{"id":"https://openalex.org/W4401328219","doi":"https://doi.org/10.1109/tsmc.2024.3431453","title":"Reinforcement Learning for Finite-Horizon H\u221e Tracking Control of Unknown Discrete Linear Time-Varying System","display_name":"Reinforcement Learning for Finite-Horizon H\u221e Tracking Control of Unknown Discrete Linear Time-Varying System","publication_year":2024,"publication_date":"2024-08-05","ids":{"openalex":"https://openalex.org/W4401328219","doi":"https://doi.org/10.1109/tsmc.2024.3431453"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2024.3431453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2024.3431453","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","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/A5036740005","display_name":"Linwei Ye","orcid":"https://orcid.org/0000-0002-4093-5498"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linwei Ye","raw_affiliation_strings":["Key Laboratory of Advanced Process Control of Light Industry (Ministry of Education), Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0002-4093-5498","affiliations":[{"raw_affiliation_string":"Key Laboratory of Advanced Process Control of Light Industry (Ministry of Education), Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035678026","display_name":"Zhonggai Zhao","orcid":"https://orcid.org/0000-0002-4508-4979"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhonggai Zhao","raw_affiliation_strings":["Key Laboratory of Advanced Process Control of Light Industry (Ministry of Education), Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0002-4508-4979","affiliations":[{"raw_affiliation_string":"Key Laboratory of Advanced Process Control of Light Industry (Ministry of Education), Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100394563","display_name":"Fei Liu","orcid":"https://orcid.org/0000-0001-7160-2605"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Liu","raw_affiliation_strings":["Institute of Automation, Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0001-7160-2605","affiliations":[{"raw_affiliation_string":"Institute of Automation, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5637,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90622363,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"54","issue":"10","first_page":"6385","last_page":"6396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9341999888420105,"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":0.9341999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7157155275344849},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.6660662889480591},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.6565780639648438},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.574964702129364},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5714886784553528},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5180254578590393},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4618128538131714},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4171103239059448},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3811849355697632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2444206178188324},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15236401557922363},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09104868769645691},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.0662970244884491}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7157155275344849},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.6660662889480591},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.6565780639648438},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.574964702129364},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5714886784553528},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5180254578590393},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4618128538131714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4171103239059448},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3811849355697632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2444206178188324},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15236401557922363},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09104868769645691},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0662970244884491},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2024.3431453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2024.3431453","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5426409165","display_name":null,"funder_award_id":"61833007","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W639062186","https://openalex.org/W1500134124","https://openalex.org/W1972243698","https://openalex.org/W2005437559","https://openalex.org/W2013895638","https://openalex.org/W2041626001","https://openalex.org/W2073990179","https://openalex.org/W2332672415","https://openalex.org/W2498694880","https://openalex.org/W2550394442","https://openalex.org/W2564717627","https://openalex.org/W2766143943","https://openalex.org/W2789465846","https://openalex.org/W2883806155","https://openalex.org/W2885245712","https://openalex.org/W2907944110","https://openalex.org/W2912832158","https://openalex.org/W2931650895","https://openalex.org/W2942227124","https://openalex.org/W2942517366","https://openalex.org/W2964196486","https://openalex.org/W2982396425","https://openalex.org/W2982570199","https://openalex.org/W2997938989","https://openalex.org/W3022710553","https://openalex.org/W3023586494","https://openalex.org/W3027032642","https://openalex.org/W3110708742","https://openalex.org/W3111143034","https://openalex.org/W3120441334","https://openalex.org/W3124444594","https://openalex.org/W3155168014","https://openalex.org/W3211437739","https://openalex.org/W3213059358","https://openalex.org/W4200325667","https://openalex.org/W4206824914","https://openalex.org/W4210732025","https://openalex.org/W4214717370","https://openalex.org/W4255333822","https://openalex.org/W4285240592","https://openalex.org/W4319993323","https://openalex.org/W6804409665"],"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/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W4391331176"],"abstract_inverted_index":{"This":[0],"article":[1],"considers":[2],"the":[3,40,53,111,119,122,128,131,153,157,174,177],"finite-horizon":[4,72,90,120],"H<inline-formula":[5,41,81,91],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[6,42,82,92],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[7,43,83,93],"<tex-math":[8,44,84,94],"notation=\"LaTeX\">$_{\\infty":[9,45,85,95],"}$":[10,46,86,96],"</tex-math></inline-formula>":[11,47,87,97],"tracking":[12,88,98],"problem":[13],"for":[14,145,150],"a":[15,101,143],"class":[16],"of":[17,55,130,160,176],"discrete":[18],"linear":[19],"time-varying":[20,75,102,116],"systems.":[21,76],"Two":[22,167],"reinforcement":[23],"learning":[24],"(RL)":[25],"methods\u2014policy":[26],"iteration":[27,165],"(PI)":[28],"and":[29,64,67,163],"Q-learning\u2014are":[30],"proposed":[31,154,178],"to":[32,79,113,172],"solve":[33],"this":[34,106],"problem.":[35],"The":[36],"latter":[37],"can":[38],"obtain":[39],"controller":[48],"without":[49],"system":[50],"dynamics.":[51],"In":[52,77],"field":[54],"RL":[56],"control,":[57,89],"most":[58],"studies":[59,69],"focus":[60],"on":[61],"infinite-horizon":[62,80],"control":[63,73,99,136,148],"time-invariant":[65],"systems,":[66],"few":[68],"have":[70],"investigated":[71],"or":[74],"contrast":[78],"involves":[100],"value":[103,123,164],"function.":[104],"While":[105],"introduces":[107],"challenges,":[108],"it":[109],"empowers":[110],"algorithm":[112],"effectively":[114],"handle":[115],"problems.":[117],"Within":[118],"framework,":[121],"function":[124],"is":[125,140],"bounded,":[126],"allowing":[127],"removal":[129],"discount":[132],"factor,":[133],"thereby":[134],"enhancing":[135],"performance.":[137],"Additionally,":[138],"there":[139],"no":[141],"longer":[142],"need":[144],"an":[146],"admissible":[147],"law":[149],"initialization,":[151],"providing":[152],"algorithms":[155],"with":[156],"combined":[158],"advantages":[159],"both":[161],"PI":[162],"(VI).":[166],"simulation":[168],"examples":[169],"are":[170],"used":[171],"verify":[173],"effectiveness":[175],"algorithms.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2024-08-06T00:00:00"}