{"id":"https://openalex.org/W4417131020","doi":"https://doi.org/10.1109/tase.2025.3641195","title":"Online Transfer-Enabled Temporal Difference Learning for Discrete-Time Markov Jump Systems","display_name":"Online Transfer-Enabled Temporal Difference Learning for Discrete-Time Markov Jump Systems","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4417131020","doi":"https://doi.org/10.1109/tase.2025.3641195"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2025.3641195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3641195","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":null,"display_name":"Huiwen Xue","orcid":"https://orcid.org/0009-0002-9646-3167"},"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":true,"raw_author_name":"Huiwen Xue","raw_affiliation_strings":["Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), School of Internet of Things Engineering, Jiangnan University, Wuxi, China","School of Internet of Things Engineering, Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), School of Internet of Things Engineering, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]},{"raw_affiliation_string":"School of Internet of Things Engineering, 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/A5032246506","display_name":"Jiwei Wen","orcid":"https://orcid.org/0000-0001-8780-4762"},"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":"Jiwei Wen","raw_affiliation_strings":["Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), School of Internet of Things Engineering, Jiangnan University, Wuxi, China","School of Internet of Things Engineering, Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), School of Internet of Things Engineering, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]},{"raw_affiliation_string":"School of Internet of Things Engineering, 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/A5100739668","display_name":"Peng Shi","orcid":"https://orcid.org/0000-0001-8218-586X"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peng Shi","raw_affiliation_strings":["School of Electrical and Mechanical Engineering, The University of Adelaide, Adelaide, SA, Australia","School of Electrical and Mechanical Engineering, The University of Adelaide, SA, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Mechanical Engineering, The University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"School of Electrical and Mechanical Engineering, The University of Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033061949","display_name":"Xiaoli Luan","orcid":"https://orcid.org/0000-0002-4805-1726"},"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":"Xiaoli Luan","raw_affiliation_strings":["Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), School of Internet of Things Engineering, Jiangnan University, Wuxi, China","School of Internet of Things Engineering, Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), School of Internet of Things Engineering, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]},{"raw_affiliation_string":"School of Internet of Things Engineering, Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I111599522"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20452021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"1315","last_page":"1326"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5131999850273132,"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":0.5131999850273132,"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":0.12120000272989273,"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/T10046","display_name":"Stability and Control of Uncertain Systems","score":0.04349999874830246,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/estimator","display_name":"Estimator","score":0.7555999755859375},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.618399977684021},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5379999876022339},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5141000151634216},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5045999884605408},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.46650001406669617},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4172999858856201},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4041000008583069},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.3952000141143799}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7555999755859375},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.618399977684021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6089000105857849},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5379999876022339},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5141000151634216},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5045999884605408},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4172999858856201},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4025999903678894},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.3905999958515167},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C2780695682","wikidata":"https://www.wikidata.org/wiki/Q4005959","display_name":"Jump","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34360000491142273},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.3093999922275543},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C2776825372","wikidata":"https://www.wikidata.org/wiki/Q3922411","display_name":"Jump process","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.2883000075817108},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26660001277923584},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2025.3641195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3641195","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/G1103876958","display_name":null,"funder_award_id":"B23008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1140094114","display_name":null,"funder_award_id":"62073154","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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"},{"id":"https://openalex.org/G6625608275","display_name":null,"funder_award_id":"B23008","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"},{"id":"https://openalex.org/G6862166440","display_name":null,"funder_award_id":"DP240101140","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G7476285073","display_name":null,"funder_award_id":"W2341048","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7885040424","display_name":null,"funder_award_id":"61991402","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8207744982","display_name":null,"funder_award_id":"202306790036","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G8569361878","display_name":null,"funder_award_id":"202306790046","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1490978409","https://openalex.org/W2179469667","https://openalex.org/W2248055227","https://openalex.org/W2534055124","https://openalex.org/W3011697356","https://openalex.org/W3080755120","https://openalex.org/W3091437458","https://openalex.org/W3207268251","https://openalex.org/W4220721753","https://openalex.org/W4312816360","https://openalex.org/W4320488444","https://openalex.org/W4362602398","https://openalex.org/W4378838672","https://openalex.org/W4383337679","https://openalex.org/W4384819582","https://openalex.org/W4386590925","https://openalex.org/W4389160174","https://openalex.org/W4391484607","https://openalex.org/W4391881172","https://openalex.org/W4396911939","https://openalex.org/W4399338334","https://openalex.org/W4399568695","https://openalex.org/W4401247060","https://openalex.org/W4401382148","https://openalex.org/W4401687408","https://openalex.org/W4403936662","https://openalex.org/W4404278973","https://openalex.org/W4405488477","https://openalex.org/W4406610419","https://openalex.org/W4408176029","https://openalex.org/W4409581531","https://openalex.org/W4411599584","https://openalex.org/W4415748205"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,26,29,37,40,68,85,92,97,102,113,151,154,158,182,188],"robust":[4],"control":[5,82],"problem":[6],"of":[7,32,39,71,104,150,187],"Markov":[8],"jump":[9],"linear":[10],"systems":[11,62],"(MJLSs)":[12],"with":[13,88],"unknown":[14],"transition":[15],"probabilities":[16],"(TPs).":[17],"While":[18],"existing":[19],"temporal":[20,49],"difference":[21,50],"learning":[22,51,106],"(TDL)":[23],"methods":[24],"eliminate":[25],"requirement":[27],"for":[28,153],"precise":[30],"value":[31,114,155],"TPs,":[33],"they":[34],"often":[35],"overlook":[36],"rapidity":[38],"method":[41,53],"convergence.":[42],"Therefore,":[43],"we":[44],"propose":[45],"an":[46,117,177],"online":[47,159],"transfer-enabled":[48],"(TTDL)":[52],"that":[54],"explores":[55],"prior":[56],"knowledge":[57,125],"from":[58,84,91],"similar":[59],"yet":[60],"different":[61],"to":[63,95],"accelerate":[64],"convergence":[65,152],"and":[66,129,138,167,185],"improve":[67],"estimation":[69],"accuracy":[70],"decision":[72,99],"matrices.":[73,100],"Specifically,":[74],"a":[75,147],"transfer":[76,119,137],"estimator":[77,109],"is":[78,110],"constructed":[79],"by":[80],"combining":[81],"parameters":[83],"source":[86,124],"domain":[87,94],"mode":[89],"trajectories":[90],"target":[93,98],"approximate":[96],"At":[101],"beginning":[103],"each":[105],"episode,":[107],"this":[108],"incorporated":[111],"into":[112],"function":[115,156],"through":[116],"adaptive":[118],"mechanism.":[120],"The":[121,143],"mechanism":[122],"uses":[123],"only":[126],"when":[127],"reliable":[128],"suppresses":[130],"it":[131],"near":[132],"convergence,":[133],"effectively":[134],"avoiding":[135],"negative":[136],"yielding":[139],"rapid":[140],"policy":[141],"updates.":[142],"theoretical":[144],"analysis":[145],"provides":[146],"rigorous":[148],"proof":[149],"in":[157],"TTDL":[160],"method.":[161,190],"Comparative":[162],"experiments":[163],"validate":[164],"its":[165,169],"effectiveness":[166],"highlight":[168],"reliability":[170],"under":[171],"data-scarce":[172],"scenarios.":[173],"An":[174],"application":[175],"on":[176],"aero-engine":[178],"system":[179],"further":[180],"validates":[181],"practical":[183],"applicability":[184],"efficiency":[186],"proposed":[189]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-08T00:00:00"}