{"id":"https://openalex.org/W4401806721","doi":"https://doi.org/10.1109/tnnls.2024.3443082","title":"De-Pessimism Offline Reinforcement Learning via Value Compensation","display_name":"De-Pessimism Offline Reinforcement Learning via Value Compensation","publication_year":2024,"publication_date":"2024-08-23","ids":{"openalex":"https://openalex.org/W4401806721","doi":"https://doi.org/10.1109/tnnls.2024.3443082","pmid":"https://pubmed.ncbi.nlm.nih.gov/39178073"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3443082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3443082","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/A5104098071","display_name":"Ziang Huang","orcid":"https://orcid.org/0000-0001-7772-921X"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenbo Huang","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7772-921X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065846668","display_name":"Jing Zhao","orcid":"https://orcid.org/0000-0003-0158-5330"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhao","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0158-5330","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047846625","display_name":"Shiliang Sun","orcid":"https://orcid.org/0000-0001-7069-3752"},"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":"Shiliang Sun","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7069-3752","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104098071"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":1.4667,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86366786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"36","issue":"7","first_page":"12655","last_page":"12667"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10270","display_name":"Blockchain Technology Applications and Security","score":0.921500027179718,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10270","display_name":"Blockchain Technology Applications and Security","score":0.921500027179718,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/pessimism","display_name":"Pessimism","score":0.7650736570358276},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7584606409072876},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.681382954120636},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.506747305393219},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.4924968183040619},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44608747959136963},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.38169774413108826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3622746765613556},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2291071116924286},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.21772289276123047},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09001383185386658},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.055792808532714844}],"concepts":[{"id":"https://openalex.org/C9992130","wikidata":"https://www.wikidata.org/wiki/Q484954","display_name":"Pessimism","level":2,"score":0.7650736570358276},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7584606409072876},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.681382954120636},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.506747305393219},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.4924968183040619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44608747959136963},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.38169774413108826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3622746765613556},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2291071116924286},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.21772289276123047},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09001383185386658},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.055792808532714844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3443082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3443082","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:39178073","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39178073","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/G5558540163","display_name":null,"funder_award_id":"22ZR1421700","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G5796687318","display_name":null,"funder_award_id":"62076096","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/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2522489477","https://openalex.org/W2772589676","https://openalex.org/W2904246096","https://openalex.org/W2963411833","https://openalex.org/W2978455699","https://openalex.org/W3015082424","https://openalex.org/W3092429416","https://openalex.org/W3182751084","https://openalex.org/W3189931457","https://openalex.org/W4226167551","https://openalex.org/W4226257065","https://openalex.org/W4246262524","https://openalex.org/W4360584316","https://openalex.org/W4377024253","https://openalex.org/W6604666559","https://openalex.org/W6630907848","https://openalex.org/W6634413486","https://openalex.org/W6679700999","https://openalex.org/W6687045409","https://openalex.org/W6737893269","https://openalex.org/W6747473740","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6769342953","https://openalex.org/W6771270455","https://openalex.org/W6776601253","https://openalex.org/W6777091672","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6779656125","https://openalex.org/W6780159193","https://openalex.org/W6791413555","https://openalex.org/W6792049622","https://openalex.org/W6795014841","https://openalex.org/W6796289742","https://openalex.org/W6796429164","https://openalex.org/W6796589144","https://openalex.org/W6802363888","https://openalex.org/W6802659552","https://openalex.org/W6804472631","https://openalex.org/W6838356327","https://openalex.org/W6840739175","https://openalex.org/W6849582448","https://openalex.org/W6858393028"],"related_works":["https://openalex.org/W4380987628","https://openalex.org/W2418537576","https://openalex.org/W2557514562","https://openalex.org/W214945085","https://openalex.org/W1987935396","https://openalex.org/W3126025002","https://openalex.org/W2354456418","https://openalex.org/W3197683035","https://openalex.org/W2006807542","https://openalex.org/W2374935031"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"has":[4],"been":[5],"widely":[6],"used":[7],"in":[8,88,119,145,190],"practice":[9],"due":[10],"to":[11,69,83,122],"its":[12,143],"efficient":[13],"data":[14],"utilization,":[15],"but":[16],"it":[17],"still":[18],"faces":[19],"the":[20,45,54,65,74,79,85,89,98,113,125,138,151,158,164,186],"challenge":[21],"of":[22,103,128,140,188],"training":[23],"vulnerability":[24],"caused":[25],"by":[26,57],"policy":[27,35,47,146],"deviation.":[28],"Existing":[29],"offline":[30,167],"RL":[31,168],"methods":[32],"that":[33],"add":[34],"constraints":[36],"or":[37,78,100],"perform":[38],"conservative":[39],"Q-value":[40,61],"estimation":[41],"are":[42,87],"pessimistic,":[43],"making":[44],"learned":[46],"suboptimal.":[48],"In":[49],"this":[50],"article,":[51],"we":[52,154],"address":[53],"pessimism":[55],"problem":[56],"focusing":[58],"on":[59,108],"accurate":[60],"estimation.":[62],"We":[63,135],"propose":[64],"de-pessimism":[66,166],"(DEP)":[67],"operator":[68,77,81,95],"estimate":[70],"Q":[71,126],"values":[72,121],"using":[73],"optimal":[75],"Bellman":[76],"compensation":[80,94],"according":[82],"whether":[84],"actions":[86,106],"behavior":[90,114],"support":[91],"set.":[92],"The":[93],"qualitatively":[96],"determines":[97],"positive":[99,129],"negative":[101],"nature":[102],"out-of-distribution":[104],"(OOD)":[105],"based":[107],"their":[109],"performance":[110,175],"compared":[111],"with":[112],"actions.":[115],"It":[116],"leverages":[117],"differences":[118],"state":[120],"compensate":[123],"for":[124],"value":[127],"OOD":[130],"actions,":[131],"thereby":[132],"alleviating":[133],"pessimism.":[134,192],"theoretically":[136],"demonstrate":[137],"convergence":[139],"DEP":[141,156,189],"and":[142,181],"effectiveness":[144],"improvement.":[147],"To":[148],"further":[149],"advance":[150],"practical":[152],"application,":[153],"integrate":[155],"into":[157],"soft":[159],"actor-critic":[160],"(SAC)":[161],"algorithm,":[162],"yielding":[163],"value-compensated":[165],"(DoRL-VC).":[169],"Experimentally,":[170],"DoRL-VC":[171],"achieves":[172],"state-of-the-art":[173],"(SOTA)":[174],"across":[176],"mujoco":[177],"locomotion,":[178],"Maze":[179],"2-D,":[180],"challenging":[182],"Adroit":[183],"tasks,":[184],"illustrating":[185],"efficacy":[187],"mitigating":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}