{"id":"https://openalex.org/W7133319024","doi":"https://doi.org/10.1109/tase.2026.3669902","title":"Inverse Reinforcement Learning for Sojourn-Probability-Based Fuzzy-Switched Systems","display_name":"Inverse Reinforcement Learning for Sojourn-Probability-Based Fuzzy-Switched Systems","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7133319024","doi":"https://doi.org/10.1109/tase.2026.3669902"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2026.3669902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3669902","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","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/A5128010880","display_name":"Jun Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I120825670","display_name":"Yunnan Normal University","ror":"https://ror.org/00sc9n023","country_code":"CN","type":"education","lineage":["https://openalex.org/I120825670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Cheng","raw_affiliation_strings":["Yunnan Key Laboratory of Modern Analytical Mathematics and Its Applications and the School of Mathematics, Yunnan Normal University, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0002-3483-747X","affiliations":[{"raw_affiliation_string":"Yunnan Key Laboratory of Modern Analytical Mathematics and Its Applications and the School of Mathematics, Yunnan Normal University, Kunming, China","institution_ids":["https://openalex.org/I120825670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127924780","display_name":"Yang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I120825670","display_name":"Yunnan Normal University","ror":"https://ror.org/00sc9n023","country_code":"CN","type":"education","lineage":["https://openalex.org/I120825670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["School of Mathematics, Yunnan Normal University, Kunming, China"],"raw_orcid":"https://orcid.org/0009-0002-2338-3406","affiliations":[{"raw_affiliation_string":"School of Mathematics, Yunnan Normal University, Kunming, China","institution_ids":["https://openalex.org/I120825670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127974386","display_name":"Bin Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Zhang","raw_affiliation_strings":["School of Mathematics and Statistics, Guangxi Normal University, Guilin, China"],"raw_orcid":"https://orcid.org/0000-0001-7654-5072","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127963170","display_name":"Huaicheng Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I23632641","display_name":"Shanghai University of Electric Power","ror":"https://ror.org/02w4tny03","country_code":"CN","type":"education","lineage":["https://openalex.org/I23632641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaicheng Yan","raw_affiliation_strings":["Faculty of Artificial Intelligence, Shanghai University of Electric Power, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5496-1809","affiliations":[{"raw_affiliation_string":"Faculty of Artificial Intelligence, Shanghai University of Electric Power, Shanghai, China","institution_ids":["https://openalex.org/I23632641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128014372","display_name":"Yueying Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueying Wang","raw_affiliation_strings":["School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9737-6765","affiliations":[{"raw_affiliation_string":"School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":36.3153,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.99589751,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"23","issue":null,"first_page":"5629","last_page":"5639"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.44359999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.44359999895095825,"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.08820000290870667,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.05620000138878822,"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/convergence","display_name":"Convergence (economics)","score":0.6383000016212463},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.6037999987602234},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5961999893188477},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5552999973297119},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5400000214576721},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.517300009727478},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.43810001015663147}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6383000016212463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6340000033378601},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.6037999987602234},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5961999893188477},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5552999973297119},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5400000214576721},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.517300009727478},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.43810001015663147},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C195975749","wikidata":"https://www.wikidata.org/wiki/Q1475705","display_name":"Fuzzy control system","level":3,"score":0.3831000030040741},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C2780695682","wikidata":"https://www.wikidata.org/wiki/Q4005959","display_name":"Jump","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.26089999079704285},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2026.3669902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3669902","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6934822931","display_name":null,"funder_award_id":"12161011","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":26,"referenced_works":["https://openalex.org/W2068006336","https://openalex.org/W2139408068","https://openalex.org/W2347074400","https://openalex.org/W2498694880","https://openalex.org/W2807477133","https://openalex.org/W3044806847","https://openalex.org/W3091182627","https://openalex.org/W3136450882","https://openalex.org/W3156476459","https://openalex.org/W3200276130","https://openalex.org/W4283835015","https://openalex.org/W4310329823","https://openalex.org/W4310599883","https://openalex.org/W4321021825","https://openalex.org/W4384304106","https://openalex.org/W4390081990","https://openalex.org/W4390357563","https://openalex.org/W4391806873","https://openalex.org/W4396542304","https://openalex.org/W4398226372","https://openalex.org/W4407827592","https://openalex.org/W4408020227","https://openalex.org/W4409683775","https://openalex.org/W4412747666","https://openalex.org/W4413639552","https://openalex.org/W4414321881"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,48,57,73,124,129,142],"inverse":[4],"reinforcement":[5],"learning":[6,87],"(IRL)":[7],"problem":[8],"for":[9],"fuzzy":[10,18,80],"switched":[11,81],"systems":[12],"characterized":[13],"by":[14],"sojourn":[15,34],"probabilities.":[16],"Classical":[17],"Markov":[19],"jump":[20],"system":[21,144],"approaches":[22],"rely":[23],"on":[24,134],"transition":[25],"probabilities,":[26],"which":[27],"are":[28],"often":[29],"difficult":[30],"to":[31,92,113],"estimate,":[32],"whereas":[33],"probabilities":[35],"provide":[36],"a":[37,63,85,108,135],"more":[38],"realistic":[39],"and":[40,56,97,100,116,126,154],"tractable":[41],"description":[42],"of":[43,50,59,128],"switching":[44,93],"behavior.":[45],"To":[46],"address":[47],"challenges":[49],"nonlinear":[51],"dynamics,":[52],"uncertain":[53],"model":[54],"residence,":[55],"lack":[58],"known":[60],"cost":[61,149],"functions,":[62,150],"novel":[64],"IRL":[65,77,161],"framework":[66,74],"is":[67],"proposed.":[68],"Different":[69],"from":[70],"existing":[71],"methods,":[72],"(i)":[75],"establishes":[76],"under":[78],"sojourn-probability-based":[79],"systems,":[82],"(ii)":[83],"incorporates":[84],"dynamic":[86],"rate":[88],"mechanism":[89],"that":[90,141],"adapts":[91],"conditions,":[94],"mitigating":[95],"oscillations":[96],"accelerating":[98],"convergence,":[99],"(iii)":[101],"introduces":[102],"constraint-based":[103],"parameter":[104],"updates":[105],"together":[106],"with":[107,159],"new":[109],"penalty-matrix":[110],"update":[111],"strategy":[112],"ensure":[114],"convergence":[115,127],"reduce":[117],"computational":[118],"complexity.":[119],"Rigorous":[120],"theoretical":[121],"analysis":[122],"demonstrates":[123],"stability":[125],"proposed":[130],"algorithms.":[131],"Simulation":[132],"study":[133],"benchmark":[136],"tunnel":[137],"diode":[138],"circuit":[139],"confirm":[140],"learner":[143],"can":[145],"accurately":[146],"reconstruct":[147],"equivalent":[148],"reproduce":[151],"expert":[152],"trajectories,":[153],"achieve":[155],"superior":[156],"performance":[157],"compared":[158],"conventional":[160],"methods.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-03-04T00:00:00"}