{"id":"https://openalex.org/W7117584577","doi":"https://doi.org/10.1109/tac.2025.3649291","title":"Model-Free Offline Reinforcement Learning for Linear Quadratic Control","display_name":"Model-Free Offline Reinforcement Learning for Linear Quadratic Control","publication_year":2025,"publication_date":"2025-12-30","ids":{"openalex":"https://openalex.org/W7117584577","doi":"https://doi.org/10.1109/tac.2025.3649291"},"language":null,"primary_location":{"id":"doi:10.1109/tac.2025.3649291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3649291","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":"https://openalex.org/A5020222014","display_name":"Haoran Ma","orcid":"https://orcid.org/0000-0002-2899-484X"},"institutions":[{"id":"https://openalex.org/I4392738113","display_name":"China Electric Power Research Institute","ror":"https://ror.org/05ehpzy81","country_code":null,"type":"facility","lineage":["https://openalex.org/I17442442","https://openalex.org/I4392738113"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Ma","raw_affiliation_strings":["State Key Laboratory of Power Grid Safety, China Electric Power Research Institute, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0171-5345","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Power Grid Safety, China Electric Power Research Institute, Beijing, China","institution_ids":["https://openalex.org/I4392738113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020893567","display_name":"Zhengen Zhao","orcid":"https://orcid.org/0000-0003-2630-9690"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengen Zhao","raw_affiliation_strings":["College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-2630-9690","affiliations":[{"raw_affiliation_string":"College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073295075","display_name":"Dingguo Liang","orcid":"https://orcid.org/0000-0002-9243-0045"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4391767778","display_name":"State Key Laboratory of Turbulence and Complex Systems","ror":"https://ror.org/04km98768","country_code":null,"type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingguo Liang","raw_affiliation_strings":["State Key Laboratory for Turbulence and Complex Systems, Department of Mechanics and Engineering Science, College of Engineering, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9243-0045","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Turbulence and Complex Systems, Department of Mechanics and Engineering Science, College of Engineering, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100771505","display_name":"Ying Yang","orcid":"https://orcid.org/0000-0001-6327-631X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4391767778","display_name":"State Key Laboratory of Turbulence and Complex Systems","ror":"https://ror.org/04km98768","country_code":null,"type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Yang","raw_affiliation_strings":["State Key Laboratory for Turbulence and Complex Systems, Department of Mechanics and Engineering Science, College of Engineering, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6327-631X","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Turbulence and Complex Systems, Department of Mechanics and Engineering Science, College of Engineering, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4391767778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68717311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"71","issue":"6","first_page":"4035","last_page":"4042"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9715999960899353,"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":0.9715999960899353,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.011599999852478504,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.00419999985024333,"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":0.8054999709129333},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5928000211715698},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5827000141143799},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5788000226020813},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5748000144958496},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5511999726295471},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5105000138282776},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4593000113964081},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4377000033855438}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8054999709129333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5974000096321106},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5928000211715698},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5827000141143799},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5788000226020813},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5748000144958496},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5511999726295471},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5105000138282776},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4593000113964081},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4377000033855438},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4352000057697296},{"id":"https://openalex.org/C204495892","wikidata":"https://www.wikidata.org/wiki/Q1798304","display_name":"Linear-quadratic-Gaussian control","level":3,"score":0.430400013923645},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.42320001125335693},{"id":"https://openalex.org/C155386361","wikidata":"https://www.wikidata.org/wiki/Q1649571","display_name":"Process control","level":3,"score":0.3978999853134155},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C81845259","wikidata":"https://www.wikidata.org/wiki/Q290117","display_name":"Quadratic programming","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.28060001134872437},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27070000767707825},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2558000087738037},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2025.3649291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3649291","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/G1799315264","display_name":null,"funder_award_id":"62173003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4776265103","display_name":null,"funder_award_id":"62473195","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8670534201","display_name":null,"funder_award_id":"T2121002","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,65],"paper":[1],"investigates":[2],"the":[3,27,31,43,46,57,67,87,100,103],"linear":[4],"quadratic":[5],"control":[6,93],"problem":[7],"with":[8,50],"both":[9],"process":[10,61],"and":[11,36,62,95,106,111],"measurement":[12,63],"noise":[13],"using":[14],"reinforcement":[15,72],"learning.":[16],"Instead":[17],"of":[18,45,69,86,102],"requiring":[19],"a":[20,51],"system":[21],"model":[22],"or":[23],"real-time":[24],"controller":[25,33],"updates,":[26],"proposed":[28,104],"approach":[29],"derives":[30],"optimal":[32],"from":[34],"offline":[35],"noise-corrupted":[37],"data.":[38],"A":[39],"key":[40],"contribution":[41],"is":[42],"formulation":[44],"Bellman":[47],"optimality":[48,80],"equation":[49],"correction":[52],"term":[53],"that":[54],"compensates":[55],"for":[56],"bias":[58],"introduced":[59],"by":[60],"noise.":[64],"addresses":[66],"limitations":[68],"existing":[70],"model-free":[71],"learning":[73],"approaches,":[74],"which":[75],"may":[76],"fail":[77],"to":[78],"achieve":[79],"in":[81,109],"noisy":[82],"environments.":[83],"The":[84],"analysis":[85],"algorithm":[88],"provides":[89],"guarantees":[90],"on":[91],"robustness,":[92],"performance,":[94],"computational":[96],"complexity.":[97],"Simulations":[98],"validate":[99],"effectiveness":[101],"method":[105],"demonstrate":[107],"improvements":[108],"accuracy":[110],"runtime.":[112]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-30T00:00:00"}