{"id":"https://openalex.org/W4409981390","doi":"https://doi.org/10.1080/00207179.2025.2497894","title":"Output feedback linear quadratic regulator design through one-shot Q-function learning","display_name":"Output feedback linear quadratic regulator design through one-shot Q-function learning","publication_year":2025,"publication_date":"2025-04-30","ids":{"openalex":"https://openalex.org/W4409981390","doi":"https://doi.org/10.1080/00207179.2025.2497894"},"language":"en","primary_location":{"id":"doi:10.1080/00207179.2025.2497894","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207179.2025.2497894","pdf_url":null,"source":{"id":"https://openalex.org/S88061139","display_name":"International Journal of Control","issn_l":"0020-7179","issn":["0020-7179","1366-5820"],"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","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Control","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/A5117393985","display_name":"Ahmad Pishro Asl","orcid":null},"institutions":[{"id":"https://openalex.org/I107853901","display_name":"Sahand University of Technology","ror":"https://ror.org/03wdrmh81","country_code":"IR","type":"education","lineage":["https://openalex.org/I107853901"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ahmad Pishro Asl","raw_affiliation_strings":["Sahand University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sahand University of Technology","institution_ids":["https://openalex.org/I107853901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020216791","display_name":"Ahmad Akbari","orcid":"https://orcid.org/0000-0002-0387-1616"},"institutions":[{"id":"https://openalex.org/I107853901","display_name":"Sahand University of Technology","ror":"https://ror.org/03wdrmh81","country_code":"IR","type":"education","lineage":["https://openalex.org/I107853901"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Ahmad Akbari","raw_affiliation_strings":["Sahand University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sahand University of Technology","institution_ids":["https://openalex.org/I107853901"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5020216791"],"corresponding_institution_ids":["https://openalex.org/I107853901"],"apc_list":null,"apc_paid":null,"fwci":2.6832,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.90585258,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"99","issue":"1","first_page":"98","last_page":"110"},"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":0.9944999814033508,"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":0.9810000061988831,"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/regulator","display_name":"Regulator","score":0.6836109161376953},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6070725321769714},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5618532299995422},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.5403187274932861},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.48889032006263733},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4136695861816406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.353657066822052},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3389740586280823},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2963365912437439},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.19227707386016846},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.1905883550643921},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17279377579689026},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09592437744140625}],"concepts":[{"id":"https://openalex.org/C6929976","wikidata":"https://www.wikidata.org/wiki/Q3771881","display_name":"Regulator","level":3,"score":0.6836109161376953},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6070725321769714},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5618532299995422},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.5403187274932861},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48889032006263733},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4136695861816406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.353657066822052},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3389740586280823},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2963365912437439},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.19227707386016846},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.1905883550643921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17279377579689026},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09592437744140625},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/00207179.2025.2497894","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207179.2025.2497894","pdf_url":null,"source":{"id":"https://openalex.org/S88061139","display_name":"International Journal of Control","issn_l":"0020-7179","issn":["0020-7179","1366-5820"],"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","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W92805021","https://openalex.org/W1513689897","https://openalex.org/W1616818660","https://openalex.org/W1907796993","https://openalex.org/W1983523797","https://openalex.org/W2011866373","https://openalex.org/W2037025184","https://openalex.org/W2116508132","https://openalex.org/W2145956080","https://openalex.org/W2151966330","https://openalex.org/W2484646121","https://openalex.org/W2484957131","https://openalex.org/W2487144912","https://openalex.org/W2523345745","https://openalex.org/W2529970964","https://openalex.org/W2570494446","https://openalex.org/W2600133099","https://openalex.org/W2772589676","https://openalex.org/W2776811469","https://openalex.org/W2790759697","https://openalex.org/W2807098429","https://openalex.org/W2979207987","https://openalex.org/W3035230405","https://openalex.org/W3080911326","https://openalex.org/W3175769301","https://openalex.org/W3184481401","https://openalex.org/W3185447307","https://openalex.org/W3187550742","https://openalex.org/W3213472335","https://openalex.org/W4200561738","https://openalex.org/W4206318793","https://openalex.org/W4206759694","https://openalex.org/W4296437947","https://openalex.org/W4310121338","https://openalex.org/W4317038497","https://openalex.org/W4320515731","https://openalex.org/W4361794133","https://openalex.org/W4385009615","https://openalex.org/W4386736705","https://openalex.org/W4388319978","https://openalex.org/W4391214679","https://openalex.org/W4391655974","https://openalex.org/W6675663018"],"related_works":["https://openalex.org/W2354064740","https://openalex.org/W2731754693","https://openalex.org/W267916353","https://openalex.org/W2326995340","https://openalex.org/W1985169903","https://openalex.org/W2152693275","https://openalex.org/W311622956","https://openalex.org/W1592622096","https://openalex.org/W2122083069","https://openalex.org/W2050309662"],"abstract_inverted_index":{"In":[0],"model-free":[1],"control,":[2],"reinforcement":[3],"learning":[4],"(RL)":[5],"methods":[6,23],"such":[7],"as":[8,41],"Q-learning":[9],"have":[10],"been":[11],"employed":[12],"to":[13,29],"design":[14],"discrete-time":[15],"(DT)":[16],"linear":[17,47],"quadratic":[18],"regulators":[19],"(LQR).":[20],"However,":[21],"these":[22],"suffer":[24],"from":[25,74],"sample":[26],"inefficiency":[27],"due":[28],"their":[30],"iterative":[31],"nature.":[32],"Using":[33],"an":[34,105,118,130],"alternative":[35,64],"formulation":[36,65],"of":[37,84],"the":[38,68,95,115,124,134],"LQR":[39],"problem":[40,138],"a":[42,58,81],"semi-definite":[43],"program":[44],"(SDP)":[45],"with":[46],"matrix":[48],"inequality":[49],"(LMI)":[50],"constraints":[51],"can":[52],"address":[53],"this":[54,63],"challenge.":[55],"We":[56,122],"propose":[57],"novel":[59],"approach":[60,112],"that":[61,113],"constructs":[62],"and":[66,109,133,145],"learns":[67],"optimal":[69],"output":[70],"feedback":[71],"Q-function":[72],"exclusively":[73],"input-output":[75],"data.":[76],"Our":[77],"method":[78,126],"requires":[79],"only":[80],"single":[82],"batch":[83],"data,":[85],"enabling":[86],"what":[87],"we":[88,98],"term":[89],"one-shot":[90],"learning.":[91],"Furthermore,":[92],"by":[93],"leveraging":[94],"Bellman":[96],"equation,":[97],"achieve":[99],"online":[100],"controller":[101],"adaptation,":[102],"resulting":[103],"in":[104,139],"off-policy,":[106],"model-free,":[107],"sample-efficient,":[108],"non-iterative":[110],"adaptive":[111],"eliminates":[114],"need":[116],"for":[117],"initial":[119],"stabilising":[120],"policy.":[121],"validate":[123],"proposed":[125],"through":[127],"simulations":[128],"on":[129],"unstable":[131],"system":[132],"load":[135],"frequency":[136],"control":[137],"power":[140],"systems,":[141],"demonstrating":[142],"its":[143],"effectiveness":[144],"real-world":[146],"applicability.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
