{"id":"https://openalex.org/W2523345745","doi":"https://doi.org/10.1109/tcyb.2015.2477810","title":"Optimal Output-Feedback Control of Unknown Continuous-Time Linear Systems Using Off-policy Reinforcement Learning","display_name":"Optimal Output-Feedback Control of Unknown Continuous-Time Linear Systems Using Off-policy Reinforcement Learning","publication_year":2016,"publication_date":"2016-09-22","ids":{"openalex":"https://openalex.org/W2523345745","doi":"https://doi.org/10.1109/tcyb.2015.2477810","mag":"2523345745","pmid":"https://pubmed.ncbi.nlm.nih.gov/28113995"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2015.2477810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2015.2477810","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5063118155","display_name":"Hamidreza Modares","orcid":"https://orcid.org/0000-0003-0800-5140"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hamidreza Modares","raw_affiliation_strings":["University of Texas at Arlington Research Institute, Fort Worth, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington Research Institute, Fort Worth, TX, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["University of Texas at Arlington Research Institute, Fort Worth, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington Research Institute, Fort Worth, TX, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067046312","display_name":"Zhong\u2010Ping Jiang","orcid":"https://orcid.org/0000-0002-4868-9359"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Ping Jiang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, New York University, Brooklyn, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New York University, Brooklyn, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063118155"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.5807,"has_fulltext":false,"cited_by_count":168,"citation_normalized_percentile":{"value":0.98581371,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"46","issue":"11","first_page":"2401","last_page":"2410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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":1.0,"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9672999978065491,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/algebraic-riccati-equation","display_name":"Algebraic Riccati equation","score":0.7686431407928467},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7449097633361816},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7326568365097046},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6577625870704651},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6478734612464905},{"id":"https://openalex.org/keywords/riccati-equation","display_name":"Riccati equation","score":0.6254928112030029},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5710680484771729},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.5250627398490906},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5249381065368652},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5165508985519409},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4737566113471985},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.46977609395980835},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.46718600392341614},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.39085495471954346},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3208855092525482},{"id":"https://openalex.org/keywords/differential-equation","display_name":"Differential equation","score":0.1369771659374237},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10488691926002502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09427580237388611}],"concepts":[{"id":"https://openalex.org/C13847129","wikidata":"https://www.wikidata.org/wiki/Q4723989","display_name":"Algebraic Riccati equation","level":4,"score":0.7686431407928467},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7449097633361816},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7326568365097046},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6577625870704651},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6478734612464905},{"id":"https://openalex.org/C45473103","wikidata":"https://www.wikidata.org/wiki/Q851503","display_name":"Riccati equation","level":3,"score":0.6254928112030029},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5710680484771729},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.5250627398490906},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5249381065368652},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5165508985519409},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4737566113471985},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.46977609395980835},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.46718600392341614},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.39085495471954346},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3208855092525482},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.1369771659374237},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10488691926002502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09427580237388611},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2015.2477810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2015.2477810","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:28113995","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28113995","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2162513236","display_name":null,"funder_award_id":"ECCS-1230040","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4736517984","display_name":null,"funder_award_id":"ECCS-1101401","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7718234719","display_name":null,"funder_award_id":"W911NF-11-D-0001","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G836722894","display_name":null,"funder_award_id":"N00014-13-1-0562","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8542925397","display_name":null,"funder_award_id":"N000141410718","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W13127292","https://openalex.org/W69446332","https://openalex.org/W164195080","https://openalex.org/W1579168430","https://openalex.org/W1601081659","https://openalex.org/W1968908471","https://openalex.org/W1972243698","https://openalex.org/W1972809999","https://openalex.org/W1984451210","https://openalex.org/W2003183707","https://openalex.org/W2011694027","https://openalex.org/W2012451615","https://openalex.org/W2013895638","https://openalex.org/W2020047580","https://openalex.org/W2024303516","https://openalex.org/W2037025184","https://openalex.org/W2041626001","https://openalex.org/W2058627792","https://openalex.org/W2081514674","https://openalex.org/W2085194340","https://openalex.org/W2121863487","https://openalex.org/W2148439597","https://openalex.org/W2151966330","https://openalex.org/W2156156852","https://openalex.org/W2167939001","https://openalex.org/W2484646121","https://openalex.org/W2487144912","https://openalex.org/W6606695597","https://openalex.org/W6665171041"],"related_works":["https://openalex.org/W2005019312","https://openalex.org/W2547959172","https://openalex.org/W2018296362","https://openalex.org/W2727200542","https://openalex.org/W2002357820","https://openalex.org/W197349956","https://openalex.org/W2997206142","https://openalex.org/W2027962246","https://openalex.org/W2804494800","https://openalex.org/W2116228702"],"abstract_inverted_index":{"A":[0,141],"model-free":[1,173],"off-policy":[2],"reinforcement":[3],"learning":[4],"algorithm":[5,21],"is":[6,57,66,96,114,144,178,193,200,209,219],"developed":[7,146,179],"to":[8,29,72,82,98,147,211,222],"learn":[9],"the":[10,23,30,70,73,77,83,93,100,103,118,129,136,139,164,182,185,189,196,204],"optimal":[11,33,49,104,110],"output-feedback":[12],"(OPFB)":[13],"solution":[14,71,81],"for":[15,36,47,92],"linear":[16],"continuous-time":[17],"systems.":[18],"The":[19,216],"proposed":[20,197,217],"has":[22],"important":[24],"feature":[25],"of":[26,32,79,102,135,138,184],"being":[27],"applicable":[28],"design":[31],"OPFB":[34,111,176,198,206],"controllers":[35],"both":[37,48],"regulation":[38,50,225],"and":[39,51,59,88,152,226],"tracking":[40,228],"problems.":[41],"To":[42,107],"provide":[43],"a":[44,53,60,80,133,149,172,212,224,227],"unified":[45],"framework":[46],"tracking,":[52],"discounted":[54,61,84],"performance":[55],"function":[56],"employed":[58],"algebraic":[62],"Riccati":[63],"equation":[64,143],"(ARE)":[65],"derived":[67],"which":[68],"gives":[69],"problem.":[74,229],"Conditions":[75],"on":[76,128,163],"existence":[78],"ARE":[85],"are":[86],"provided":[87],"an":[89,109,154],"upper":[90],"bound":[91],"discount":[94],"factor":[95],"found":[97],"assure":[99],"stability":[101],"control":[105,150,214],"solution.":[106],"develop":[108],"controller,":[112],"it":[113,208],"first":[115],"shown":[116,194],"that":[117,195],"system":[119,130,165,186,190],"state":[120,187],"can":[121],"be":[122],"constructed":[123],"using":[124,158,168],"some":[125,160],"limited":[126,161],"observations":[127,162],"output":[131],"over":[132],"period":[134],"history":[137],"system.":[140],"Bellman":[142,170],"then":[145],"evaluate":[148],"policy":[151,156],"find":[153],"improved":[155],"simultaneously":[157],"only":[159],"output.":[166],"Then,":[167],"this":[169],"equation,":[171],"Off-policy":[174],"RL-based":[175],"controller":[177],"without":[180],"requiring":[181],"knowledge":[183],"or":[188],"dynamics.":[191],"It":[192],"method":[199,218],"more":[201],"powerful":[202],"than":[203],"static":[205],"as":[207],"equivalent":[210],"state-feedback":[213],"policy.":[215],"successfully":[220],"used":[221],"solve":[223]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":5}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}