{"id":"https://openalex.org/W7105589838","doi":"https://doi.org/10.1109/tac.2025.3632464","title":"Low-Complexity Q-Value Iteration Learning for Linear Quadratic Regulators Without Initial Stabilizing Gain","display_name":"Low-Complexity Q-Value Iteration Learning for Linear Quadratic Regulators Without Initial Stabilizing Gain","publication_year":2025,"publication_date":"2025-11-13","ids":{"openalex":"https://openalex.org/W7105589838","doi":"https://doi.org/10.1109/tac.2025.3632464"},"language":null,"primary_location":{"id":"doi:10.1109/tac.2025.3632464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3632464","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic 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":null,"display_name":"Longyang Huang","orcid":"https://orcid.org/0000-0001-5123-5043"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longyang Huang","raw_affiliation_strings":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5123-5043","affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lin Zhao","orcid":"https://orcid.org/0000-0002-1078-887X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lin Zhao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-1078-887X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":null,"display_name":"Weidong Zhang","orcid":"https://orcid.org/0000-0002-4700-1276"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Zhang","raw_affiliation_strings":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4700-1276","affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50656323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"71","issue":"5","first_page":"2998","last_page":"3013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9107999801635742,"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":0.9107999801635742,"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":0.0210999995470047,"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/T10046","display_name":"Stability and Control of Uncertain Systems","score":0.01889999955892563,"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/convergence","display_name":"Convergence (economics)","score":0.6937000155448914},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.6852999925613403},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6194999814033508},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5676000118255615},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5645999908447266},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.5507000088691711},{"id":"https://openalex.org/keywords/iterative-learning-control","display_name":"Iterative learning control","score":0.4844000041484833},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.47029998898506165},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.4641000032424927},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.45669999718666077}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6937000155448914},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.6852999925613403},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6194999814033508},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5676000118255615},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5645999908447266},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5231999754905701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4941999912261963},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.4844000041484833},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4293999969959259},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3628999888896942},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C81845259","wikidata":"https://www.wikidata.org/wiki/Q290117","display_name":"Quadratic programming","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C6929976","wikidata":"https://www.wikidata.org/wiki/Q3771881","display_name":"Regulator","level":3,"score":0.2964000105857849},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28929999470710754},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C145242015","wikidata":"https://www.wikidata.org/wiki/Q774123","display_name":"Approximation theory","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2025.3632464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3632464","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1586938274","display_name":null,"funder_award_id":"2022ZD0119900","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G2260626412","display_name":null,"funder_award_id":"U24A20260","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5721963804","display_name":null,"funder_award_id":"U2141234","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"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1999172680","https://openalex.org/W2005437559","https://openalex.org/W2013895638","https://openalex.org/W2022018324","https://openalex.org/W2024303516","https://openalex.org/W2082247780","https://openalex.org/W2124477018","https://openalex.org/W2148439597","https://openalex.org/W2151966330","https://openalex.org/W2165726932","https://openalex.org/W2467518411","https://openalex.org/W2580629550","https://openalex.org/W2907312290","https://openalex.org/W2966348706","https://openalex.org/W2979207987","https://openalex.org/W2995764727","https://openalex.org/W2999535065","https://openalex.org/W3012010640","https://openalex.org/W3012066402","https://openalex.org/W3045059767","https://openalex.org/W3092167358","https://openalex.org/W3161299873","https://openalex.org/W3175769301","https://openalex.org/W3182751084","https://openalex.org/W4200038771","https://openalex.org/W4200561738","https://openalex.org/W4210704481","https://openalex.org/W4214717370","https://openalex.org/W4233947285","https://openalex.org/W4290717511","https://openalex.org/W4293195488","https://openalex.org/W4312258136","https://openalex.org/W4313591116","https://openalex.org/W4362500581","https://openalex.org/W4387150541","https://openalex.org/W4387965994","https://openalex.org/W4401246379","https://openalex.org/W4402300769"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3],"demonstrated":[4],"promising":[5],"results":[6],"in":[7,97],"the":[8,34,55,60,65,78,90,104,117,120],"data-driven":[9,88],"design":[10,22],"of":[11,59,119],"linear":[12],"quadratic":[13],"regulator":[14],"(LQR)":[15],"controllers.":[16],"However,":[17],"existing":[18,87],"RL-based":[19],"LQR":[20],"controller":[21],"methods":[23],"face":[24],"challenges":[25],"regarding":[26],"computational":[27,98],"complexity,":[28,30],"sample":[29,100],"system":[31],"stability,":[32],"and":[33,57,99,102],"requirement":[35,105],"for":[36,106],"a":[37,47,107],"stabilizing":[38,108],"gain.":[39,109],"To":[40],"address":[41],"these":[42],"issues,":[43],"this":[44],"paper":[45],"proposes":[46],"novel":[48],"low-complexity":[49],"Q-value":[50],"iteration":[51],"algorithm.":[52,67,122],"We":[53],"establish":[54],"convergence":[56],"monotonicity":[58],"iterative":[61],"sequence":[62],"generated":[63],"by":[64],"proposed":[66,91,121],"Furthermore,":[68],"an":[69],"algorithmic":[70],"stopping":[71],"condition":[72],"is":[73,82],"designed":[74],"to":[75,86,115],"guarantee":[76],"that":[77],"resulting":[79],"control":[80],"gain":[81],"stabilizing.":[83],"In":[84],"contrast":[85],"methods,":[89],"algorithm":[92],"achieves":[93],"both":[94],"significant":[95],"improvements":[96],"efficiency":[101],"removes":[103],"Comparative":[110],"simulation":[111],"studies":[112],"are":[113],"conducted":[114],"demonstrate":[116],"effectiveness":[118]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-11-13T00:00:00"}