{"id":"https://openalex.org/W4377079698","doi":"https://doi.org/10.1109/tcsii.2023.3277696","title":"Online Adaptive Integral Reinforcement Learning for Nonlinear Multi-Input System","display_name":"Online Adaptive Integral Reinforcement Learning for Nonlinear Multi-Input System","publication_year":2023,"publication_date":"2023-05-18","ids":{"openalex":"https://openalex.org/W4377079698","doi":"https://doi.org/10.1109/tcsii.2023.3277696"},"language":"en","primary_location":{"id":"doi:10.1109/tcsii.2023.3277696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsii.2023.3277696","pdf_url":null,"source":{"id":"https://openalex.org/S93916849","display_name":"IEEE Transactions on Circuits & Systems II Express Briefs","issn_l":"1549-7747","issn":["1549-7747","1558-3791"],"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 Circuits and Systems II: Express Briefs","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/A5024107767","display_name":"Yongfeng Lv","orcid":"https://orcid.org/0000-0002-9139-7220"},"institutions":[{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yongfeng Lv","raw_affiliation_strings":["College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, China"],"raw_orcid":"https://orcid.org/0000-0002-9139-7220","affiliations":[{"raw_affiliation_string":"College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, China","institution_ids":["https://openalex.org/I9086337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074537365","display_name":"Huimin Chang","orcid":"https://orcid.org/0000-0001-9352-0846"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimin Chang","raw_affiliation_strings":["School of Mathematical Sciences, Shanxi University, Taiyuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066239914","display_name":"Jun Zhao","orcid":"https://orcid.org/0000-0003-2908-2583"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhao","raw_affiliation_strings":["College of Transportation, Shandong University of Science and Technology, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-2908-2583","affiliations":[{"raw_affiliation_string":"College of Transportation, Shandong University of Science and Technology, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024107767"],"corresponding_institution_ids":["https://openalex.org/I9086337"],"apc_list":null,"apc_paid":null,"fwci":4.8285,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.95923469,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"70","issue":"11","first_page":"4176","last_page":"4180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9922999739646912,"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":0.9922999739646912,"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/T14444","display_name":"Power Systems and Renewable Energy","score":0.9330000281333923,"subfield":{"id":"https://openalex.org/subfields/2102","display_name":"Energy Engineering and Power Technology"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8505823612213135},{"id":"https://openalex.org/keywords/hamilton\u2013jacobi\u2013bellman-equation","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","score":0.788434624671936},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7589589357376099},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6701290607452393},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6424206495285034},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.6403341293334961},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5879613161087036},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.50311678647995},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.429690420627594},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3763829171657562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32750403881073},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3061831593513489},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.254349946975708},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.13871076703071594}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8505823612213135},{"id":"https://openalex.org/C196978813","wikidata":"https://www.wikidata.org/wiki/Q3302775","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","level":3,"score":0.788434624671936},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7589589357376099},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6701290607452393},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6424206495285034},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.6403341293334961},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5879613161087036},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.50311678647995},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.429690420627594},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3763829171657562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32750403881073},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3061831593513489},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.254349946975708},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.13871076703071594},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsii.2023.3277696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsii.2023.3277696","pdf_url":null,"source":{"id":"https://openalex.org/S93916849","display_name":"IEEE Transactions on Circuits & Systems II Express Briefs","issn_l":"1549-7747","issn":["1549-7747","1558-3791"],"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 Circuits and Systems II: Express Briefs","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7968106072","display_name":null,"funder_award_id":"62203279","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G980805614","display_name":null,"funder_award_id":"62103296","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":22,"referenced_works":["https://openalex.org/W1595516097","https://openalex.org/W1970127232","https://openalex.org/W2002260889","https://openalex.org/W2024303516","https://openalex.org/W2068949505","https://openalex.org/W2089904313","https://openalex.org/W2093831009","https://openalex.org/W2105917283","https://openalex.org/W2107674817","https://openalex.org/W2475651303","https://openalex.org/W2568019971","https://openalex.org/W2605603065","https://openalex.org/W2755970611","https://openalex.org/W2968532797","https://openalex.org/W2999863957","https://openalex.org/W3041482332","https://openalex.org/W3093985518","https://openalex.org/W4200008856","https://openalex.org/W4307230233","https://openalex.org/W4309763124","https://openalex.org/W4313476622","https://openalex.org/W6804360855"],"related_works":["https://openalex.org/W2358967034","https://openalex.org/W2155717523","https://openalex.org/W2024495128","https://openalex.org/W4319881067","https://openalex.org/W3130577778","https://openalex.org/W4287328202","https://openalex.org/W1974398766","https://openalex.org/W1499259824","https://openalex.org/W2187721800","https://openalex.org/W2087292112"],"abstract_inverted_index":{"In":[0],"this":[1],"brief":[2],"article,":[3],"a":[4,81],"novel":[5,82],"adaptive":[6],"integral":[7,56],"reinforcement":[8,57],"learning":[9,83],"(AIRL)":[10],"scheme":[11],"is":[12,21,41,85,107],"proposed":[13,121],"for":[14],"the":[15,25,29,36,51,55,64,89,100,116,120],"continuous-time":[16],"(CT)":[17],"system.":[18,34],"Moreover,":[19],"it":[20],"used":[22,48,86,97],"to":[23,49,87,98,114],"learn":[24],"optimal":[26],"controls":[27],"of":[28,39,74],"partially":[30],"unknown":[31,90],"multi-input":[32,40],"nonlinear":[33],"Firstly,":[35],"Nash":[37],"equilibrium":[38],"defined.":[42],"Two":[43],"neural":[44],"networks":[45],"(NN)":[46],"are":[47,77,96,112],"approximate":[50],"cost":[52],"functions":[53],"with":[54,119],"signal,":[58],"which":[59],"can":[60],"avoid":[61],"directly":[62],"solving":[63],"Hamilton\u2013Jacobi\u2013Bellman":[65],"(HJB)":[66],"equation":[67],"such":[68],"that":[69],"dynamic":[70],"information":[71],"and":[72],"derivatives":[73],"NN":[75,91],"activations":[76],"not":[78],"needed.":[79],"Then,":[80],"algorithm":[84],"update":[88],"weights.":[92],"The":[93,103],"studied":[94],"weights":[95],"obtain":[99],"optimum":[101],"multi-policies.":[102],"learned":[104],"weight":[105],"convergence":[106],"proved.":[108],"Finally,":[109],"two":[110],"examples":[111],"presented":[113],"verify":[115],"system":[117],"performance":[118],"AIRL":[122],"scheme.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}