{"id":"https://openalex.org/W4391759535","doi":"https://doi.org/10.1109/tpami.2024.3364844","title":"Efficient Offline Reinforcement Learning With Relaxed Conservatism","display_name":"Efficient Offline Reinforcement Learning With Relaxed Conservatism","publication_year":2024,"publication_date":"2024-02-12","ids":{"openalex":"https://openalex.org/W4391759535","doi":"https://doi.org/10.1109/tpami.2024.3364844","pmid":"https://pubmed.ncbi.nlm.nih.gov/38345962"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3364844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3364844","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5085372626","display_name":"Longyang Huang","orcid":"https://orcid.org/0000-0001-5123-5043"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Longyang Huang","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002412202","display_name":"Botao Dong","orcid":"https://orcid.org/0000-0002-2026-6856"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Botao Dong","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414775","display_name":"Weidong Zhang","orcid":"https://orcid.org/0000-0002-4700-1276"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Zhang","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China","school of Information and Communication Engineering, Hainan University, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"school of Information and Communication Engineering, Hainan University, China","institution_ids":["https://openalex.org/I20942203"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085372626"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":4.3644,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.9472401,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"46","issue":"8","first_page":"5260","last_page":"5272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9631999731063843,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10524","display_name":"Traffic control and management","score":0.9613000154495239,"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/conservatism","display_name":"Conservatism","score":0.9126590490341187},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9124773740768433},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7684125900268555},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7009495496749878},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6353830695152283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5576472282409668},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5476266145706177},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5062617063522339},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49961233139038086},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.45005205273628235},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.41747233271598816},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.07463991641998291},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.07085675001144409}],"concepts":[{"id":"https://openalex.org/C96640997","wikidata":"https://www.wikidata.org/wiki/Q5163004","display_name":"Conservatism","level":3,"score":0.9126590490341187},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9124773740768433},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7684125900268555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7009495496749878},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6353830695152283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5576472282409668},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5476266145706177},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5062617063522339},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49961233139038086},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.45005205273628235},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.41747233271598816},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.07463991641998291},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.07085675001144409},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3364844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3364844","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38345962","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38345962","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5721963804","display_name":null,"funder_award_id":"U2141234","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2072931156","https://openalex.org/W2107726111","https://openalex.org/W2240067561","https://openalex.org/W2518143623","https://openalex.org/W2522489477","https://openalex.org/W2735325244","https://openalex.org/W2955358753","https://openalex.org/W2978455699","https://openalex.org/W2991355586","https://openalex.org/W3009593063","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3032675404","https://openalex.org/W3102159535","https://openalex.org/W3129659662","https://openalex.org/W3171176697","https://openalex.org/W3178504712","https://openalex.org/W3178520484","https://openalex.org/W3185083385","https://openalex.org/W3195968524","https://openalex.org/W3205794883","https://openalex.org/W3207335863","https://openalex.org/W3212538202","https://openalex.org/W4220774516","https://openalex.org/W4223423875","https://openalex.org/W4226356857","https://openalex.org/W4226420669","https://openalex.org/W4312326293","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6771270455","https://openalex.org/W6774583691","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6777091672","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6784678651","https://openalex.org/W6790644358","https://openalex.org/W6792049622","https://openalex.org/W6793620907","https://openalex.org/W6793841834","https://openalex.org/W6795014841","https://openalex.org/W6796589144","https://openalex.org/W6796926305","https://openalex.org/W6798641224","https://openalex.org/W6799359760","https://openalex.org/W6802659552","https://openalex.org/W6802762872","https://openalex.org/W6809817560","https://openalex.org/W6810653392","https://openalex.org/W6839066311"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W4225619808"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,6,71],"(RL)":[3],"aims":[4],"at":[5],"an":[7],"optimal":[8],"policy":[9,45,108,151],"from":[10],"a":[11,47,55,72],"static":[12],"offline":[13,28,59,93,179],"data":[14],"set,":[15],"without":[16,128],"interacting":[17],"with":[18,61,126],"the":[19,22,26,36,39,43,78,82,103,113,117,121,134,137,141,149,161,165],"environment.":[20],"However,":[21],"theoretical":[23],"understanding":[24],"of":[25,38,87,92,116,123,156],"existing":[27,177],"RL":[29,60,94,180],"methods":[30,95],"needs":[31],"further":[32],"studies,":[33],"among":[34],"which":[35],"conservatism":[37,63,86,104],"learned":[40,44,83,88,124,138],"Q-function":[41,73,80,139,143],"and":[42,57,90,120,127,140,160,174],"is":[46,75,96,158],"major":[48],"issue.":[49],"In":[50],"this":[51,68],"article,":[52],"we":[53],"propose":[54],"simple":[56],"efficient":[58],"relaxed":[62],"(ORL-RC)":[64],"framework":[65],"for":[66],"addressing":[67],"concern":[69],"by":[70,147],"that":[74,102,133,169],"close":[76],"to":[77,107],"true":[79,142],"under":[81],"policy.":[84],"The":[85,98],"Q-functions":[89,125],"policies":[91],"analyzed.":[97],"analysis":[99],"results":[100,115,163],"support":[101],"can":[105,144],"lead":[106],"performance":[109,173],"degradation.":[110],"We":[111],"establish":[112],"convergence":[114],"proposed":[118],"ORL-RC,":[119],"bounds":[122],"sampling":[129],"errors,":[130],"respectively,":[131],"suggesting":[132],"gap":[135],"between":[136],"be":[145],"reduced":[146],"executing":[148],"conservative":[150],"improvement.":[152],"A":[153],"practical":[154],"implementation":[155],"ORL-RC":[157,170],"presented":[159],"experimental":[162],"on":[164],"D4RL":[166],"benchmark":[167],"suggest":[168],"exhibits":[171],"superior":[172],"substantially":[175],"outperforms":[176],"state-of-the-art":[178],"methods.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}