{"id":"https://openalex.org/W4399778479","doi":"https://doi.org/10.1080/00207721.2024.2364289","title":"Infinite-time robust optimal output tracking of continuous-time linear systems using undiscounted reinforcement learning","display_name":"Infinite-time robust optimal output tracking of continuous-time linear systems using undiscounted reinforcement learning","publication_year":2024,"publication_date":"2024-06-18","ids":{"openalex":"https://openalex.org/W4399778479","doi":"https://doi.org/10.1080/00207721.2024.2364289"},"language":"en","primary_location":{"id":"doi:10.1080/00207721.2024.2364289","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207721.2024.2364289","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/A5055949918","display_name":"Ali Amirparast","orcid":"https://orcid.org/0000-0003-3812-6488"},"institutions":[{"id":"https://openalex.org/I86958956","display_name":"Ferdowsi University of Mashhad","ror":"https://ror.org/00g6ka752","country_code":"IR","type":"education","lineage":["https://openalex.org/I86958956"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ali Amirparast","raw_affiliation_strings":["Department of Electrical Engineering, Ferdowsi University of Mashhad, Mashhad, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Ferdowsi University of Mashhad, Mashhad, Iran","institution_ids":["https://openalex.org/I86958956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077074758","display_name":"Seyed Kamal Hosseini Sani","orcid":"https://orcid.org/0000-0002-1452-9453"},"institutions":[{"id":"https://openalex.org/I86958956","display_name":"Ferdowsi University of Mashhad","ror":"https://ror.org/00g6ka752","country_code":"IR","type":"education","lineage":["https://openalex.org/I86958956"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"S. Kamal Hosseini Sani","raw_affiliation_strings":["Department of Electrical Engineering, Ferdowsi University of Mashhad, Mashhad, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Ferdowsi University of Mashhad, Mashhad, Iran","institution_ids":["https://openalex.org/I86958956"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5077074758"],"corresponding_institution_ids":["https://openalex.org/I86958956"],"apc_list":null,"apc_paid":null,"fwci":0.8647,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75112399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"55","issue":"14","first_page":"2933","last_page":"2951"},"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9922000169754028,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9646000266075134,"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":0.7286304235458374},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7236664295196533},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5056290626525879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47863808274269104},{"id":"https://openalex.org/keywords/output-feedback","display_name":"Output feedback","score":0.4460490643978119},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.40120819211006165},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3431241810321808},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3319806158542633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2875692844390869}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7286304235458374},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7236664295196533},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5056290626525879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47863808274269104},{"id":"https://openalex.org/C3018623182","wikidata":"https://www.wikidata.org/wiki/Q154021","display_name":"Output feedback","level":3,"score":0.4460490643978119},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.40120819211006165},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3431241810321808},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3319806158542633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2875692844390869},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/00207721.2024.2364289","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207721.2024.2364289","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:14:p:2933-2951","is_oa":false,"landing_page_url":"http://hdl.handle.net/10.1080/00207721.2024.2364289","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W560518094","https://openalex.org/W1522531528","https://openalex.org/W1614417283","https://openalex.org/W1994765701","https://openalex.org/W2011694027","https://openalex.org/W2012451615","https://openalex.org/W2013895638","https://openalex.org/W2024303516","https://openalex.org/W2032704188","https://openalex.org/W2035003264","https://openalex.org/W2037025184","https://openalex.org/W2054073213","https://openalex.org/W2061714571","https://openalex.org/W2080092370","https://openalex.org/W2111034649","https://openalex.org/W2148295141","https://openalex.org/W2152161277","https://openalex.org/W2167757582","https://openalex.org/W2333120204","https://openalex.org/W2484646121","https://openalex.org/W2501776475","https://openalex.org/W2523345745","https://openalex.org/W2580629550","https://openalex.org/W2727279496","https://openalex.org/W2789465846","https://openalex.org/W2800330509","https://openalex.org/W2807176303","https://openalex.org/W3090211896","https://openalex.org/W3109894257","https://openalex.org/W4205496101","https://openalex.org/W4206318793","https://openalex.org/W4206759694","https://openalex.org/W4241431509","https://openalex.org/W4285067142","https://openalex.org/W4296121324","https://openalex.org/W4308861704","https://openalex.org/W4380203438","https://openalex.org/W4389726203","https://openalex.org/W4394722009","https://openalex.org/W6634206955","https://openalex.org/W7014788697"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"This":[0],"research":[1],"paper":[2,58],"focuses":[3],"on":[4,156],"addressing":[5],"the":[6,24,35,50,70,74,88,108,146,174,179,191],"challenge":[7],"of":[8,73,87,110,145,160,178],"infinite-time":[9],"linear":[10,16],"quadratic":[11],"tracking":[12],"control":[13,81,127,192],"(LQT)":[14],"for":[15,98],"systems":[17,99],"with":[18,100],"parametric":[19,185],"uncertainty.":[20],"Traditional":[21],"solutions":[22],"to":[23,33,106,113,166],"LQT":[25],"problem":[26],"often":[27],"involve":[28],"using":[29,63,131],"a":[30,80,114,124,140,161,167],"discount":[31],"factor":[32],"prevent":[34],"cost":[36,66],"function":[37,67],"from":[38],"growing":[39],"unbounded":[40],"over":[41],"time.":[42],"However,":[43,97],"this":[44,55,57,122],"approach":[45,62],"can":[46],"introduce":[47],"instability":[48],"in":[49,139,183,190],"closed-loop":[51,76],"system.":[52,77,193],"To":[53,78,120],"overcome":[54],"issue,":[56],"proposes":[59],"an":[60,64,157],"alternative":[61],"undiscounted":[65],"that":[68,103],"ensures":[69],"asymptotic":[71],"stability":[72,189],"uncertain":[75,101,158],"design":[79],"scheme":[82],"without":[83],"requiring":[84],"precise":[85],"knowledge":[86],"system":[89],"dynamics,":[90],"reinforcement":[91,135],"learning":[92,136],"(RL)":[93],"algorithms":[94,112],"are":[95],"employed.":[96],"parameters":[102],"may":[104],"lead":[105],"instability,":[107],"convergence":[109],"RL":[111],"stabilising":[115],"solution":[116],"is":[117,129,151],"not":[118],"guaranteed.":[119],"address":[121],"limitation,":[123],"robust":[125,148,180],"optimal":[126,149,181],"structure":[128],"developed":[130],"on-policy":[132],"and":[133,176,187],"off-policy":[134],"algorithms,":[137],"resulting":[138],"model-free":[141],"controller.":[142],"The":[143],"effectiveness":[144],"proposed":[147],"controller":[150,182],"validated":[152],"through":[153],"comparative":[154],"simulations":[155,172],"model":[159],"DC\u2013DC":[162],"buck":[163],"converter":[164],"connected":[165],"constant":[168],"power":[169],"load.":[170],"These":[171],"demonstrate":[173],"advantages":[175],"benefits":[177],"handling":[184],"uncertainty":[186],"ensuring":[188]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2025-10-10T00:00:00"}