{"id":"https://openalex.org/W7128923063","doi":"https://doi.org/10.1080/00207179.2026.2623467","title":"Q-learning for continuous-time linear systems: a data-driven infinite horizon optimal control approach with dynamic output feedback","display_name":"Q-learning for continuous-time linear systems: a data-driven infinite horizon optimal control approach with dynamic output feedback","publication_year":2026,"publication_date":"2026-02-14","ids":{"openalex":"https://openalex.org/W7128923063","doi":"https://doi.org/10.1080/00207179.2026.2623467"},"language":"en","primary_location":{"id":"doi:10.1080/00207179.2026.2623467","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207179.2026.2623467","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/A5101508336","display_name":"Yuehua Chen","orcid":"https://orcid.org/0000-0002-4646-4017"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanlin Chen","raw_affiliation_strings":["Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125998966","display_name":"Shaoping Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaoping Shen","raw_affiliation_strings":["Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113950700","display_name":"Zikun Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zikun Hu","raw_affiliation_strings":["Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016669699","display_name":"Zhibin Li","orcid":"https://orcid.org/0000-0002-4430-3762"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibin Li","raw_affiliation_strings":["Shandong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5125998966"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1794729,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"99","issue":"6","first_page":"1943","last_page":"1956"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9287999868392944,"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":0.9287999868392944,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.014000000432133675,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.010300000198185444,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6789000034332275},{"id":"https://openalex.org/keywords/output-feedback","display_name":"Output feedback","score":0.6640999913215637},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6104999780654907},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.45170000195503235},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44339999556541443},{"id":"https://openalex.org/keywords/feedback-control","display_name":"Feedback control","score":0.42750000953674316}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6789000034332275},{"id":"https://openalex.org/C3018623182","wikidata":"https://www.wikidata.org/wiki/Q154021","display_name":"Output feedback","level":3,"score":0.6640999913215637},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6104999780654907},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4684000015258789},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C3018651601","wikidata":"https://www.wikidata.org/wiki/Q183635","display_name":"Feedback control","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38420000672340393},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3490000069141388},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3402999937534332},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C204495892","wikidata":"https://www.wikidata.org/wiki/Q1798304","display_name":"Linear-quadratic-Gaussian control","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/00207179.2026.2623467","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207179.2026.2623467","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":[{"id":"https://openalex.org/G5516150561","display_name":null,"funder_award_id":"U23A20336","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W601351931","https://openalex.org/W1980972971","https://openalex.org/W2005437559","https://openalex.org/W2008166951","https://openalex.org/W2013895638","https://openalex.org/W2024303516","https://openalex.org/W2087063454","https://openalex.org/W2137092694","https://openalex.org/W2148439597","https://openalex.org/W2151966330","https://openalex.org/W2152161277","https://openalex.org/W2160698719","https://openalex.org/W2167939001","https://openalex.org/W2467518411","https://openalex.org/W2523345745","https://openalex.org/W2529970964","https://openalex.org/W2564717627","https://openalex.org/W2783964454","https://openalex.org/W2801370262","https://openalex.org/W2807176303","https://openalex.org/W2907944110","https://openalex.org/W3087896133","https://openalex.org/W4205951204","https://openalex.org/W4214717370","https://openalex.org/W4402330678","https://openalex.org/W4407212638","https://openalex.org/W4412623520"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,51],"online":[4],"Q-learning":[5],"algorithm":[6],"for":[7,80],"solving":[8],"the":[9,29,38,41,63,81,84,91,94,107],"infinite-horizon":[10],"optimal":[11,42,64],"control":[12],"problem":[13],"of":[14,83,93],"linear":[15],"time-invariant":[16],"systems":[17],"with":[18],"completely":[19],"unknown":[20],"dynamics,":[21],"using":[22,66],"dynamic":[23],"output":[24],"feedback.":[25],"First,":[26],"we":[27],"formulate":[28],"Q-function":[30],"based":[31],"on":[32],"a":[33],"parameterised":[34],"observer":[35],"derived":[36],"from":[37],"Hamiltonian":[39],"and":[40,60,90],"cost.":[43],"An":[44],"actor-critic":[45],"approximator":[46],"structure":[47],"is":[48],"developed":[49],"within":[50],"integrated":[52],"reinforcement":[53],"learning":[54,96],"framework,":[55],"ensuring":[56],"closed-loop":[57,85],"asymptotic":[58],"stability":[59,82],"convergence":[61,92],"to":[62,105],"solution":[65],"only":[67],"measurable":[68],"input-output":[69],"data,":[70],"without":[71],"requiring":[72],"any":[73],"model":[74],"information.":[75],"Theoretical":[76],"guarantees":[77],"are":[78,103],"provided":[79],"system,":[86],"including":[87],"state":[88],"estimation,":[89],"adaptive":[95],"algorithm.":[97],"Finally,":[98],"two":[99],"comprehensive":[100],"simulation":[101],"examples":[102],"presented":[104],"validate":[106],"proposed":[108],"scheme.":[109]},"counts_by_year":[],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2026-02-15T00:00:00"}
