{"id":"https://openalex.org/W2787184676","doi":"https://doi.org/10.1109/ssci.2017.8280874","title":"Event-triggered integral reinforcement learning for nonlinear continuous-time systems","display_name":"Event-triggered integral reinforcement learning for nonlinear continuous-time systems","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2787184676","doi":"https://doi.org/10.1109/ssci.2017.8280874","mag":"2787184676"},"language":"en","primary_location":{"id":"doi:10.1109/ssci.2017.8280874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2017.8280874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5049454999","display_name":"Qichao Zhang","orcid":"https://orcid.org/0000-0001-9747-391X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qichao Zhang","raw_affiliation_strings":["The state Key Laboratory of Management and Control for Complex Systems, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"The state Key Laboratory of Management and Control for Complex Systems, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["The state Key Laboratory of Management and Control for Complex Systems, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"The state Key Laboratory of Management and Control for Complex Systems, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049454999"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.2271,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59470101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","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":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/T12047","display_name":"Viral Infections and Vectors","score":0.9693999886512756,"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":0.9434000253677368,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8690131902694702},{"id":"https://openalex.org/keywords/hamilton\u2013jacobi\u2013bellman-equation","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","score":0.8679782152175903},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7483987808227539},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.7198193073272705},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.678368091583252},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6371235847473145},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5968377590179443},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5753626823425293},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5424755811691284},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4837617874145508},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4796631634235382},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42976027727127075},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.40589505434036255},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.33716708421707153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2923685312271118},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27663350105285645}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8690131902694702},{"id":"https://openalex.org/C196978813","wikidata":"https://www.wikidata.org/wiki/Q3302775","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","level":3,"score":0.8679782152175903},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7483987808227539},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7198193073272705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.678368091583252},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6371235847473145},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5968377590179443},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5753626823425293},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5424755811691284},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4837617874145508},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4796631634235382},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42976027727127075},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40589505434036255},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.33716708421707153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2923685312271118},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27663350105285645},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci.2017.8280874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2017.8280874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","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":24,"referenced_works":["https://openalex.org/W1891098503","https://openalex.org/W1972809999","https://openalex.org/W1978921618","https://openalex.org/W2012451615","https://openalex.org/W2019478222","https://openalex.org/W2055091851","https://openalex.org/W2081514674","https://openalex.org/W2102933137","https://openalex.org/W2121863487","https://openalex.org/W2183137222","https://openalex.org/W2291165559","https://openalex.org/W2312229020","https://openalex.org/W2319074362","https://openalex.org/W2405379562","https://openalex.org/W2480536132","https://openalex.org/W2538000344","https://openalex.org/W2586495351","https://openalex.org/W2606548817","https://openalex.org/W3150098721","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W6645043749","https://openalex.org/W6713924959","https://openalex.org/W6728719408"],"related_works":["https://openalex.org/W2032834442","https://openalex.org/W3153900688","https://openalex.org/W2115544975","https://openalex.org/W2902017027","https://openalex.org/W1654696814","https://openalex.org/W4291598237","https://openalex.org/W2766998270","https://openalex.org/W3168988147","https://openalex.org/W4239477580","https://openalex.org/W4292330635"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"the":[3,8,28,31,37,45,53,60,74,79,93,96],"optimal":[4,75,80],"control":[5,47],"problem":[6],"for":[7],"continuous-time":[9],"nonlinear":[10],"systems":[11],"with":[12,82],"partially":[13],"unknown":[14],"dynamics":[15,41],"is":[16,24,42,49,70,89],"investigated.":[17],"The":[18],"event-triggered":[19,46],"internal":[20,40],"reinforcement":[21],"learning":[22],"(IRL)":[23],"proposed":[25,97],"to":[26,51,72,91],"approach":[27,73],"solution":[29],"of":[30,39,95],"Hamilton-Jacobi-Bellman":[32],"(HJB)":[33],"equation.":[34],"Note":[35],"that":[36],"knowledge":[38],"relaxed,":[43],"and":[44,56,78],"scheme":[48],"adopted":[50],"reduce":[52],"computational":[54],"burden":[55],"communication":[57],"resources.":[58],"For":[59],"online":[61],"implementation":[62],"purpose,":[63],"a":[64,86],"single-critic":[65],"neural":[66],"network":[67],"(NN)":[68],"structure":[69],"constructed":[71],"value":[76],"function":[77],"policy":[81],"convergence":[83],"analysis.":[84],"Finally,":[85],"simulation":[87],"example":[88],"provided":[90],"demonstrate":[92],"effectiveness":[94],"algorithm.":[98]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}