{"id":"https://openalex.org/W2896495862","doi":"https://doi.org/10.1109/ijcnn.2018.8489343","title":"Off-Policy Integral Reinforcement Learning for Semi-Global Constrained Output Regulation of Continuous-Time Linear Systems","display_name":"Off-Policy Integral Reinforcement Learning for Semi-Global Constrained Output Regulation of Continuous-Time Linear Systems","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2896495862","doi":"https://doi.org/10.1109/ijcnn.2018.8489343","mag":"2896495862"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2018.8489343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5053342436","display_name":"Yongliang Yang","orcid":"https://orcid.org/0000-0002-3144-8604"},"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":"Yongliang Yang","raw_affiliation_strings":["School of Automation & Electrical Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation & Electrical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101499468","display_name":"Xianzhong Chen","orcid":"https://orcid.org/0000-0003-4113-6994"},"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":false,"raw_author_name":"Xianzhong Chen","raw_affiliation_strings":["School of Automation & Electrical Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation & Electrical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101512101","display_name":"Yixin Yin","orcid":"https://orcid.org/0000-0001-6056-8878"},"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":false,"raw_author_name":"Yixin Yin","raw_affiliation_strings":["School of Automation & Electrical Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation & Electrical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038037619","display_name":"Donald C. Wunsch","orcid":"https://orcid.org/0000-0002-9726-9051"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donald C. Wunsch","raw_affiliation_strings":["Department of Electrical & Computer Engineering, Missouri University of Science & Technology, Rolla, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, Missouri University of Science & Technology, Rolla, USA","institution_ids":["https://openalex.org/I20382870"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053342436"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":0.2019,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55080767,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9800000190734863,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9789999723434448,"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/algebraic-riccati-equation","display_name":"Algebraic Riccati equation","score":0.7614877223968506},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7550643682479858},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7030971050262451},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5964351892471313},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5741884112358093},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5424104928970337},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.523933470249176},{"id":"https://openalex.org/keywords/riccati-equation","display_name":"Riccati equation","score":0.4919597804546356},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.430145263671875},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3740294575691223},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.31993505358695984},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30264925956726074},{"id":"https://openalex.org/keywords/partial-differential-equation","display_name":"Partial differential equation","score":0.1603723168373108},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14132606983184814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1012285053730011}],"concepts":[{"id":"https://openalex.org/C13847129","wikidata":"https://www.wikidata.org/wiki/Q4723989","display_name":"Algebraic Riccati equation","level":4,"score":0.7614877223968506},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7550643682479858},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7030971050262451},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5964351892471313},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5741884112358093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5424104928970337},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.523933470249176},{"id":"https://openalex.org/C45473103","wikidata":"https://www.wikidata.org/wiki/Q851503","display_name":"Riccati equation","level":3,"score":0.4919597804546356},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.430145263671875},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3740294575691223},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.31993505358695984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30264925956726074},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.1603723168373108},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14132606983184814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1012285053730011},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2018.8489343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W114979488","https://openalex.org/W296003671","https://openalex.org/W610804881","https://openalex.org/W1614417283","https://openalex.org/W1972243698","https://openalex.org/W2012451615","https://openalex.org/W2013895638","https://openalex.org/W2068202815","https://openalex.org/W2085194340","https://openalex.org/W2097253853","https://openalex.org/W2108286682","https://openalex.org/W2108695617","https://openalex.org/W2117668711","https://openalex.org/W2118589723","https://openalex.org/W2119925384","https://openalex.org/W2132858840","https://openalex.org/W2148439597","https://openalex.org/W2151966330","https://openalex.org/W2165538017","https://openalex.org/W2172291674","https://openalex.org/W2173085035","https://openalex.org/W2333120204","https://openalex.org/W2475651303","https://openalex.org/W2484646121","https://openalex.org/W2567168244","https://openalex.org/W2580629550","https://openalex.org/W2585299106","https://openalex.org/W2754627144","https://openalex.org/W2789789879","https://openalex.org/W2793914020","https://openalex.org/W2798534591","https://openalex.org/W4213367573","https://openalex.org/W4249919931","https://openalex.org/W6750297707"],"related_works":["https://openalex.org/W2005019312","https://openalex.org/W2105459831","https://openalex.org/W1546579375","https://openalex.org/W2127238600","https://openalex.org/W1563296412","https://openalex.org/W16457797","https://openalex.org/W2792258377","https://openalex.org/W1530596433","https://openalex.org/W2096105566","https://openalex.org/W1993854306"],"abstract_inverted_index":{"This":[0],"paper":[1,86],"presents":[2],"a":[3,108,123],"data-driven":[4],"method":[5,95],"based":[6,40],"on":[7,41,118],"off-policy":[8],"integral":[9],"reinforcement":[10],"learning":[11],"to":[12,49,76,128,136],"solve":[13,137],"the":[14,32,50,56,67,78,81,93,119,130,133,138],"semi-global":[15,139],"output":[16,35,140],"regulation":[17,36,141],"of":[18,27,55,103,132,142],"continuous-time":[19,143],"linear":[20,110,144],"systems":[21,145],"with":[22,101,112,146],"input":[23,33,147],"saturation.":[24,148],"A":[25],"family":[26],"state":[28],"feedback":[29,98],"laws":[30],"for":[31],"constrained":[34],"problem":[37],"is":[38,59,73,87,90,126],"designed":[39],"solving":[42],"an":[43],"algebraic":[44],"Riccati":[45],"equation.":[46],"In":[47],"contrast":[48],"existing":[51],"methods,":[52],"complete":[53],"knowledge":[54],"system":[57,111],"dynamics":[58],"no":[60],"longer":[61],"required":[62],"in":[63,84],"this":[64,85],"paper.":[65],"Instead,":[66],"data":[68],"collected":[69],"from":[70],"online":[71],"implementation":[72],"efficiently":[74],"utilized":[75],"design":[77,83],"controller.":[79],"Therefore,":[80],"controller":[82],"data-driven.":[88],"It":[89],"shown":[91],"that":[92],"presented":[94,134],"can":[96],"find":[97],"control":[99],"inputs":[100],"constraint":[102],"amplitude":[104],"saturation":[105],"and":[106],"stabilize":[107],"given":[109],"all":[113],"its":[114],"poles":[115],"inside":[116],"or":[117],"imaginary":[120],"axis.":[121],"Finally,":[122],"simulation":[124],"example":[125],"conducted":[127],"show":[129],"validity":[131],"approach":[135]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}