{"id":"https://openalex.org/W4387886070","doi":"https://doi.org/10.1109/tcsii.2023.3326456","title":"Reinforcement Learning-Based Robust Tracking Control for Unknown Markov Jump Systems and its Application","display_name":"Reinforcement Learning-Based Robust Tracking Control for Unknown Markov Jump Systems and its Application","publication_year":2023,"publication_date":"2023-10-23","ids":{"openalex":"https://openalex.org/W4387886070","doi":"https://doi.org/10.1109/tcsii.2023.3326456"},"language":"en","primary_location":{"id":"doi:10.1109/tcsii.2023.3326456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsii.2023.3326456","pdf_url":null,"source":{"id":"https://openalex.org/S93916849","display_name":"IEEE Transactions on Circuits & Systems II Express Briefs","issn_l":"1549-7747","issn":["1549-7747","1558-3791"],"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 Circuits and Systems II: Express Briefs","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/A5067323219","display_name":"Hao Shen","orcid":"https://orcid.org/0000-0002-4688-9146"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Shen","raw_affiliation_strings":["School of Electrical and Information Engineering, Anhui University of Technology, Ma’anshan, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Anhui University of Technology, Ma’anshan, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011843182","display_name":"Jiacheng Wu","orcid":"https://orcid.org/0000-0001-7607-8777"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiacheng Wu","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618681","display_name":"Yun Wang","orcid":"https://orcid.org/0000-0003-3117-8955"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Wang","raw_affiliation_strings":["School of Electrical and Information Engineering, Anhui University of Technology, Ma’anshan, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Anhui University of Technology, Ma’anshan, China","institution_ids":["https://openalex.org/I92178344"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100378538","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0002-5519-9016"},"institutions":[{"id":"https://openalex.org/I92178344","display_name":"Anhui University of Technology","ror":"https://ror.org/02qdtrq21","country_code":"CN","type":"education","lineage":["https://openalex.org/I92178344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["School of Electrical and Information Engineering, Anhui University of Technology, Ma’anshan, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Anhui University of Technology, Ma’anshan, China","institution_ids":["https://openalex.org/I92178344"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067323219"],"corresponding_institution_ids":["https://openalex.org/I92178344"],"apc_list":null,"apc_paid":null,"fwci":2.2187,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.89963002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"71","issue":"3","first_page":"1211","last_page":"1215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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":0.9997000098228455,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9779000282287598,"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"}},{"id":"https://openalex.org/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9329000115394592,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7498409152030945},{"id":"https://openalex.org/keywords/algebraic-riccati-equation","display_name":"Algebraic Riccati equation","score":0.7170277237892151},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6420310139656067},{"id":"https://openalex.org/keywords/riccati-equation","display_name":"Riccati equation","score":0.6022578477859497},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5604511499404907},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5546344518661499},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5439460277557373},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4756167531013489},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.47506850957870483},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.44897687435150146},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4345168471336365},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4321937561035156},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.42863601446151733},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.40859705209732056},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35398977994918823},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.26555371284484863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1665804386138916},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15049433708190918},{"id":"https://openalex.org/keywords/differential-equation","display_name":"Differential equation","score":0.07751694321632385}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7498409152030945},{"id":"https://openalex.org/C13847129","wikidata":"https://www.wikidata.org/wiki/Q4723989","display_name":"Algebraic Riccati equation","level":4,"score":0.7170277237892151},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6420310139656067},{"id":"https://openalex.org/C45473103","wikidata":"https://www.wikidata.org/wiki/Q851503","display_name":"Riccati equation","level":3,"score":0.6022578477859497},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5604511499404907},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5546344518661499},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5439460277557373},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4756167531013489},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.47506850957870483},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.44897687435150146},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4345168471336365},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4321937561035156},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.42863601446151733},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.40859705209732056},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35398977994918823},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.26555371284484863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1665804386138916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15049433708190918},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.07751694321632385},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/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/tcsii.2023.3326456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsii.2023.3326456","pdf_url":null,"source":{"id":"https://openalex.org/S93916849","display_name":"IEEE Transactions on Circuits & Systems II Express Briefs","issn_l":"1549-7747","issn":["1549-7747","1558-3791"],"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 Circuits and Systems II: Express Briefs","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1322164634","display_name":null,"funder_award_id":"62173001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3460663202","display_name":null,"funder_award_id":"62273006","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":20,"referenced_works":["https://openalex.org/W1490978409","https://openalex.org/W1992865529","https://openalex.org/W2152452913","https://openalex.org/W2333120204","https://openalex.org/W2790139300","https://openalex.org/W2943141190","https://openalex.org/W3002297177","https://openalex.org/W3127008750","https://openalex.org/W3127275112","https://openalex.org/W3132420033","https://openalex.org/W3134087507","https://openalex.org/W3152004456","https://openalex.org/W3203011581","https://openalex.org/W4200009615","https://openalex.org/W4213367573","https://openalex.org/W4220837569","https://openalex.org/W4285505520","https://openalex.org/W4308616306","https://openalex.org/W4320018447","https://openalex.org/W4321483989"],"related_works":["https://openalex.org/W2005019312","https://openalex.org/W2018296362","https://openalex.org/W2547959172","https://openalex.org/W2727200542","https://openalex.org/W2002357820","https://openalex.org/W2334216590","https://openalex.org/W2997206142","https://openalex.org/W2027962246","https://openalex.org/W2244442793","https://openalex.org/W2107449083"],"abstract_inverted_index":{"This":[0],"brief":[1],"presents":[2],"a":[3,65,85,129],"novel":[4,86],"reinforcement":[5,75],"learning-based":[6],"robust":[7,22],"tracking":[8,20],"control":[9,53],"method":[10,144],"for":[11],"discrete-time":[12],"unknown":[13],"Markov":[14,109],"jump":[15,110],"systems.":[16],"First,":[17],"the":[18,38,46,51,56,73,78,94,97,104,120,123,139,142,146],"optimal":[19,30,52,79],"and":[21,49,103,145],"controller":[23],"design":[24],"problem":[25],"is":[26,82,126,135],"formulated":[27],"as":[28,64],"an":[29],"output":[31,80,105],"regulation":[32,106],"problem.":[33],"In":[34],"particular,":[35],"we":[36],"reconstruct":[37],"stochastic":[39,98],"coupled":[40,99],"algebraic":[41,100],"Riccati":[42,101],"equation":[43,102,107],"to":[44,137],"decouple":[45],"jumping":[47],"mode":[48],"approximate":[50],"policy,":[54],"where":[55],"knowledge":[57],"of":[58,96,108,122,141],"system":[59,117],"dynamics":[60],"should":[61],"be":[62],"known":[63],"priori.":[66],"To":[67],"solve":[68],"this":[69,92],"problem,":[70],"by":[71,114],"employing":[72],"online":[74,116],"learning":[76,89],"approach,":[77],"regulator":[81],"learned":[83],"within":[84],"data-based":[87],"parallel":[88],"framework.":[90],"On":[91],"basis,":[93],"solutions":[95],"systems":[111],"are":[112],"obtained":[113],"using":[115],"data.":[118],"Moreover,":[119],"convergence":[121],"proposed":[124,143],"algorithms":[125],"analyzed.":[127],"Finally,":[128],"PWM-driven":[130],"DC-DC":[131],"boost":[132],"converter":[133],"model":[134],"provided":[136],"show":[138],"effectiveness":[140],"main":[147],"theoretical":[148],"results.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}