{"id":"https://openalex.org/W4404576982","doi":"https://doi.org/10.1109/tnnls.2024.3488358","title":"Decoupled Prioritized Resampling for Offline RL","display_name":"Decoupled Prioritized Resampling for Offline RL","publication_year":2024,"publication_date":"2024-11-21","ids":{"openalex":"https://openalex.org/W4404576982","doi":"https://doi.org/10.1109/tnnls.2024.3488358","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030407"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3488358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3488358","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":"Yang Yue","orcid":"https://orcid.org/0009-0002-0437-7238"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yue","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-0437-7238","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032599820","display_name":"Bingyi Kang","orcid":"https://orcid.org/0000-0003-2637-4695"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bingyi Kang","raw_affiliation_strings":["Sea AI Laboratory, Fusionopolis Place, Singapore","Sea AI Laboratory, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sea AI Laboratory, Fusionopolis Place, Singapore","institution_ids":[]},{"raw_affiliation_string":"Sea AI Laboratory, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao Ma","orcid":"https://orcid.org/0000-0001-5466-867X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Ma","raw_affiliation_strings":["Sea AI Laboratory, Fusionopolis Place, Singapore","Sea AI Laboratory, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5466-867X","affiliations":[{"raw_affiliation_string":"Sea AI Laboratory, Fusionopolis Place, Singapore","institution_ids":[]},{"raw_affiliation_string":"Sea AI Laboratory, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qisen Yang","orcid":"https://orcid.org/0000-0002-2587-2660"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qisen Yang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2587-2660","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013240918","display_name":"Gao Huang","orcid":"https://orcid.org/0000-0002-7251-0988"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao Huang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7251-0988","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101868179","display_name":"Shiji Song","orcid":"https://orcid.org/0000-0003-0858-1770"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiji Song","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0858-1770","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100381753","display_name":"Shuicheng Yan","orcid":"https://orcid.org/0000-0001-8906-3777"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuicheng Yan","raw_affiliation_strings":["Sea AI Laboratory, Fusionopolis Place, Singapore","Sea AI Laboratory, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8906-3777","affiliations":[{"raw_affiliation_string":"Sea AI Laboratory, Fusionopolis Place, Singapore","institution_ids":[]},{"raw_affiliation_string":"Sea AI Laboratory, Singapore, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8347,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.88010298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"36","issue":"7","first_page":"13094","last_page":"13108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9815999865531921,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9815999865531921,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10126","display_name":"Logic, programming, and type systems","score":0.9312000274658203,"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/T10142","display_name":"Formal Methods in Verification","score":0.9251000285148621,"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/resampling","display_name":"Resampling","score":0.6502877473831177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5869635939598083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39007848501205444}],"concepts":[{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.6502877473831177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5869635939598083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39007848501205444}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3488358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3488358","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:40030407","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030407","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/G5313418749","display_name":null,"funder_award_id":"42327901","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":47,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W2139418546","https://openalex.org/W2902098903","https://openalex.org/W2978455699","https://openalex.org/W4327729182","https://openalex.org/W4360584316","https://openalex.org/W4388469888","https://openalex.org/W6634413486","https://openalex.org/W6677067356","https://openalex.org/W6687681856","https://openalex.org/W6748839928","https://openalex.org/W6751540476","https://openalex.org/W6755015941","https://openalex.org/W6757469721","https://openalex.org/W6760755450","https://openalex.org/W6763177082","https://openalex.org/W6763704811","https://openalex.org/W6764976746","https://openalex.org/W6769342953","https://openalex.org/W6771270455","https://openalex.org/W6773785716","https://openalex.org/W6774948183","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6779402086","https://openalex.org/W6779656125","https://openalex.org/W6780159193","https://openalex.org/W6780559895","https://openalex.org/W6783671239","https://openalex.org/W6791413555","https://openalex.org/W6796289742","https://openalex.org/W6796589144","https://openalex.org/W6796926305","https://openalex.org/W6797702751","https://openalex.org/W6798709053","https://openalex.org/W6801801719","https://openalex.org/W6802659552","https://openalex.org/W6803771995","https://openalex.org/W6804160314","https://openalex.org/W6838725491","https://openalex.org/W6840739175","https://openalex.org/W6841549819","https://openalex.org/W6843816287","https://openalex.org/W6847582351","https://openalex.org/W6849777368","https://openalex.org/W6853174557","https://openalex.org/W6858814583"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2052515325","https://openalex.org/W2050948537","https://openalex.org/W2767646790","https://openalex.org/W2352041579","https://openalex.org/W1488006380","https://openalex.org/W1998176685","https://openalex.org/W2138381686"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"is":[4,122,170],"challenged":[5],"by":[6,101],"the":[7,25,29,50,69,91,103,106,152],"distributional":[8],"shift":[9],"problem.":[10],"To":[11],"tackle":[12],"this":[13,54,114],"issue,":[14],"existing":[15],"works":[16],"mainly":[17],"focus":[18],"on":[19,143],"designing":[20],"sophisticated":[21],"policy":[22,27,71,100,185],"constraints":[23,34],"between":[24],"learned":[26,51],"and":[28,40,77,110,137,151,196,206,229],"behavior":[30,99,108,178],"policy.":[31,52],"However,":[32],"these":[33],"are":[35,232],"applied":[36],"equally":[37],"to":[38,113,124,134],"well-performing":[39],"inferior":[41],"actions":[42],"through":[43],"uniform":[44],"sampling,":[45],"which":[46,63],"might":[47],"negatively":[48],"affect":[49],"In":[53],"article,":[55],"we":[56,88],"propose":[57],"offline":[58,75,119,175],"decoupled":[59,80],"prioritized":[60],"resampling":[61,81],"(ODPR),":[62],"designs":[64],"specialized":[65],"priority":[66,93],"functions":[67,94],"for":[68,82,160],"suboptimal":[70],"constraint":[72],"issue":[73],"in":[74,220],"RL":[76,120,176],"employs":[78],"unique":[79],"training":[83],"stability.":[84],"Through":[85],"theoretical":[86],"analysis,":[87],"show":[89],"that":[90,203],"distinctive":[92],"induce":[95],"a":[96,117,126,144,164],"provable":[97],"improved":[98,115],"modifying":[102],"distribution":[104],"of":[105],"original":[107],"policy,":[109,116],"when":[111],"constrained":[112],"policy-constrained":[118],"algorithm":[121],"likely":[123],"yield":[125],"better":[127],"solution.":[128],"We":[129],"provide":[130],"two":[131],"practical":[132],"implementations":[133],"balance":[135],"computation":[136],"performance:":[138],"one":[139],"estimates":[140],"priorities":[141],"based":[142],"fit":[145],"value":[146],"network":[147],"[advantage-based":[148],"ODPR":[149,158,169],"(ODPR-A)]":[150],"other":[153],"utilizes":[154],"trajectory":[155,226],"returns":[156],"[return-based":[157],"(ODPR-R)]":[159],"quick":[161],"computation.":[162],"As":[163],"highly":[165],"compatible":[166],"plug-and-play":[167],"component,":[168],"evaluated":[171],"with":[172],"five":[173],"prevalent":[174],"algorithms:":[177],"cloning":[179],"(BC),":[180],"twin":[181],"delayed":[182],"deep":[183],"deterministic":[184],"gradient":[186],"+":[187,190],"BC":[188],"(TD3":[189],"BC),":[191],"OnestepRL,":[192],"conservative":[193],"Q-learning":[194,198],"(CQL),":[195],"implicit":[197],"(IQL).":[199],"Our":[200],"experiments":[201],"confirm":[202],"both":[204],"ODPR-A":[205,216],"ODPR-R":[207],"significantly":[208],"improve":[209],"performance":[210],"across":[211],"all":[212],"baseline":[213],"methods.":[214],"Moreover,":[215],"can":[217],"be":[218],"effective":[219],"some":[221],"challenging":[222],"settings,":[223],"i.e.,":[224],"without":[225],"information.":[227],"Code":[228],"pretrained":[230],"weights":[231],"available":[233],"at":[234],"https://github.com/yueyang130/ODPR.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}