{"id":"https://openalex.org/W4415178866","doi":"https://doi.org/10.1109/tnnls.2025.3616159","title":"Toward Reliable Offline Reinforcement Learning via Lyapunov Uncertainty Control","display_name":"Toward Reliable Offline Reinforcement Learning via Lyapunov Uncertainty Control","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W4415178866","doi":"https://doi.org/10.1109/tnnls.2025.3616159","pmid":"https://pubmed.ncbi.nlm.nih.gov/41086074"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3616159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3616159","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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":"Ke Jiang","orcid":"https://orcid.org/0009-0004-3113-3786"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Jiang","raw_affiliation_strings":["College of Computer Science and Technology, MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0004-3113-3786","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100704262","display_name":"Li Yao","orcid":"https://orcid.org/0000-0001-6356-7926"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Li","raw_affiliation_strings":["School of Computer and Information Technology, Shanxi University, Taiyuan, China"],"raw_orcid":"https://orcid.org/0000-0001-6356-7926","affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004478562","display_name":"Xiaoyang Tan","orcid":"https://orcid.org/0000-0002-2683-8667"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyang Tan","raw_affiliation_strings":["College of Computer Science and Technology, MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2683-8667","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31934894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"3","first_page":"1347","last_page":"1361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.942799985408783,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.942799985408783,"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"}},{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.923799991607666,"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"}},{"id":"https://openalex.org/T10917","display_name":"Smart Grid Security and Resilience","score":0.9025999903678894,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7261999845504761},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5655999779701233},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5260999798774719},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5145999789237976},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.48429998755455017},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.48019999265670776},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.39259999990463257}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7261999845504761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6154999732971191},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5655999779701233},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5260999798774719},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5145999789237976},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.48429998755455017},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.48019999265670776},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.39259999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36579999327659607},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29490000009536743},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C2776829284","wikidata":"https://www.wikidata.org/wiki/Q1341651","display_name":"Lyapunov stability","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C101403955","wikidata":"https://www.wikidata.org/wiki/Q6707083","display_name":"Lyapunov optimization","level":5,"score":0.2797999978065491},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2734000086784363}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3616159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3616159","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:41086074","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41086074","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7215590708","display_name":null,"funder_award_id":"62476128","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Learning":[0],"trustworthy":[1],"and":[2,40,72,132,139],"reliable":[3,74],"offline":[4,24],"policies":[5],"presents":[6],"significant":[7],"challenges":[8],"due":[9],"to":[10,29,50,59,67,112,135],"the":[11,35,46,57,64,81,87,115,137,142],"inherent":[12],"uncertainty":[13,71,84,107],"in":[14,95],"pre-collected":[15],"datasets.":[16],"In":[17],"this":[18,31],"article,":[19],"we":[20,79,128],"propose":[21],"a":[22,52,119],"novel":[23],"reinforcement":[25],"learning":[26],"(RL)":[27],"method":[28],"tackle":[30],"issue.":[32],"Inspired":[33],"by":[34],"concepts":[36],"of":[37,141],"Lyapunov":[38,106],"stability":[39],"control-invariant":[41],"sets":[42],"from":[43],"control":[44,108],"theory,":[45],"central":[47],"idea":[48],"is":[49,110],"introduce":[51],"restricted":[53],"state":[54,121],"space":[55],"for":[56],"agent":[58,116],"operate":[60],"within,":[61],"which":[62],"allows":[63],"learned":[65],"models":[66],"exhibit":[68],"reduced":[69],"Bellman":[70,83],"make":[73],"decisions.":[75],"To":[76],"achieve":[77],"this,":[78],"regulate":[80],"expected":[82],"associated":[85],"with":[86],"new":[88],"policy,":[89],"ensuring":[90],"that":[91,114],"its":[92,124],"growth":[93],"trend":[94],"subsequent":[96],"states":[97],"remains":[98,117],"within":[99,118],"acceptable":[100],"limits.":[101],"The":[102],"resulting":[103],"method,":[104],"termed":[105],"(LUC),":[109],"shown":[111],"guarantee":[113],"low-uncertainty":[120],"enclosure":[122],"throughout":[123],"entire":[125],"trajectory.":[126],"Furthermore,":[127],"perform":[129],"extensive":[130],"theoretical":[131],"experimental":[133],"analysis":[134],"showcase":[136],"effectiveness":[138],"feasibility":[140],"proposed":[143],"LUC.":[144]},"counts_by_year":[],"updated_date":"2026-03-03T06:13:14.889584","created_date":"2025-10-15T00:00:00"}