{"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":2.8847,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.91737652,"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":{"pdf":false,"grobid_xml":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":[3,34,41,87,95,98,104,107,129,133,150,153],"finite-horizon":[4,60,72,96],"H$_{\\infty":[5,35,69,73],"}$tracking":[6,70,74],"problem":[7],"for":[8,121,126],"a":[9,77,119],"class":[10],"of":[11,43,106,136,152],"discrete":[12],"linear":[13],"time-varying":[14,63,78,92],"systems.":[15,64],"Two":[16,143],"reinforcement":[17],"learning":[18],"(RL)":[19],"methods\u2014policy":[20],"iteration":[21,141],"(PI)":[22],"and":[23,52,55,139],"Q-learning\u2014are":[24],"proposed":[25,130,154],"to":[26,67,89,148],"solve":[27],"this":[28,82],"problem.":[29],"The":[30],"latter":[31],"can":[32],"obtain":[33],"}$controller":[36],"without":[37],"system":[38],"dynamics.":[39],"In":[40,65],"field":[42],"RL":[44],"control,":[45,71],"most":[46],"studies":[47,57],"focus":[48],"on":[49],"infinite-horizon":[50,68],"control":[51,61,75,112,124],"time-invariant":[53],"systems,":[54],"few":[56],"have":[58],"investigated":[59],"or":[62],"contrast":[66],"involves":[76],"value":[79,99,140],"function.":[80],"While":[81],"introduces":[83],"challenges,":[84],"it":[85],"empowers":[86],"algorithm":[88],"effectively":[90],"handle":[91],"problems.":[93],"Within":[94],"framework,":[97],"function":[100],"is":[101,116],"bounded,":[102],"allowing":[103],"removal":[105],"discount":[108],"factor,":[109],"thereby":[110],"enhancing":[111],"performance.":[113],"Additionally,":[114],"there":[115],"no":[117],"longer":[118],"need":[120],"an":[122],"admissible":[123],"law":[125],"initialization,":[127],"providing":[128],"algorithms":[131],"with":[132],"combined":[134],"advantages":[135],"both":[137],"PI":[138],"(VI).":[142],"simulation":[144],"examples":[145],"are":[146],"used":[147],"verify":[149],"effectiveness":[151],"algorithms.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":6}],"updated_date":"2026-08-30T07:30:35.949966","created_date":"2024-08-06T00:00:00"}