{"id":"https://openalex.org/W7104902537","doi":"https://doi.org/10.1109/tii.2025.3627122","title":"Horizon-Greedy <i>Q</i> -Ensembles Regularized Decision Transformer: An Offline Reinforcement Learning Approach for Robotic Tasks","display_name":"Horizon-Greedy <i>Q</i> -Ensembles Regularized Decision Transformer: An Offline Reinforcement Learning Approach for Robotic Tasks","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7104902537","doi":"https://doi.org/10.1109/tii.2025.3627122"},"language":null,"primary_location":{"id":"doi:10.1109/tii.2025.3627122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2025.3627122","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","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":null,"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":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2026-6856","affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Dong","orcid":"https://orcid.org/0009-0001-4042-628X"},"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":"Xin Dong","raw_affiliation_strings":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-4042-628X","affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xi Chen","orcid":null},"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":"Xi Chen","raw_affiliation_strings":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mingxuan Wang","orcid":null},"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":"Mingxuan Wang","raw_affiliation_strings":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hongtian Chen","orcid":"https://orcid.org/0000-0002-8600-9668"},"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":"Hongtian Chen","raw_affiliation_strings":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8600-9668","affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8902817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"22","issue":"2","first_page":"1440","last_page":"1451"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8513000011444092,"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":0.8513000011444092,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.032600000500679016,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.028200000524520874,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.76910001039505},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7106000185012817},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5005000233650208},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.48100000619888306},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.39250001311302185},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.3555000126361847},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.35249999165534973},{"id":"https://openalex.org/keywords/grippers","display_name":"Grippers","score":0.33149999380111694}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.76910001039505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715499997138977},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7106000185012817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.628600001335144},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5026999711990356},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5005000233650208},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.48100000619888306},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.39250001311302185},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.32919999957084656},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.2870999872684479},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27149999141693115},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.26429998874664307},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tii.2025.3627122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2025.3627122","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7658259272575378,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G7941178911","display_name":null,"funder_award_id":"62303308","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":17,"referenced_works":["https://openalex.org/W2761873684","https://openalex.org/W2962787969","https://openalex.org/W4311486598","https://openalex.org/W4320015828","https://openalex.org/W4378422081","https://openalex.org/W4385833430","https://openalex.org/W4389799499","https://openalex.org/W4392477589","https://openalex.org/W4393159899","https://openalex.org/W4403447678","https://openalex.org/W4403863643","https://openalex.org/W4405598230","https://openalex.org/W4408913787","https://openalex.org/W4410399797","https://openalex.org/W4415796382","https://openalex.org/W4415797569","https://openalex.org/W4415797675"],"related_works":[],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,9],"(RL)":[3],"offers":[4],"a":[5,74,97,122],"promising":[6],"paradigm":[7],"for":[8,69,77],"policies":[10],"from":[11,117],"precollected":[12],"datasets.":[13],"Nonetheless,":[14],"applying":[15],"it":[16],"to":[17,111],"robotic":[18,70,142,158],"control":[19],"poses":[20],"significant":[21],"challenges,":[22],"including":[23],"non-Markovian":[24,86],"dynamics":[25],"and":[26,135,144],"the":[27,37,49,90],"scarcity":[28],"of":[29,33,39,92],"high-quality":[30],"demonstrations,":[31,94],"both":[32],"which":[34,131],"can":[35],"undermine":[36],"performance":[38],"existing":[40],"methods.":[41],"To":[42,88],"address":[43],"these":[44],"issues,":[45],"this":[46],"work":[47],"introduces":[48],"horizon-<italic":[50],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[51,54,57,61,124],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">G</i>reedy":[52],"<italic":[53,56,60,123],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Q</i>-ensembles":[55],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">R</i>egularized":[58],"decision":[59],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">T</i>ransformer":[62],"(GQRT),":[63],"an":[64],"offline":[65],"RL":[66],"algorithm":[67],"tailored":[68],"tasks.":[71],"GQRT":[72,149],"leverages":[73],"transformer-based":[75],"policy":[76,100],"trajectory":[78],"modeling,":[79],"thereby":[80],"enabling":[81],"effective":[82],"long-horizon":[83],"decision-making":[84],"in":[85,156],"settings.":[87],"alleviate":[89],"lack":[91],"expert":[93],"we":[95,120],"develop":[96],"multistep":[98],"horizon-greedy":[99],"evaluation":[101],"mechanism":[102],"that":[103,148],"stitches":[104],"suboptimal":[105],"sequences":[106],"into":[107],"improved":[108],"trajectories.":[109],"Furthermore,":[110],"cope":[112],"with":[113,126],"mixed-quality":[114],"demonstrations":[115],"collected":[116],"diverse":[118],"sources,":[119],"incorporate":[121],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Q</i>-ensemble":[125],"lower":[127],"confidence":[128],"bound":[129],"regularization,":[130],"ensures":[132],"more":[133],"stable":[134],"reliable":[136],"value":[137],"estimation.":[138],"Extensive":[139],"experiments":[140],"on":[141],"locomotion":[143],"manipulation":[145],"benchmarks":[146],"demonstrate":[147],"achieves":[150],"state-of-the-art":[151],"performance,":[152],"validating":[153],"its":[154],"robustness":[155],"complex":[157],"scenarios.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-12T00:00:00"}