{"id":"https://openalex.org/W4395680426","doi":"https://doi.org/10.1109/tcyb.2024.3385910","title":"Offline Reinforcement Learning With Behavior Value Regularization","display_name":"Offline Reinforcement Learning With Behavior Value Regularization","publication_year":2024,"publication_date":"2024-04-26","ids":{"openalex":"https://openalex.org/W4395680426","doi":"https://doi.org/10.1109/tcyb.2024.3385910","pmid":"https://pubmed.ncbi.nlm.nih.gov/38669164"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2024.3385910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2024.3385910","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","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":false,"raw_author_name":"Longyang Huang","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5123-5043","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"],"raw_orcid":"https://orcid.org/0000-0002-2026-6856","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/A5014747872","display_name":"Wei Xie","orcid":"https://orcid.org/0000-0003-4984-6659"},"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":"Wei Xie","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4984-6659","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, Haikou, Hainan, China"],"raw_orcid":"https://orcid.org/0000-0002-4700-1276","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, Haikou, Hainan, China","institution_ids":["https://openalex.org/I20942203"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6413,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9057437,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"54","issue":"6","first_page":"3692","last_page":"3704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9871000051498413,"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/reinforcement","display_name":"Reinforcement","score":0.7606291174888611},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7270078063011169},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5302217602729797},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.38109496235847473},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34849247336387634},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.26909390091896057},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.13328814506530762}],"concepts":[{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.7606291174888611},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7270078063011169},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5302217602729797},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38109496235847473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34849247336387634},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26909390091896057},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13328814506530762}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2024.3385910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2024.3385910","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:38669164","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38669164","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 cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G2978885535","display_name":null,"funder_award_id":"2022ZD0119901","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"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"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W192920577","https://openalex.org/W2967474307","https://openalex.org/W2986925736","https://openalex.org/W2991355586","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3130292943","https://openalex.org/W3167222229","https://openalex.org/W3178225342","https://openalex.org/W3185083385","https://openalex.org/W3196740181","https://openalex.org/W4220733308","https://openalex.org/W4225428162","https://openalex.org/W4285285554","https://openalex.org/W4287266180","https://openalex.org/W4294891511","https://openalex.org/W4297944358","https://openalex.org/W4312650890","https://openalex.org/W4381327812","https://openalex.org/W4382318909","https://openalex.org/W4386524114","https://openalex.org/W4386875113","https://openalex.org/W4389584650","https://openalex.org/W4391759535","https://openalex.org/W6748839928","https://openalex.org/W6757469721","https://openalex.org/W6771270455","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6777091672","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6780159193","https://openalex.org/W6787262146","https://openalex.org/W6790644358","https://openalex.org/W6792413377","https://openalex.org/W6796157606","https://openalex.org/W6796589144","https://openalex.org/W6802659552","https://openalex.org/W6839066311","https://openalex.org/W6842723896","https://openalex.org/W6843642121","https://openalex.org/W6850204301","https://openalex.org/W6856759589","https://openalex.org/W6857008120"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,29],"(offline":[3],"RL)":[4],"aims":[5],"to":[6,85],"find":[7],"task-solving":[8],"policies":[9],"from":[10],"prerecorded":[11],"datasets":[12,148],"without":[13],"online":[14],"environment":[15],"interaction.":[16],"It":[17],"is":[18,74,172],"unfortunate":[19],"that":[20],"extrapolation":[21],"errors":[22],"can":[23],"cause":[24],"over-optimistic":[25,133],"Q-value":[26,134],"estimates":[27,135],"when":[28],"with":[30,51,100,114],"a":[31],"fixed":[32],"dataset,":[33],"limiting":[34],"the":[35,38,58,62,65,68,71,77,81,87,90,96,106,119,124,127,143,150,153,157,163],"performance":[36,158],"of":[37,70,89,95,126,152,160,170],"learned":[39,82],"policy.":[40,92],"To":[41],"tackle":[42],"this":[43,45],"issue,":[44],"article":[46],"proposes":[47],"an":[48],"offline":[49,116,165],"actor-critic":[50,117],"behavior":[52,72,91,101,128],"value":[53,69,83,88,102,107,125],"regularization":[54,78,103],"(OAC-BVR)":[55],"method.":[56],"In":[57],"policy":[59,73,98],"evaluation":[60,99],"stage,":[61],"difference":[63,109],"between":[64],"Q-function":[66,138],"and":[67,105,136,146,156],"considered":[75],"as":[76],"term,":[79],"driving":[80],"function":[84,108],"approach":[86],"The":[93,168],"convergence":[94],"proposed":[97,120,154],"(PE-BVR)":[104],"are":[110],"analyzed,":[111],"respectively.":[112],"Compared":[113],"existing":[115],"methods,":[118],"OAC-BVR":[121,161,171],"method":[122],"integrates":[123],"policy,":[129],"thereby":[130],"simultaneously":[131],"alleviating":[132],"reducing":[137],"bias.":[139],"Experimental":[140],"results":[141],"on":[142],"D4RL":[144],"MuJoCo":[145],"Maze2d":[147],"demonstrate":[149],"validity":[151],"PE-BVR":[155],"advantage":[159],"over":[162],"state-of-the-art":[164],"RL":[166],"algorithms.":[167],"code":[169],"available":[173],"at":[174],"https://github.com/LongyangHuang/OAC-BVR.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}