{"id":"https://openalex.org/W4412623467","doi":"https://doi.org/10.1109/tnnls.2025.3589418","title":"Online Adaptable Offline RL With Guidance Model","display_name":"Online Adaptable Offline RL With Guidance Model","publication_year":2025,"publication_date":"2025-07-24","ids":{"openalex":"https://openalex.org/W4412623467","doi":"https://doi.org/10.1109/tnnls.2025.3589418","pmid":"https://pubmed.ncbi.nlm.nih.gov/40705583"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3589418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3589418","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/A5113162264","display_name":"Xun Wang","orcid":"https://orcid.org/0009-0008-8140-2621"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology and School of Computer Science, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0008-8140-2621","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology and School of Computer Science, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087385084","display_name":"Jingmian Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingmian Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology and School of Computer Science, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-8296-8964","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology and School of Computer Science, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015547394","display_name":"Zhuzhong Qian","orcid":"https://orcid.org/0000-0003-1625-7575"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuzhong Qian","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology and School of Computer Science, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1625-7575","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology and School of Computer Science, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076424029","display_name":"Bolei Zhang","orcid":"https://orcid.org/0000-0002-9406-4499"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bolei Zhang","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9406-4499","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":2.1362,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89110882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"36","issue":"11","first_page":"19762","last_page":"19774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9966999888420105,"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":0.9966999888420105,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9790999889373779,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.8748276233673096},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8244705200195312},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7947806715965271},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5844441652297974},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.5408772230148315},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49065127968788147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4760827124118805},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.41963285207748413},{"id":"https://openalex.org/keywords/online-model","display_name":"Online model","score":0.4164872169494629},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1142168641090393},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.08787274360656738}],"concepts":[{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.8748276233673096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8244705200195312},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7947806715965271},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5844441652297974},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.5408772230148315},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49065127968788147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4760827124118805},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.41963285207748413},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.4164872169494629},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1142168641090393},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.08787274360656738},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3589418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3589418","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:40705583","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40705583","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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2227299984","display_name":null,"funder_award_id":"62202238","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5524979704","display_name":null,"funder_award_id":"623B1024","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7275319038","display_name":null,"funder_award_id":"2024M751506","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2787933113","https://openalex.org/W3127561923","https://openalex.org/W3216656735","https://openalex.org/W4386524114","https://openalex.org/W4387185245","https://openalex.org/W4404810339"],"related_works":["https://openalex.org/W4386150577","https://openalex.org/W3207447243","https://openalex.org/W4225619808","https://openalex.org/W2108431359","https://openalex.org/W4390110149","https://openalex.org/W4394710425","https://openalex.org/W3042122676","https://openalex.org/W4390722922","https://openalex.org/W2271247938","https://openalex.org/W2890402543"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,18],"(RL)":[2],"has":[3,68],"emerged":[4],"as":[5],"a":[6,60,116],"promising":[7],"approach":[8],"across":[9],"various":[10],"applications,":[11],"yet":[12],"its":[13,156],"reliance":[14],"on":[15],"repeated":[16],"trial-and-error":[17],"to":[19,85,89,119,127],"develop":[20],"effective":[21,110],"policies":[22,48],"from":[23],"scratch":[24],"poses":[25],"significant":[26],"challenges":[27],"for":[28,76,100],"deployment":[29],"in":[30,154],"scenarios":[31],"where":[32],"interaction":[33],"is":[34,74,83],"costly":[35],"or":[36],"constrained.":[37],"In":[38],"this":[39],"work,":[40],"we":[41,107],"investigate":[42],"the":[43,91,146,151],"offline-to-online":[44],"RL":[45,112],"paradigm,":[46],"wherein":[47],"are":[49],"initially":[50],"pretrained":[51],"using":[52],"offline":[53,72,111],"historical":[54],"datasets":[55],"and":[56,123,134],"subsequently":[57],"fine-tuned":[58],"with":[59],"limited":[61],"amount":[62],"of":[63,93,141],"online":[64,101,128],"interaction.":[65],"Previous":[66],"research":[67],"suggested":[69],"that":[70,114],"efficient":[71],"pretraining":[73],"crucial":[75],"achieving":[77],"optimal":[78],"final":[79],"performance.":[80],"However,":[81],"it":[82],"challenging":[84],"incorporate":[86],"appropriate":[87],"conservatism":[88,122],"prevent":[90],"overestimation":[92],"out-of-distribution":[94],"(OOD)":[95],"data":[96],"while":[97],"maintaining":[98],"adaptability":[99,126],"fine-tuning.":[102,129],"To":[103],"address":[104],"these":[105],"issues,":[106],"propose":[108],"an":[109],"algorithm":[113],"integrates":[115],"guidance":[117,152],"model":[118,153],"introduce":[120],"suitable":[121],"ensure":[124],"seamless":[125],"Our":[130],"rigorous":[131],"theoretical":[132],"analysis":[133],"extensive":[135],"experimental":[136],"evaluations":[137],"demonstrate":[138],"better":[139],"performance":[140],"our":[142],"novel":[143],"algorithm,":[144],"underscoring":[145],"critical":[147],"role":[148],"played":[149],"by":[150],"enhancing":[155],"efficacy.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2025-10-10T00:00:00"}