{"id":"https://openalex.org/W4401246379","doi":"https://doi.org/10.1109/tase.2024.3434533","title":"Q-Learning Methods for LQR Control of Completely Unknown Discrete-Time Linear Systems","display_name":"Q-Learning Methods for LQR Control of Completely Unknown Discrete-Time Linear Systems","publication_year":2024,"publication_date":"2024-08-02","ids":{"openalex":"https://openalex.org/W4401246379","doi":"https://doi.org/10.1109/tase.2024.3434533"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2024.3434533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2024.3434533","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","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/A5103585690","display_name":"Wenwu Fan","orcid":"https://orcid.org/0000-0002-7310-0382"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenwu Fan","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021953090","display_name":"Junlin Xiong","orcid":"https://orcid.org/0000-0002-0128-4960"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlin Xiong","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103585690"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.0967,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8717726,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"22","issue":null,"first_page":"5933","last_page":"5943"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11749","display_name":"Iterative Learning Control Systems","score":0.9187999963760376,"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"}},"topics":[{"id":"https://openalex.org/T11749","display_name":"Iterative Learning Control Systems","score":0.9187999963760376,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9063000082969666,"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/control-theory","display_name":"Control theory (sociology)","score":0.6117727160453796},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5251288414001465},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.47155308723449707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46160000562667847},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.4597407281398773},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.43635275959968567},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.43603238463401794},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.41379010677337646},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.33657485246658325},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29572802782058716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22909867763519287},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09784701466560364}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6117727160453796},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5251288414001465},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.47155308723449707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46160000562667847},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.4597407281398773},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.43635275959968567},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.43603238463401794},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.41379010677337646},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.33657485246658325},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29572802782058716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22909867763519287},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09784701466560364},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2024.3434533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2024.3434533","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8020654489","display_name":null,"funder_award_id":"62273320","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1616818660","https://openalex.org/W2005437559","https://openalex.org/W2011866373","https://openalex.org/W2087063454","https://openalex.org/W2129288433","https://openalex.org/W2149804959","https://openalex.org/W2151966330","https://openalex.org/W2165726932","https://openalex.org/W2547247639","https://openalex.org/W2807176303","https://openalex.org/W2905020454","https://openalex.org/W2924607344","https://openalex.org/W2969103356","https://openalex.org/W2979207987","https://openalex.org/W2995764727","https://openalex.org/W3009014967","https://openalex.org/W3012066402","https://openalex.org/W3044015199","https://openalex.org/W3098412154","https://openalex.org/W3106313228","https://openalex.org/W3159667783","https://openalex.org/W3184620837","https://openalex.org/W3185439814","https://openalex.org/W3195923278","https://openalex.org/W3199938616","https://openalex.org/W4200100878","https://openalex.org/W4200561738","https://openalex.org/W4205172873","https://openalex.org/W4210704481","https://openalex.org/W4214717370","https://openalex.org/W4243655891","https://openalex.org/W4287617987","https://openalex.org/W4290717511","https://openalex.org/W4306822038","https://openalex.org/W4308902993","https://openalex.org/W4312548927","https://openalex.org/W4362722548","https://openalex.org/W4378194701","https://openalex.org/W4378802327","https://openalex.org/W4380903904","https://openalex.org/W4382365356","https://openalex.org/W4385062410","https://openalex.org/W4389987589"],"related_works":["https://openalex.org/W2482034469","https://openalex.org/W1987193149","https://openalex.org/W2166081455","https://openalex.org/W2607757002","https://openalex.org/W2615607975","https://openalex.org/W2192101006","https://openalex.org/W2116800748","https://openalex.org/W2638730922","https://openalex.org/W2190465783","https://openalex.org/W2027827693"],"abstract_inverted_index":{"This":[0,60,153],"paper":[1,61,208,243,255,332],"focuses":[2,256],"on":[3,134,146,257,317,339],"solving":[4,69,168],"the":[5,70,95,101,111,121,128,135,150,158,185,215,225,233,251,258,276,281,298,340,346,358,364,373],"linear":[6,12,23,42,216,222],"quadratic":[7,217],"regulator":[8,218],"problem":[9,73,89,171,187,219,260],"for":[10,22,68,90,188,220,283],"discrete-time":[11,221],"systems":[13,24],"without":[14,74],"knowing":[15],"system":[16,93,191,235],"matrices.":[17],"The":[18,124,301,324],"classical":[19],"Q-learning":[20,29,33,36,45,105,129,147,179,211],"methods":[21,212,305],"can":[25,156],"be":[26],"divided":[27],"into":[28],"value":[30,37],"iteration":[31,38,47,181],"and":[32,192],"policy":[34,46,99,291,322,349],"iteration.":[35,174,323],"converges":[39],"at":[40],"a":[41,49,141,162,178],"convergence":[43,51,125],"rate.":[44],"has":[48],"second-order":[50],"rate":[52,126],"but":[53],"requires":[54],"an":[55,76,87,91,169,189],"initial":[56,77,318],"stabilizing":[57,78],"control":[58,72,79,98,285,348],"policy.":[59,80],"aims":[62],"to":[63,109,117,120,148,183,201,206,213,231,246,274,290,296,344,356],"propose":[64,177,270],"efficient":[65],"model-free":[66,142,248,272],"algorithms":[67,273,294,311,343],"optimal":[71,97,122,159,284,347],"requiring":[75],"In":[81,335],"this":[82,242,254,331],"paper,":[83],"we":[84,139,176,337],"first":[85],"present":[86],"equivalent":[88,112,186],"auxiliary":[92,136,190],"with":[94,321],"same":[96],"as":[100],"LQR":[102,151,170,259,277],"problem.":[103,152],"A":[104],"algorithm":[106,130,182,328,369],"is":[107,115,131,229,244,263,306],"proposed":[108,329],"solve":[110,149,184,214,275,297],"problem,":[113,278],"which":[114,279],"proven":[116],"converge":[118],"monotonically":[119],"solution.":[123],"of":[127,165,286,303,309,326,342,360,367],"heavily":[132],"dependent":[133],"system,":[137],"so":[138,241],"introduce":[140],"homotopy":[143,154],"method":[144,155],"based":[145],"achieve":[157],"solution":[160],"in":[161,172,238,266,330,372],"finite":[163],"number":[164],"iterations":[166],"by":[167],"each":[173,368],"Additionally,":[175],"Lyapunov":[180,299],"analyze":[193],"its":[194],"properties.":[195],"Finally,":[196,363],"two":[197],"examples":[198,353],"are":[199,333,354,370],"provided":[200],"demonstrate":[202],"our":[203,293,304,310,361],"results.":[204],"Note":[205],"Practitioners\u2014This":[207],"proposes":[209],"several":[210,271],"systems.":[223],"On":[224,250],"one":[226],"hand,":[227,253],"it":[228,262],"difficult":[230],"know":[232],"exact":[234],"dynamics":[236],"knowledge":[237],"actual":[239,287],"engineering,":[240],"devoted":[245],"developing":[247],"algorithms.":[249],"other":[252],"because":[261],"widely":[264],"spread":[265],"practical":[267,352],"applications.":[268,288],"We":[269],"provides":[280],"basis":[282],"Similar":[289],"iteration,":[292],"need":[295],"equation.":[300],"advantage":[302],"that":[307],"all":[308],"do":[312],"not":[313],"have":[314],"strict":[315],"constraints":[316],"conditions":[319],"compared":[320],"properties":[325],"every":[327],"provided.":[334],"addition,":[336],"focus":[338],"efficiency":[341],"obtain":[345],"faster.":[350],"Two":[351],"used":[355],"verify":[357],"effectiveness":[359],"methods.":[362],"applicable":[365],"situations":[366],"summarized":[371],"conclusion.":[374]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}