{"id":"https://openalex.org/W1991119064","doi":"https://doi.org/10.1109/tcyb.2015.2421338","title":"Off-Policy Actor-Critic Structure for Optimal Control of Unknown Systems With Disturbances","display_name":"Off-Policy Actor-Critic Structure for Optimal Control of Unknown Systems With Disturbances","publication_year":2015,"publication_date":"2015-04-28","ids":{"openalex":"https://openalex.org/W1991119064","doi":"https://doi.org/10.1109/tcyb.2015.2421338","mag":"1991119064","pmid":"https://pubmed.ncbi.nlm.nih.gov/25935054"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2015.2421338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2015.2421338","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/A5040323322","display_name":"Ruizhuo Song","orcid":"https://orcid.org/0000-0002-6693-2738"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruizhuo Song","raw_affiliation_strings":["School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087825639","display_name":"Qinglai Wei","orcid":"https://orcid.org/0000-0001-7002-9800"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinglai Wei","raw_affiliation_strings":["The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100625792","display_name":"Huaguang Zhang","orcid":"https://orcid.org/0000-0002-2375-9824"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaguang Zhang","raw_affiliation_strings":["School of Information Science and Engineering, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040323322"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":26.174,"has_fulltext":false,"cited_by_count":230,"citation_normalized_percentile":{"value":0.99746635,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"46","issue":"5","first_page":"1041","last_page":"1050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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":0.9998999834060669,"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/T12047","display_name":"Viral Infections and Vectors","score":0.9700999855995178,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9638000130653381,"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/control-theory","display_name":"Control theory (sociology)","score":0.736728847026825},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.6068388819694519},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5946726202964783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5799136757850647},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5740769505500793},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5621161460876465},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5470215082168579},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4860568344593048},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4275958240032196},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3759266138076782},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.372506320476532},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36472585797309875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23205512762069702},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.12346082925796509},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08597061038017273}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.736728847026825},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.6068388819694519},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5946726202964783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5799136757850647},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5740769505500793},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5621161460876465},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5470215082168579},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4860568344593048},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4275958240032196},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3759266138076782},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.372506320476532},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36472585797309875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23205512762069702},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.12346082925796509},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08597061038017273},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2015.2421338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2015.2421338","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:25935054","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25935054","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":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1801858584","display_name":null,"funder_award_id":"FRF-TP-14-119A2","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2966638085","display_name":null,"funder_award_id":"4132078","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G5586296773","display_name":null,"funder_award_id":"4143065","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G6900036684","display_name":null,"funder_award_id":"61120106011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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/G7950651630","display_name":null,"funder_award_id":"ECCS-1128050","funder_id":"https://openalex.org/F4320337392","funder_display_name":"Division of Electrical, Communications and Cyber Systems"},{"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/G8966910550","display_name":null,"funder_award_id":"2013M530527","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"},{"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":46,"referenced_works":["https://openalex.org/W1517236425","https://openalex.org/W1595516097","https://openalex.org/W1972809999","https://openalex.org/W1983089547","https://openalex.org/W1988194407","https://openalex.org/W1999213690","https://openalex.org/W2011310556","https://openalex.org/W2012451615","https://openalex.org/W2012655144","https://openalex.org/W2013895638","https://openalex.org/W2014558518","https://openalex.org/W2014729048","https://openalex.org/W2020192303","https://openalex.org/W2023465281","https://openalex.org/W2024303516","https://openalex.org/W2033030672","https://openalex.org/W2047090868","https://openalex.org/W2048687352","https://openalex.org/W2052305027","https://openalex.org/W2058538513","https://openalex.org/W2059084100","https://openalex.org/W2060605484","https://openalex.org/W2078977470","https://openalex.org/W2080504737","https://openalex.org/W2081758070","https://openalex.org/W2083283377","https://openalex.org/W2087063454","https://openalex.org/W2088246243","https://openalex.org/W2093831009","https://openalex.org/W2098035803","https://openalex.org/W2100276679","https://openalex.org/W2101116544","https://openalex.org/W2102933137","https://openalex.org/W2104843094","https://openalex.org/W2108286682","https://openalex.org/W2121863487","https://openalex.org/W2138131694","https://openalex.org/W2139416664","https://openalex.org/W2142620596","https://openalex.org/W2148439597","https://openalex.org/W2151966330","https://openalex.org/W2152161277","https://openalex.org/W2156629001","https://openalex.org/W2171754584","https://openalex.org/W2495714227","https://openalex.org/W3150098721"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"An":[0],"optimal":[1,114],"control":[2,115],"method":[3,116],"is":[4,22,31,52,80,83,102],"developed":[5],"for":[6,117],"unknown":[7,11,58,74,118],"continuous-time":[8],"systems":[9,119],"with":[10,120],"disturbances":[12,77],"in":[13],"this":[14],"paper.":[15],"The":[16,105],"integral":[17],"reinforcement":[18],"learning":[19,30],"(IRL)":[20],"algorithm":[21],"presented":[23],"to":[24,33,37,45],"obtain":[25],"the":[26,35,71,86,99,109,112],"iterative":[27],"control.":[28],"Off-policy":[29],"used":[32,44],"allow":[34],"dynamics":[36],"be":[38,67],"completely":[39],"unknown.":[40],"Neural":[41],"networks":[42],"are":[43,57,89],"construct":[46],"critic":[47],"and":[48],"action":[49],"networks.":[50],"It":[51,82],"shown":[53],"that":[54,85],"if":[55],"there":[56],"disturbances,":[59,75],"off-policy":[60],"IRL":[61],"may":[62,66],"not":[63],"converge":[64],"or":[65],"biased.":[68],"For":[69],"reducing":[70],"influence":[72],"of":[73,98,111],"a":[76],"compensation":[78],"controller":[79],"added.":[81],"proven":[84],"weight":[87],"errors":[88],"uniformly":[90],"ultimately":[91],"bounded":[92],"based":[93],"on":[94],"Lyapunov":[95],"techniques.":[96],"Convergence":[97],"Hamiltonian":[100],"function":[101],"also":[103],"proven.":[104],"simulation":[106],"study":[107],"demonstrates":[108],"effectiveness":[110],"proposed":[113],"disturbances.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":32},{"year":2016,"cited_by_count":19},{"year":2015,"cited_by_count":2}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}