{"id":"https://openalex.org/W4388199748","doi":"https://doi.org/10.1080/00207721.2023.2272217","title":"Adaptive output feedback reinforcement learning control for continuous time switched stochastic nonlinear systems with unknown control coefficients and full-state constraints","display_name":"Adaptive output feedback reinforcement learning control for continuous time switched stochastic nonlinear systems with unknown control coefficients and full-state constraints","publication_year":2023,"publication_date":"2023-10-25","ids":{"openalex":"https://openalex.org/W4388199748","doi":"https://doi.org/10.1080/00207721.2023.2272217"},"language":"en","primary_location":{"id":"doi:10.1080/00207721.2023.2272217","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207721.2023.2272217","pdf_url":null,"source":{"id":"https://openalex.org/S129640837","display_name":"International Journal of Systems Science","issn_l":"0020-7721","issn":["0020-7721","1464-5319"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Systems Science","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/A5077610461","display_name":"Hongyao Li","orcid":"https://orcid.org/0000-0002-6939-3290"},"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":"Hongyao Li","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, People's Republic of China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113403260","display_name":"Fuli Wang","orcid":"https://orcid.org/0000-0002-7468-528X"},"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":true,"raw_author_name":"Fuli Wang","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries (Northeastern University), College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries (Northeastern University), College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, People's Republic of China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5113403260"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":1.0363,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80384088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"55","issue":"2","first_page":"332","last_page":"354"},"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9986000061035156,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9891999959945679,"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/control-theory","display_name":"Control theory (sociology)","score":0.7898803353309631},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6159332990646362},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.572130560874939},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5568324327468872},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5527948141098022},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.544261634349823},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47355666756629944},{"id":"https://openalex.org/keywords/output-feedback","display_name":"Output feedback","score":0.4372090697288513},{"id":"https://openalex.org/keywords/feedback-control","display_name":"Feedback control","score":0.41707485914230347},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.41537004709243774},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.23762169480323792},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17587316036224365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15366867184638977},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11145138740539551}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7898803353309631},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6159332990646362},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.572130560874939},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5568324327468872},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5527948141098022},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.544261634349823},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47355666756629944},{"id":"https://openalex.org/C3018623182","wikidata":"https://www.wikidata.org/wiki/Q154021","display_name":"Output feedback","level":3,"score":0.4372090697288513},{"id":"https://openalex.org/C3018651601","wikidata":"https://www.wikidata.org/wiki/Q183635","display_name":"Feedback control","level":2,"score":0.41707485914230347},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41537004709243774},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.23762169480323792},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17587316036224365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15366867184638977},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11145138740539551},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/00207721.2023.2272217","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207721.2023.2272217","pdf_url":null,"source":{"id":"https://openalex.org/S129640837","display_name":"International Journal of Systems Science","issn_l":"0020-7721","issn":["0020-7721","1464-5319"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Systems Science","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:taf:tsysxx:v:55:y:2024:i:2:p:332-354","is_oa":false,"landing_page_url":"http://hdl.handle.net/10.1080/00207721.2023.2272217","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1054396882","https://openalex.org/W1900371862","https://openalex.org/W1982132986","https://openalex.org/W1986024064","https://openalex.org/W1995299431","https://openalex.org/W2008612678","https://openalex.org/W2013728047","https://openalex.org/W2024197616","https://openalex.org/W2024303516","https://openalex.org/W2051671655","https://openalex.org/W2077195478","https://openalex.org/W2089904313","https://openalex.org/W2121672983","https://openalex.org/W2162820017","https://openalex.org/W2330892803","https://openalex.org/W2411666193","https://openalex.org/W2471350850","https://openalex.org/W2512542300","https://openalex.org/W2536699117","https://openalex.org/W2601030518","https://openalex.org/W2733294185","https://openalex.org/W2763038559","https://openalex.org/W2963402165","https://openalex.org/W3094395473","https://openalex.org/W3121132815","https://openalex.org/W3124444594","https://openalex.org/W3174508330","https://openalex.org/W3196774968","https://openalex.org/W4206009461","https://openalex.org/W4206295944","https://openalex.org/W4206318793","https://openalex.org/W4206422821","https://openalex.org/W4206759694","https://openalex.org/W4214672868","https://openalex.org/W4225718765","https://openalex.org/W4245328890","https://openalex.org/W4249368235","https://openalex.org/W4283314984","https://openalex.org/W4285185563","https://openalex.org/W4297399558","https://openalex.org/W4312434028","https://openalex.org/W4312688468","https://openalex.org/W4383337173"],"related_works":["https://openalex.org/W2334516743","https://openalex.org/W2486306719","https://openalex.org/W2106487132","https://openalex.org/W2369282358","https://openalex.org/W2482257683","https://openalex.org/W2001368270","https://openalex.org/W3022029778","https://openalex.org/W2019249007","https://openalex.org/W4287553357","https://openalex.org/W2800406697"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"the":[3,18,43,61,66,73,78,85,89,92,101,118],"problem":[4],"of":[5,36,91,117],"adaptive":[6,79],"neural":[7],"network":[8],"(NN)":[9],"reinforcement":[10],"learning":[11,68],"(RL)":[12],"tracking":[13,62,93],"control":[14,28,45,75],"is":[15,82,98,121],"investigated":[16],"for":[17],"continuous":[19],"time":[20,104],"(CT)":[21],"switched":[22,48],"stochastic":[23],"nonlinear":[24],"systems":[25],"with":[26],"unknown":[27,44],"coefficients":[29],"and":[30,47,72,95,107],"full-state":[31],"constraints.":[32],"First,":[33],"a":[34],"set":[35],"reconstructed":[37,56],"states":[38],"are":[39,51],"defined":[40],"to":[41,53,59],"handle":[42],"coefficients,":[46],"state":[49],"observers":[50],"developed":[52,83],"estimate":[54],"unmeasurable":[55],"states.":[57],"Then,":[58],"improve":[60],"performance,":[63],"based":[64],"on":[65],"minimal":[67],"parameter":[69],"(MLP)":[70],"method":[71,106],"RL":[74,80],"design":[76],"technique,":[77],"controller":[81],"by":[84,123],"backstepping":[86],"method.":[87],"Finally,":[88],"boundedness":[90],"error":[94],"all":[96],"signals":[97],"demonstrated":[99],"via":[100],"average":[102],"dwell":[103],"(ADT)":[105],"tangent":[108],"type":[109],"time-varying":[110],"barrier":[111],"multiple":[112],"Lyapunov":[113],"functions.":[114],"The":[115],"effectiveness":[116],"proposed":[119],"scheme":[120],"verified":[122],"two":[124],"examples.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-10-10T00:00:00"}