{"id":"https://openalex.org/W4412353404","doi":"https://doi.org/10.1109/tsmc.2025.3583392","title":"PCDT: Pessimistic Critic Decision Transformer for Offline Reinforcement Learning","display_name":"PCDT: Pessimistic Critic Decision Transformer for Offline Reinforcement Learning","publication_year":2025,"publication_date":"2025-07-11","ids":{"openalex":"https://openalex.org/W4412353404","doi":"https://doi.org/10.1109/tsmc.2025.3583392"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2025.3583392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3583392","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5108064895","display_name":"Xuesong Wang","orcid":"https://orcid.org/0000-0002-5327-1088"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuesong Wang","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5327-1088","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101714293","display_name":"Hengrui Zhang","orcid":"https://orcid.org/0000-0001-5090-3177"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengrui Zhang","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101885863","display_name":"Jiazhi Zhang","orcid":"https://orcid.org/0009-0009-8963-6374"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiazhi Zhang","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-8963-6374","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643265","display_name":"C. L. Philip Chen","orcid":"https://orcid.org/0000-0001-5451-7230"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"C. L. Philip Chen","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5451-7230","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091364297","display_name":"Yuhu Cheng","orcid":"https://orcid.org/0000-0003-2022-9999"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhu Cheng","raw_affiliation_strings":["School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2022-9999","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6847,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93036878,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"55","issue":"10","first_page":"7247","last_page":"7258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8442999720573425,"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":0.8442999720573425,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7485544681549072},{"id":"https://openalex.org/keywords/pessimism","display_name":"Pessimism","score":0.6622384190559387},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.640756368637085},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6020129323005676},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4503357708454132},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.393196165561676},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3536418080329895},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21762153506278992},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.17579591274261475},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12325641512870789},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08919748663902283},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.05114471912384033}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7485544681549072},{"id":"https://openalex.org/C9992130","wikidata":"https://www.wikidata.org/wiki/Q484954","display_name":"Pessimism","level":2,"score":0.6622384190559387},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.640756368637085},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6020129323005676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4503357708454132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.393196165561676},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3536418080329895},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21762153506278992},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.17579591274261475},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12325641512870789},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08919748663902283},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.05114471912384033},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2025.3583392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3583392","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4756161396","display_name":null,"funder_award_id":"62176259","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4823360002","display_name":null,"funder_award_id":"62373364","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6172462902","display_name":null,"funder_award_id":"BE2022095","funder_id":"https://openalex.org/F4320327780","funder_display_name":"Key Research and Development Program of Jiangxi Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327780","display_name":"Key Research and Development Program of Jiangxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W3045372678","https://openalex.org/W3129584569","https://openalex.org/W3188220908","https://openalex.org/W4385938565","https://openalex.org/W4393159899","https://openalex.org/W4396542660","https://openalex.org/W4400070556","https://openalex.org/W4402041279","https://openalex.org/W4402435476"],"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":{"DT,":[0],"as":[1,19],"a":[2,23,79,93,120,162],"conditional":[3],"sequence":[4,105,152],"modeling":[5],"(CSM)":[6],"approach,":[7],"learns":[8],"the":[9,36,53,71,77,104,127,132,137,145,151,167,177,182,193,202],"action":[10],"distribution":[11],"for":[12,27,55,83],"each":[13],"state":[14],"using":[15],"historical":[16],"information,":[17],"such":[18],"trajectory":[20,47,72],"returns,":[21],"offering":[22],"supervised":[24],"learning":[25,30,176],"paradigm":[26],"offline":[28],"reinforcement":[29],"(Offline":[31],"RL).":[32],"However,":[33],"due":[34],"to":[35,96,108,135],"fact":[37],"that":[38,111,150,171,190],"decision":[39,158],"transformer":[40,159],"(DT)":[41],"solely":[42],"concentrates":[43],"on":[44,181,206],"an":[45],"individual":[46],"with":[48,144],"high":[49],"returns-to-go,":[50],"it":[51],"neglects":[52],"potential":[54],"constructing":[56,119],"optimal":[57,178],"trajectories":[58],"by":[59,91],"combining":[60],"sequences":[61],"of":[62,175,195],"different":[63],"actions.":[64],"In":[65],"other":[66],"words,":[67],"traditional":[68],"DT":[69,81,95],"lacks":[70],"stitching":[73],"capability.":[74],"To":[75],"address":[76],"concern,":[78],"novel":[80],"(PCDT)":[82,160],"Offline":[84],"RL":[85],"is":[86,173],"proposed.":[87],"Our":[88,212],"approach":[89],"begins":[90],"pretraining":[92],"standard":[94],"explicitly":[97],"capture":[98],"behavior":[99,116,138],"sequences.":[100],"Next,":[101],"we":[102],"apply":[103],"importance":[106,153],"sampling":[107,154],"penalize":[109],"actions":[110,142],"significantly":[112],"deviate":[113],"from":[114],"these":[115],"sequences,":[117],"thereby":[118],"pessimistic":[121,156,163],"critic.":[122],"Finally,Q-values":[123],"are":[124,214],"integrated":[125],"into":[126],"policy":[128,134,139],"update":[129],"process,":[130],"enabling":[131],"learned":[133],"approximate":[136],"while":[140,166],"favoring":[141],"associated":[143],"highestQ-value.":[146],"Theoretical":[147],"analysis":[148],"shows":[149],"in":[155],"critic":[157],"establishes":[161],"lower":[164],"bound,":[165],"value":[168],"optimality":[169],"ensures":[170],"PCDT":[172,191],"capable":[174],"policy.":[179],"Results":[180],"D4RL":[183],"benchmark":[184],"tasks":[185],"and":[186,198,209],"ablation":[187],"studies":[188],"show":[189],"inherits":[192],"strengths":[194],"actor\u2013critic":[196],"(AC)":[197],"CSM":[199],"methods,":[200],"achieving":[201],"highest":[203],"normalized":[204],"scores":[205],"challenging":[207],"sparse-reward":[208],"long-horizon":[210],"tasks.":[211],"code":[213],"available":[215],"at":[216],"https://github.com/Henry0132/PCDT.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
