pdf_url":null,"source":{"id":"https://openalex.org/S129640837","display_name":"International Journal of Systems Science","issn_l":"0020-7721","issn":["0020-7721","1464-5319"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Systems Science","raw_type":"journal-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/A5034010145","display_name":"Mircea\u2010Bogdan R\u0103dac","orcid":"https://orcid.org/0000-0001-8410-6547"},"institutions":[{"id":"https://openalex.org/I3122695212","display_name":"Polytechnic University of Timi\u015foara","ror":"https://ror.org/02v91gy68","country_code":"RO","type":"education","lineage":["https://openalex.org/I3122695212"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Mircea-Bogdan Radac","raw_affiliation_strings":["Department of Automation and Applied Informatics, Politehnica University of Timisoara, Timisoara, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation and Applied Informatics, Politehnica University of Timisoara, Timisoara, Romania","institution_ids":["https://openalex.org/I3122695212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010759472","display_name":"Radu\u2010Emil Precup","orcid":"https://orcid.org/0000-0002-2060-7403"},"institutions":[{"id":"https://openalex.org/I12079687","display_name":"Edith Cowan University","ror":"https://ror.org/05jhnwe22","country_code":"AU","type":"education","lineage":["https://openalex.org/I12079687"]},{"id":"https://openalex.org/I3122695212","display_name":"Polytechnic University of Timi\u015foara","ror":"https://ror.org/02v91gy68","country_code":"RO","type":"education","lineage":["https://openalex.org/I3122695212"]}],"countries":["AU","RO"],"is_corresponding":true,"raw_author_name":"Radu-Emil Precup","raw_affiliation_strings":["Department of Automation and Applied Informatics, Politehnica University of Timisoara, Timisoara, Romania; School of Engineering, Edith Cowan University, Joondalup, WA, Australia","Department of Automation and Applied Informatics, Politehnica University of Timisoara, Timisoara, Romania","School of Engineering, Edith Cowan University, Joondalup, WA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation and Applied Informatics, Politehnica University of Timisoara, Timisoara, Romania; School of Engineering, Edith Cowan University, Joondalup, WA, Australia","institution_ids":["https://openalex.org/I3122695212"]},{"raw_affiliation_string":"Department of Automation and Applied Informatics, Politehnica University of Timisoara, Timisoara, Romania","institution_ids":["https://openalex.org/I3122695212"]},{"raw_affiliation_string":"School of Engineering, Edith Cowan University, Joondalup, WA, Australia","institution_ids":["https://openalex.org/I12079687"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088161472","display_name":"Raul\u2010Cristian Roman","orcid":"https://orcid.org/0000-0003-2551-7842"},"institutions":[{"id":"https://openalex.org/I3122695212","display_name":"Polytechnic University of Timi\u015foara","ror":"https://ror.org/02v91gy68","country_code":"RO","type":"education","lineage":["https://openalex.org/I3122695212"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Raul-Cristian Roman","raw_affiliation_strings":["Department of Automation and Applied Informatics, Politehnica University of Timisoara, Timisoara, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation and Applied Informatics, Politehnica University of Timisoara, Timisoara, Romania","institution_ids":["https://openalex.org/I3122695212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010759472"],"corresponding_institution_ids":["https://openalex.org/I12079687","https://openalex.org/I3122695212"],"apc_list":null,"apc_paid":null,"fwci":13.3727,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.98843331,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"48","issue":"5","first_page":"1071","last_page":"1083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998000264167786,"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":0.9998000264167786,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9984999895095825,"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/T11236","display_name":"Control Systems and Identification","score":0.9941999912261963,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8094425201416016},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7197157740592957},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6220264434814453},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6124418377876282},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5020241737365723},{"id":"https://openalex.org/keywords/mimo","display_name":"MIMO","score":0.4978160858154297},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.46621236205101013},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44854870438575745},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4311322569847107},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.41178959608078003},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3827574849128723},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.32555091381073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32318314909935},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2197427749633789},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.21886399388313293},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1403219997882843}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8094425201416016},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7197157740592957},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6220264434814453},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6124418377876282},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5020241737365723},{"id":"https://openalex.org/C207987634","wikidata":"https://www.wikidata.org/wiki/Q176862","display_name":"MIMO","level":3,"score":0.4978160858154297},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.46621236205101013},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44854870438575745},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4311322569847107},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.41178959608078003},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3827574849128723},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.32555091381073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32318314909935},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2197427749633789},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.21886399388313293},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1403219997882843},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":3,"locations":[{"id":"doi:10.1080/00207721.2016.1236423","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207721.2016.1236423","pdf_url":null,"source":{"id":"https://openalex.org/S129640837","display_name":"International Journal of Systems Science","issn_l":"0020-7721","issn":["0020-7721","1464-5319"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Systems Science","raw_type":"journal-article"},{"id":"pmh:oai:ro.ecu.edu.au:ecuworkspost2013-3381","is_oa":false,"landing_page_url":"https://ro.ecu.edu.au/ecuworkspost2013/2542","pdf_url":null,"source":{"id":"https://openalex.org/S4306401966","display_name":"Edith Cowan University Research Online (Edith Cowan University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I12079687","host_organization_name":"Edith Cowan University","host_organization_lineage":["https://openalex.org/I12079687"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research outputs 2014 to 2021","raw_type":"text"},{"id":"pmh:oai:RePEc:taf:tsysxx:v:48:y:2017:i:5:p:1071-1083","is_oa":false,"landing_page_url":"http://hdl.handle.net/10.1080/00207721.2016.1236423","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6793146615","display_name":null,"funder_award_id":"PN-II-RU-TE-2014-4-0207, PN-II-ID-PCE-2011-3-0109","funder_id":"https://openalex.org/F4320323983","funder_display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii"}],"funders":[{"id":"https://openalex.org/F4320323983","display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii","ror":"https://ror.org/01q7jq182"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W132264163","https://openalex.org/W166862392","https://openalex.org/W577942290","https://openalex.org/W610943335","https://openalex.org/W807629144","https://openalex.org/W925887043","https://openalex.org/W1523374892","https://openalex.org/W1825869920","https://openalex.org/W1959607397","https://openalex.org/W1972116103","https://openalex.org/W1973212500","https://openalex.org/W1984672166","https://openalex.org/W1989248346","https://openalex.org/W1990264246","https://openalex.org/W2001721683","https://openalex.org/W2003631999","https://openalex.org/W2003931400","https://openalex.org/W2012102319","https://openalex.org/W2015975537","https://openalex.org/W2019375098","https://openalex.org/W2035933463","https://openalex.org/W2040803101","https://openalex.org/W2050838777","https://openalex.org/W2060934030","https://openalex.org/W2062950232","https://openalex.org/W2065563952","https://openalex.org/W2068202815","https://openalex.org/W2074744798","https://openalex.org/W2082158148","https://openalex.org/W2092475168","https://openalex.org/W2097951814","https://openalex.org/W2104405273","https://openalex.org/W2104682245","https://openalex.org/W2106147350","https://openalex.org/W2109791710","https://openalex.org/W2117715687","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2125077163","https://openalex.org/W2125937501","https://openalex.org/W2130796753","https://openalex.org/W2132875296","https://openalex.org/W2133715004","https://openalex.org/W2134569556","https://openalex.org/W2136064843","https://openalex.org/W2136638407","https://openalex.org/W2151083101","https://openalex.org/W2151966330","https://openalex.org/W2152161277","https://openalex.org/W2163883370","https://openalex.org/W2168945912","https://openalex.org/W2233997862","https://openalex.org/W2497183556","https://openalex.org/W3100957396","https://openalex.org/W4205482704"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915","https://openalex.org/W2089415692","https://openalex.org/W4294873804"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"the":[3,45,59,91,97,124,130,135,142],"combination":[4],"of":[5,109,129],"two":[6,86,125],"model-free":[7],"controller":[8,39,76],"tuning":[9,16],"techniques,":[10],"namely":[11],"linear":[12],"virtual":[13],"reference":[14,50],"feedback":[15,38],"(VRFT)":[17],"and":[18,94],"nonlinear":[19],"state-feedback":[20],"Q-learning,":[21],"referred":[22],"to":[23,35,70],"as":[24],"a":[25,48,79,110],"new":[26],"mixed":[27],"VRFT-Q":[28,101],"learning":[29,102],"approach.":[30],"VRFT":[31,69,143],"is":[32,55,104],"first":[33],"used":[34],"find":[36],"stabilising":[37],"using":[40,62],"input-output":[41],"experimental":[42,64],"data":[43,65],"from":[44],"process":[46],"in":[47,58],"model":[49],"tracking":[51],"setting.":[52],"Reinforcement":[53],"Q-learning":[54,75,136],"next":[56],"applied":[57],"same":[60],"setting":[61],"input-state":[63],"collected":[66],"under":[67],"perturbed":[68],"ensure":[71],"good":[72],"exploration.":[73],"The":[74,100],"learned":[77],"with":[78],"batch":[80],"fitted":[81],"Q":[82],"iteration":[83],"algorithm":[84],"uses":[85],"neural":[87],"networks,":[88],"one":[89,95],"for":[90,96,123],"Q-function":[92],"estimator":[93],"controller,":[98],"respectively.":[99],"approach":[103],"validated":[105],"on":[106],"position":[107],"control":[108,127],"two-degrees-of-motion":[111],"open-loop":[112],"stable":[113],"multi":[114],"input-multi":[115],"output":[116],"(MIMO)":[117],"aerodynamic":[118],"system":[119],"(AS).":[120],"Extensive":[121],"simulations":[122],"independent":[126],"channels":[128],"MIMO":[131],"AS":[132],"show":[133],"that":[134],"controllers":[137],"clearly":[138],"improve":[139],"performance":[140],"over":[141],"controllers.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":10}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
