{"id":"https://openalex.org/W4416649966","doi":"https://doi.org/10.1109/tnnls.2025.3633997","title":"A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning","display_name":"A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning","publication_year":2025,"publication_date":"2025-11-25","ids":{"openalex":"https://openalex.org/W4416649966","doi":"https://doi.org/10.1109/tnnls.2025.3633997","pmid":"https://pubmed.ncbi.nlm.nih.gov/41289105"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3633997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3633997","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":"https://openalex.org/A5028982929","display_name":"Siyuan Guo","orcid":"https://orcid.org/0000-0002-9304-5405"},"institutions":[{"id":"https://openalex.org/I4210164189","display_name":"Jilin International Studies University","ror":"https://ror.org/05mvcw862","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210164189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Guo","raw_affiliation_strings":["School of Artificial Intelligence and the International Center of Future Science, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0002-9304-5405","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and the International Center of Future Science, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210164189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101353767","display_name":"Yanchao Sun","orcid":"https://orcid.org/0000-0002-1137-9939"},"institutions":[{"id":"https://openalex.org/I1305429384","display_name":"JPMorgan Chase & Co (United States)","ror":"https://ror.org/01x3kkr08","country_code":"US","type":"company","lineage":["https://openalex.org/I1305429384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanchao Sun","raw_affiliation_strings":["JPMorgan AI Research, New York, USA"],"raw_orcid":"https://orcid.org/0000-0002-1137-9939","affiliations":[{"raw_affiliation_string":"JPMorgan AI Research, New York, USA","institution_ids":["https://openalex.org/I1305429384"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jifeng Hu","orcid":"https://orcid.org/0000-0002-8658-9447"},"institutions":[{"id":"https://openalex.org/I4210164189","display_name":"Jilin International Studies University","ror":"https://ror.org/05mvcw862","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210164189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jifeng Hu","raw_affiliation_strings":["School of Artificial Intelligence and the International Center of Future Science, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0002-8658-9447","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and the International Center of Future Science, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210164189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001147061","display_name":"Sili Huang","orcid":"https://orcid.org/0000-0001-5387-7904"},"institutions":[{"id":"https://openalex.org/I4210164189","display_name":"Jilin International Studies University","ror":"https://ror.org/05mvcw862","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210164189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sili Huang","raw_affiliation_strings":["School of Artificial Intelligence and the International Center of Future Science, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0001-5387-7904","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and the International Center of Future Science, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210164189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108294333","display_name":"Hechang Chen","orcid":"https://orcid.org/0000-0001-7835-9556"},"institutions":[{"id":"https://openalex.org/I4210164189","display_name":"Jilin International Studies University","ror":"https://ror.org/05mvcw862","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210164189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hechang Chen","raw_affiliation_strings":["School of Artificial Intelligence and the International Center of Future Science, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0001-7835-9556","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and the International Center of Future Science, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210164189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004540162","display_name":"Haiyin Piao","orcid":"https://orcid.org/0000-0002-8519-4750"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyin Piao","raw_affiliation_strings":["Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-8519-4750","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015105117","display_name":"Lichao Sun","orcid":"https://orcid.org/0000-0003-1539-7939"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lichao Sun","raw_affiliation_strings":["Lehigh University, Bethlehem, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1539-7939","affiliations":[{"raw_affiliation_string":"Lehigh University, Bethlehem, PA, USA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029392006","display_name":"Yi Chang","orcid":"https://orcid.org/0000-0003-2697-8093"},"institutions":[{"id":"https://openalex.org/I4210164189","display_name":"Jilin International Studies University","ror":"https://ror.org/05mvcw862","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210164189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Chang","raw_affiliation_strings":["School of Artificial Intelligence and the International Center of Future Science, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0003-2697-8093","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and the International Center of Future Science, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210164189"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2378,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86386064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"37","issue":"5","first_page":"2456","last_page":"2468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.769599974155426,"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":0.769599974155426,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0746999979019165,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.01590000092983246,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8240000009536743},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6841999888420105},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.6644999980926514},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5012999773025513},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.4124999940395355},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3831000030040741}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8240000009536743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698000073432922},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6841999888420105},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.6644999980926514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5681999921798706},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5012999773025513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4691999852657318},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2718000113964081}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3633997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3633997","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:41289105","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41289105","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/G1211044700","display_name":null,"funder_award_id":"U2341229","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G524871825","display_name":null,"funder_award_id":"61976102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7138386155","display_name":null,"funder_award_id":"U19A2065","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8116777385","display_name":null,"funder_award_id":"62476110","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":16,"referenced_works":["https://openalex.org/W2142971854","https://openalex.org/W2765302304","https://openalex.org/W2904246096","https://openalex.org/W3168236455","https://openalex.org/W3185083385","https://openalex.org/W4297838928","https://openalex.org/W4306679387","https://openalex.org/W4324312897","https://openalex.org/W4360584316","https://openalex.org/W4382202996","https://openalex.org/W4385626984","https://openalex.org/W4388469888","https://openalex.org/W4401806721","https://openalex.org/W4402673477","https://openalex.org/W7133230489","https://openalex.org/W7133245739"],"related_works":[],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,9],"(RL)":[3],"provides":[4],"a":[5,15,72,96,110],"promising":[6],"solution":[7,82],"to":[8,37,55,83,115,139,147,150],"an":[10,129],"agent":[11,41],"fully":[12],"relying":[13],"on":[14],"data-driven":[16],"paradigm.":[17],"However,":[18],"constrained":[19,59],"by":[20,133],"the":[21,25,40,81,87,176],"limited":[22],"quality":[23],"of":[24,68,89],"offline":[26,136,153,167],"dataset,":[27],"its":[28],"performance":[29,162],"is":[30,35],"often":[31],"suboptimal.":[32],"Therefore,":[33],"it":[34],"desired":[36],"further":[38],"finetune":[39],"via":[42,95],"extra":[43],"online":[44,144,155,160],"interactions":[45],"before":[46],"deployment.":[47],"Unfortunately,":[48],"offline-to-online":[49],"RL":[50,137,145,168],"can":[51],"be":[52],"challenging":[53],"due":[54],"two":[56],"main":[57],"challenges:":[58],"exploratory":[60],"behavior":[61],"and":[62,123,142,154,173],"state-action":[63,100],"distribution":[64],"shift.":[65],"In":[66],"view":[67],"this,":[69],"we":[70],"propose":[71],"simple":[73],"unified":[74],"uncertainty-guided":[75],"(SUNG)":[76],"framework,":[77],"which":[78],"naturally":[79],"unifies":[80],"both":[84,120],"challenges":[85],"with":[86,119,165],"tool":[88],"uncertainty.":[90,125],"Specifically,":[91],"SUNG":[92,108,127,157],"quantifies":[93],"uncertainty":[94],"variational":[97],"autoencoder":[98],"(VAE)-based":[99],"visitation":[101],"density":[102],"estimator.":[103],"To":[104],"facilitate":[105],"efficient":[106],"exploration,":[107],"presents":[109],"practical":[111],"optimistic":[112],"exploration":[113],"strategy":[114],"select":[116],"informative":[117],"actions":[118],"high":[121,124],"value":[122],"Moreover,":[126],"develops":[128],"adaptive":[130],"exploitation":[131],"method":[132],"applying":[134],"conservative":[135],"objectives":[138,146],"high-uncertainty":[140],"samples":[141,149],"standard":[143],"low-uncertainty":[148],"smoothly":[151],"bridge":[152],"stages.":[156],"achieves":[158],"state-of-the-art":[159],"finetuning":[161],"when":[163],"combined":[164],"different":[166],"methods,":[169],"across":[170],"various":[171],"environments":[172],"datasets":[174],"in":[175,184],"D4RL":[177],"benchmark.":[178],"Codes":[179],"are":[180],"made":[181],"publicly":[182],"available":[183],"https://github.com/guosyjlu/ACBR.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-11-25T00:00:00"}