{"id":"https://openalex.org/W4285175029","doi":"https://doi.org/10.1109/tfuzz.2022.3171844","title":"Fuzzy-Based Adaptive Optimization of Unknown Discrete-Time Nonlinear Markov Jump Systems With Off-Policy Reinforcement Learning","display_name":"Fuzzy-Based Adaptive Optimization of Unknown Discrete-Time Nonlinear Markov Jump Systems With Off-Policy Reinforcement Learning","publication_year":2022,"publication_date":"2022-05-03","ids":{"openalex":"https://openalex.org/W4285175029","doi":"https://doi.org/10.1109/tfuzz.2022.3171844"},"language":"en","primary_location":{"id":"doi:10.1109/tfuzz.2022.3171844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tfuzz.2022.3171844","pdf_url":null,"source":{"id":"https://openalex.org/S134177497","display_name":"IEEE Transactions on Fuzzy Systems","issn_l":"1063-6706","issn":["1063-6706","1941-0034"],"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 Fuzzy 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/A5085669742","display_name":"Haiyang Fang","orcid":"https://orcid.org/0000-0002-6587-2737"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Haiyang Fang","raw_affiliation_strings":["Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment, School of Electrical Engineering and Automation, Anhui University, Hefei, China","Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-6587-2737","affiliations":[{"raw_affiliation_string":"Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment, School of Electrical Engineering and Automation, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001371746","display_name":"Yidong Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidong Tu","raw_affiliation_strings":["Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment, School of Electrical Engineering and Automation, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment, School of Electrical Engineering and Automation, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009768180","display_name":"Hai Wang","orcid":"https://orcid.org/0000-0003-2789-9530"},"institutions":[{"id":"https://openalex.org/I176790772","display_name":"Murdoch University","ror":"https://ror.org/00r4sry34","country_code":"AU","type":"education","lineage":["https://openalex.org/I176790772"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hai Wang","raw_affiliation_strings":["Discipline of Engineering and Energy, and the Centre for Water, Energy and Waste, Murdoch University, Murdoch, Australia"],"raw_orcid":"https://orcid.org/0000-0003-2789-9530","affiliations":[{"raw_affiliation_string":"Discipline of Engineering and Energy, and the Centre for Water, Energy and Waste, Murdoch University, Murdoch, Australia","institution_ids":["https://openalex.org/I176790772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078975428","display_name":"Shuping He","orcid":"https://orcid.org/0000-0003-1869-2116"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuping He","raw_affiliation_strings":["Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment, School of Electrical Engineering and Automation, Anhui University, Hefei, China","School of Electronic Information and Electrical Engineering, Chengdu University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-1869-2116","affiliations":[{"raw_affiliation_string":"Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment, School of Electrical Engineering and Automation, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Chengdu University, Chengdu, China","institution_ids":["https://openalex.org/I4210125143"]}]},{"author_position":"middle","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Liu","raw_affiliation_strings":["Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0001-7160-2605","affiliations":[{"raw_affiliation_string":"Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086465750","display_name":"Zhengtao Ding","orcid":"https://orcid.org/0000-0003-0690-7853"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhengtao Ding","raw_affiliation_strings":["School of Electrical and Electronic Engineering, The University of Manchester, Manchester, U.K"],"raw_orcid":"https://orcid.org/0000-0003-0690-7853","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, The University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072251844","display_name":"Shing Shin Cheng","orcid":"https://orcid.org/0000-0002-9386-5497"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shing Shin Cheng","raw_affiliation_strings":["Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-9386-5497","affiliations":[{"raw_affiliation_string":"Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.436,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96502399,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"30","issue":"12","first_page":"5276","last_page":"5290"},"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/T12277","display_name":"Frequency Control in Power Systems","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.9846000075340271,"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":0.6379513740539551},{"id":"https://openalex.org/keywords/fuzzy-control-system","display_name":"Fuzzy control system","score":0.5819820761680603},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5377979278564453},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.5237596035003662},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5117514133453369},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.49796319007873535},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.48811349272727966},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.47581058740615845},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.46364083886146545},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.38676005601882935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14567086100578308},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.08343076705932617}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6379513740539551},{"id":"https://openalex.org/C195975749","wikidata":"https://www.wikidata.org/wiki/Q1475705","display_name":"Fuzzy control system","level":3,"score":0.5819820761680603},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5377979278564453},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.5237596035003662},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5117514133453369},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.49796319007873535},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.48811349272727966},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.47581058740615845},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.46364083886146545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38676005601882935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14567086100578308},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.08343076705932617},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tfuzz.2022.3171844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tfuzz.2022.3171844","pdf_url":null,"source":{"id":"https://openalex.org/S134177497","display_name":"IEEE Transactions on Fuzzy Systems","issn_l":"1063-6706","issn":["1063-6706","1941-0034"],"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 Fuzzy Systems","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/26ee0855-78ff-4e06-be33-130dfd5753ad","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/26ee0855-78ff-4e06-be33-130dfd5753ad","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fang, H, Tu, Y, Wang, H, He, S, Liu, F, Ding, Z & Cheng, S S 2022, 'Fuzzy-Based Adaptive Optimization of Unknown Discrete-Time Nonlinear Markov Jump Systems With Off-Policy Reinforcement Learning', IEEE Transactions on Fuzzy Systems. https://doi.org/10.1109/TFUZZ.2022.3171844","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:researchrepository.murdoch.edu.au:64791","is_oa":false,"landing_page_url":"https://researchrepository.murdoch.edu.au/id/eprint/64791/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400274","display_name":"Murdoch Research Repository (Murdoch University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I176790772","host_organization_name":"Murdoch University","host_organization_lineage":["https://openalex.org/I176790772"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fang, H., Tu, Y., Wang, H. &lt;https://researchrepository.murdoch.edu.au/view/author/Wang, Hai.html&gt;ORCID: 0000-0003-2789-9530 &lt;http://orcid.org/0000-0003-2789-9530&gt;, He, S., Liu, F., Ding, Z. and Cheng, S.S. (2022) Fuzzy-Based adaptive optimization of unknown Discrete-Time Nonlinear Markov jump systems with Off-Policy reinforcement learning. IEEE Transactions on Fuzzy Systems . Early Access.","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6459810640","display_name":null,"funder_award_id":"62073001","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":33,"referenced_works":["https://openalex.org/W1984831821","https://openalex.org/W2019338681","https://openalex.org/W2024303516","https://openalex.org/W2025025159","https://openalex.org/W2037950640","https://openalex.org/W2064551186","https://openalex.org/W2114032071","https://openalex.org/W2148347691","https://openalex.org/W2152161277","https://openalex.org/W2160051270","https://openalex.org/W2596147898","https://openalex.org/W2608120938","https://openalex.org/W2616301069","https://openalex.org/W2770049904","https://openalex.org/W2792866162","https://openalex.org/W2793982551","https://openalex.org/W2802741389","https://openalex.org/W2884086177","https://openalex.org/W2914172002","https://openalex.org/W2943141190","https://openalex.org/W2945728374","https://openalex.org/W2967622731","https://openalex.org/W2990666807","https://openalex.org/W3078357177","https://openalex.org/W3100789280","https://openalex.org/W3105522550","https://openalex.org/W3110511704","https://openalex.org/W3124444594","https://openalex.org/W3138084032","https://openalex.org/W3187511779","https://openalex.org/W3200288111","https://openalex.org/W3214995827","https://openalex.org/W4299819199"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W4244250045","https://openalex.org/W296145649","https://openalex.org/W135622916"],"abstract_inverted_index":{"This":[0],"article":[1],"explores":[2],"a":[3,10,100],"novel":[4],"adaptive":[5],"optimal":[6,43],"control":[7,44],"strategy":[8],"for":[9,52,69,88,112],"class":[11],"of":[12,119,150],"sophisticated":[13],"discrete-time":[14,72],"nonlinear":[15,32],"Markov":[16,57,74],"jump":[17,75],"systems":[18,55,76],"(DTNMJSs)":[19],"via":[20],"Takagi\u2013Sugeno":[21],"fuzzy":[22,38,50,54,64,85,104],"models":[23],"and":[24,122,136,147],"reinforcement":[25],"learning":[26],"(RL)":[27],"techniques.":[28],"First,":[29],"the":[30,41,63,70,93,113,117,132,137,145,151],"original":[31],"system":[33,120],"model":[34],"is":[35,46,97,107],"represented":[36],"by":[37,77],"approximation,":[39],"while":[40],"relevant":[42],"problem":[45],"equivalent":[47],"to":[48,131,143],"designing":[49],"controllers":[51],"linear":[53,73],"with":[56,109],"jumping":[58],"parameters.":[59],"Subsequently,":[60],"we":[61],"derive":[62],"coupled":[65],"algebraic":[66],"Riccati":[67],"equations":[68],"fuzzy-based":[71],"using":[78,116],"Hamiltonian\u2013Bellman":[79],"methods.":[80],"Following":[81],"this,":[82],"an":[83],"online":[84],"optimization":[86],"algorithm":[87,106],"DTNMJSs":[89,114],"as":[90,92],"well":[91],"associated":[94],"equivalence":[95],"proof":[96],"given.":[98],"Then,":[99],"fully":[101],"model-free":[102],"off-policy":[103],"RL":[105],"derived":[108],"proved":[110],"convergence":[111],"without":[115],"information":[118],"dynamics":[121],"transition":[123],"probability.":[124],"Finally,":[125],"two":[126],"simulation":[127],"examples,":[128],"respectively,":[129],"related":[130],"single-link":[133],"robotic":[134],"arm":[135],"half-car":[138],"active":[139],"suspension":[140],"are":[141],"given":[142],"verify":[144],"effectiveness":[146],"good":[148],"performance":[149],"proposed":[152],"approach.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}
