{"id":"https://openalex.org/W7162470533","doi":"https://doi.org/10.1109/tase.2026.3697024","title":"Prioritizing Expert-Like Transitions for Reward-Free Offline Imitation Learning","display_name":"Prioritizing Expert-Like Transitions for Reward-Free Offline Imitation Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7162470533","doi":"https://doi.org/10.1109/tase.2026.3697024"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2026.3697024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3697024","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","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/A5127481402","display_name":"Zhiliang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiliang Lin","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-1864-9440","affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049290416","display_name":"Z C Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuangzhuang Chen","raw_affiliation_strings":["Intelligent Computing Center, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0336-1181","affiliations":[{"raw_affiliation_string":"Intelligent Computing Center, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127191042","display_name":"Guanming Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanming Zhu","raw_affiliation_strings":["Intelligent Computing Center, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0005-4843-2739","affiliations":[{"raw_affiliation_string":"Intelligent Computing Center, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137022726","display_name":"Li Wang","orcid":"https://orcid.org/0000-0001-8707-3269"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Wang","raw_affiliation_strings":["School of Artificial Intelligence, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8707-3269","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136996256","display_name":"Jianqiang Li","orcid":"https://orcid.org/0000-0002-2208-962X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Li","raw_affiliation_strings":["School of Artificial Intelligence, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2208-962X","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65380863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"10337","last_page":"10349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6376000046730042,"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":0.6376000046730042,"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":0.12929999828338623,"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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.046799998730421066,"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/imitation","display_name":"Imitation","score":0.36579999327659607},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.32199999690055847},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.2768999934196472},{"id":"https://openalex.org/keywords/grippers","display_name":"Grippers","score":0.27480000257492065},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2558000087738037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5817000269889832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5151000022888184},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35749998688697815},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31790000200271606},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2768999934196472},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2026.3697024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3697024","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1646442845","display_name":null,"funder_award_id":"62473264","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3550247469","display_name":null,"funder_award_id":"KJZD20230923113801004","funder_id":"https://openalex.org/F4320326705","funder_display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality"},{"id":"https://openalex.org/G5051009293","display_name":null,"funder_award_id":"2023B1515120038","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G8411257915","display_name":null,"funder_award_id":"62203134","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8955274695","display_name":null,"funder_award_id":"62373257","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/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320326705","display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Offline":[0],"imitation":[1],"learning":[2,241],"(IL)":[3],"enables":[4],"embodied":[5],"agents":[6],"of":[7,51,174,239],"AI-driven":[8],"automation":[9],"control":[10,269],"systems":[11,270],"to":[12,94,197,218],"acquire":[13],"policies":[14],"from":[15,78,98,117],"demonstrations":[16,26,89],"without":[17],"interacting":[18],"with":[19,211],"the":[20,46,105,128,153,208,235],"environment.":[21],"However,":[22],"collecting":[23],"extensive":[24],"expert":[25,53,64,118,158,198],"that":[27,73,146,231],"rely":[28],"on":[29,48,157,176,226],"a":[30,140,187],"manually":[31,180],"designed":[32,181],"reward":[33,85,154,189,240,252],"function":[34,155],"is":[35],"labor-intensive,":[36],"and":[37,65,108,160,237,242,254,266,275],"even":[38],"impractical":[39],"for":[40,81,166,191,262],"dynamic":[41],"real-world":[42],"settings.":[43],"To":[44],"mitigate":[45],"reliance":[47],"large":[49],"amounts":[50],"reward-annotated":[52],"data,":[54],"previous":[55],"works":[56],"have":[57],"made":[58],"great":[59],"efforts":[60],"by":[61,127,193],"leveraging":[62],"both":[63],"suboptimal":[66,79,88,111],"demonstrations.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,133],"reveal":[72],"existing":[74],"methods":[75],"still":[76],"suffer":[77],"results":[80],"two":[82],"reasons:":[83],"(i)":[84],"signals":[86],"in":[87,121,207,264],"are":[90,114],"not":[91,103],"reliable,":[92],"due":[93],"these":[95],"rewards":[96,178,202],"derived":[97],"inexperienced":[99],"annotators,":[100],"thus":[101],"can":[102],"reflect":[104],"actual":[106],"rewards,":[107,182],"(ii)":[109],"those":[110],"demonstrations,":[112],"which":[113],"significantly":[115],"distant":[116],"behaviors,":[119],"result":[120],"low":[122],"reconstructed":[123],"rewards.":[124],"Moreover,":[125],"motivated":[126],"recent":[129],"diffusion-based":[130],"foundation":[131],"model,":[132],"propose":[134],"Expert-Like":[135],"Transition":[136],"Imitation":[137],"Learning":[138],"(ELTIL),":[139],"novel":[141],"generative":[142],"trajectory":[143,169],"augmentation":[144],"method":[145],"effectively":[147],"leverages":[148],"diffusion":[149,209],"models.":[150],"ELTIL":[151,183,232,260],"re-designs":[152],"based":[156],"proximity,":[159],"then":[161,203],"proposes":[162],"amplified":[163,212],"return":[164],"conditioning":[165,216],"achieving":[167],"high-quality":[168],"generation.":[170],"More":[171],"specifically,":[172],"instead":[173],"relying":[175],"environment-provided":[177],"or":[179],"first":[184],"serves":[185],"as":[186,205,215,272],"good":[188],"labeler":[190],"transitions":[192],"measuring":[194],"their":[195],"distance":[196],"states.":[199],"These":[200,257],"re-designed":[201],"serve":[204],"guidance":[206],"process,":[210],"returns":[213],"contributing":[214],"values":[217],"bias":[219],"generation":[220],"toward":[221],"expert-consistent":[222],"behaviors.":[223],"Extensive":[224],"experiments":[225],"diverse":[227],"D4RL":[228],"benchmarks":[229],"demonstrate":[230],"consistently":[233],"improves":[234],"performance":[236],"stability":[238],"offline":[243],"IL":[244],"methods,":[245],"maintaining":[246],"reliability":[247],"under":[248],"varying":[249],"noise":[250],"levels,":[251],"sparsity,":[253],"dataset":[255],"distributions.":[256],"characteristics":[258],"make":[259],"well-suited":[261],"deployment":[263],"robust":[265],"reliable":[267],"automated":[268],"such":[271],"robotic":[273],"manipulation":[274],"autonomous":[276],"driving.":[277]},"counts_by_year":[],"updated_date":"2026-06-04T06:14:18.571774","created_date":"2026-05-27T00:00:00"}