{"id":"https://openalex.org/W7135094447","doi":"https://doi.org/10.1109/tpami.2026.3673238","title":"Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-Coupled Analysis","display_name":"Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-Coupled Analysis","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135094447","doi":"https://doi.org/10.1109/tpami.2026.3673238","pmid":"https://pubmed.ncbi.nlm.nih.gov/41817970"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3673238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3673238","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5101860657","display_name":"Tian Xu","orcid":"https://orcid.org/0000-0001-9409-448X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Xu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9409-448X","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012372957","display_name":"Ziniu Li","orcid":"https://orcid.org/0000-0003-0449-002X"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziniu Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0449-002X","affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128917412","display_name":"Yang Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1052-5447","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109441320","display_name":"Zhi-Quan Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi-Quan Luo","raw_affiliation_strings":["School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3995-914X","affiliations":[{"raw_affiliation_string":"School of Science and Engineering, Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.9137,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97445994,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"48","issue":"8","first_page":"8919","last_page":"8935"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.19760000705718994,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.19760000705718994,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.05090000107884407,"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/T12520","display_name":"Psychology of Moral and Emotional Judgment","score":0.048900000751018524,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7263000011444092},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5475999712944031},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.3930000066757202},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.36230000853538513},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3346000015735626}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7263000011444092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6588000059127808},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6085000038146973},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5475999712944031},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3662000000476837},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3346000015735626},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3673238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3673238","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41817970","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41817970","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3246209482","display_name":null,"funder_award_id":"623B2049","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5862880122","display_name":null,"funder_award_id":"62495093","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":18,"referenced_works":["https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2051228319","https://openalex.org/W2102847492","https://openalex.org/W2137983211","https://openalex.org/W2268617045","https://openalex.org/W2604382266","https://openalex.org/W2963389257","https://openalex.org/W3101780148","https://openalex.org/W3174663468","https://openalex.org/W3177163221","https://openalex.org/W3178520484","https://openalex.org/W3182474098","https://openalex.org/W4214717370","https://openalex.org/W4233559841","https://openalex.org/W4292022450","https://openalex.org/W4415795277","https://openalex.org/W6922480057"],"related_works":[],"abstract_inverted_index":{"Imitation":[0],"learning":[1,57],"(IL)":[2],"learns":[3],"a":[4,11,50,77,147,153,166,185,267],"policy":[5,260],"from":[6,171],"expert":[7,67,73,133,196],"trajectories,":[8,102],"serving":[9],"as":[10,83,121],"fundamental":[12,90],"paradigm":[13],"in":[14,76,126,211,263,285],"both":[15,212],"large":[16,127,215],"language":[17],"model":[18],"training":[19],"and":[20,38,103,135,190,214,244,265],"embodied":[21],"AI.":[22],"This":[23,271],"process":[24],"is":[25,179,192,209],"challenging":[26],"due":[27],"to":[28,117],"the":[29,72,139,180,193,223,232,241,251,258,276],"nature":[30],"of":[31,52,132,168,195,203,226,280],"sequential":[32],"decision-making":[33],"where":[34],"errors":[35],"can":[36,59,238],"accumulate":[37],"distributions":[39],"may":[40],"shift":[41,253],"over":[42,110],"horizons.":[43],"However,":[44],"it":[45,106],"has":[46],"been":[47],"found":[48],"that":[49,222],"kind":[51],"IL":[53],"approach,":[54],"adversarial":[55],"imitation":[56,155,224,278],"(AIL),":[58],"have":[60,136],"exceptional":[61],"empirical":[62,242],"performance.":[63],"With":[64],"just":[65],"one":[66],"trajectory,":[68],"AIL":[69,96,149,249],"often":[70],"matches":[71],"performance":[74,109],"even":[75],"long":[78,111],"horizon,":[79],"on":[80,138,165],"tasks":[81],"such":[82],"robotic":[84,172],"locomotion":[85,173],"control.":[86],"There":[87],"are":[88,123],"two":[89,200],"yet":[91],"unsolved":[92],"questions:":[93],"why":[94,104],"does":[95,105,228],"perform":[97],"well":[98],"with":[99,231],"so":[100],"few":[101],"maintain":[107],"good":[108],"horizons?":[112],"Previous":[113],"theoretical":[114],"results":[115],"fail":[116],"answer":[118],"these":[119],"questions":[120],"they":[122],"meaningful":[124,210],"only":[125],"sample":[128,216],"regime":[129],"(i.e.,":[130],"lots":[131],"trajectories)":[134],"dependence":[137],"decision":[140,233],"horizon.":[141,234],"In":[142],"this":[143,207,219],"paper,":[144],"we":[145],"analyze":[146,275],"total-variation-distance-based":[148],"(called":[150],"TV-AIL),":[151],"showing":[152],"horizon-free":[154],"gap":[156,225,279],"${\\mathcal":[157],"{O}}(\\min":[158],"\\lbrace":[159],"1,":[160],"\\sqrt{|{\\mathcal":[161],"{S}}|/N}":[162],"\\rbrace":[163],")$O(min{1,|S|/N})":[164],"class":[167],"instances":[169],"abstracted":[170],"control":[174],"tasks.":[175],"Here":[176],"$|{\\mathcal":[177],"{S}}|$|S|":[178],"state":[181],"space":[182],"size":[183],"for":[184],"Markov":[186],"Decision":[187],"Process":[188],"(MDP),":[189],"$N$N":[191],"number":[194],"trajectories.":[197],"We":[198],"emphasize":[199],"important":[201],"features":[202],"our":[204,236],"bound.":[205],"First,":[206],"bound":[208,220,237],"small":[213],"regimes.":[217],"Second,":[218],"suggests":[221],"TV-AIL":[227,264],"not":[229],"increase":[230],"Together,":[235],"therefore":[239],"explain":[240],"observations":[243],"provide":[245],"insights":[246],"into":[247],"how":[248],"addresses":[250],"distribution":[252],"issue.":[254],"Our":[255],"analysis":[256],"leverages":[257],"multi-stage":[259],"optimization":[261],"structure":[262],"presents":[266],"new":[268],"stage-coupled":[269],"analysis.":[270],"tool":[272],"also":[273],"helps":[274],"worst-case":[277],"TV-AIL,":[281],"disclosing":[282],"its":[283],"limitations":[284],"general":[286],"MDPs.":[287]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-03-13T00:00:00"}