{"id":"https://openalex.org/W7125768074","doi":"https://doi.org/10.1109/tpami.2026.3657578","title":"Adversarial Imitation Learning With General Function Approximation: Theoretical Analysis and Practical Algorithms","display_name":"Adversarial Imitation Learning With General Function Approximation: Theoretical Analysis and Practical Algorithms","publication_year":2026,"publication_date":"2026-01-27","ids":{"openalex":"https://openalex.org/W7125768074","doi":"https://doi.org/10.1109/tpami.2026.3657578","pmid":"https://pubmed.ncbi.nlm.nih.gov/41587257"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3657578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3657578","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/A5123977788","display_name":"Tian Xu","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":"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/A5124038853","display_name":"Zhilong Zhang","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":"Zhilong Zhang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China"],"raw_orcid":null,"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/A5124015328","display_name":"Zexuan Chen","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":"Zexuan Chen","raw_affiliation_strings":["School of Artificial Intelligence, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123918225","display_name":"Ruishuo Chen","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":"Ruishuo Chen","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0007-9804-8967","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/A5123921794","display_name":"Yihao Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yihao Sun","raw_affiliation_strings":["Mila-Quebec Artificial Intelligence Institute, Montréal, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila-Quebec Artificial Intelligence Institute, Montréal, QC, Canada","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124048747","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"]}]}],"institutions":[],"countries_distinct_count":2,"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":0.09550186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"6","first_page":"6380","last_page":"6392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8720999956130981,"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":0.8720999956130981,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.016899999231100082,"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":0.012799999676644802,"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/adversarial-system","display_name":"Adversarial system","score":0.7491000294685364},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.6406999826431274},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5719000101089478},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4961000084877014},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48080000281333923},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46369999647140503},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.39320001006126404},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.37070000171661377},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.36559998989105225}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7491000294685364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7059000134468079},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.6406999826431274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6243000030517578},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4961000084877014},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4771000146865845},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46369999647140503},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.39320001006126404},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38029998540878296},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C50292564","wikidata":"https://www.wikidata.org/wiki/Q2462783","display_name":"Computational learning theory","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2689000070095062},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25920000672340393}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3657578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3657578","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:41587257","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41587257","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"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1999874108","https://openalex.org/W2051228319","https://openalex.org/W2104753538","https://openalex.org/W2145339207","https://openalex.org/W2513180554","https://openalex.org/W2959895084","https://openalex.org/W2962787969","https://openalex.org/W2963654596","https://openalex.org/W3130395087","https://openalex.org/W3178520484","https://openalex.org/W3182474098","https://openalex.org/W4211030719","https://openalex.org/W4403326725","https://openalex.org/W4414079054","https://openalex.org/W7133208018","https://openalex.org/W7133211745","https://openalex.org/W7135094447"],"related_works":[],"abstract_inverted_index":{"Adversarial":[0],"imitation":[1,8],"learning":[2,87,124],"(AIL),":[3],"a":[4,48,74,146],"prominent":[5],"approach":[6],"in":[7],"learning,":[9],"has":[10],"achieved":[11],"significant":[12],"practical":[13,44,147,160],"success":[14],"powered":[15],"by":[16,60],"neural":[17],"network":[18],"approximation.":[19,71,144],"However,":[20],"existing":[21],"theoretical":[22,63,109],"analyses":[23],"of":[24,65,130,155],"AIL":[25,67,79,139,171],"are":[26],"primarily":[27],"confined":[28],"to":[29],"simplified":[30],"settings-such":[31],"as":[32],"tabular":[33],"and":[34,53,105,120],"linear":[35],"function":[36,70,143],"approximation-and":[37],"involve":[38],"complex":[39],"algorithmic":[40],"designs":[41],"that":[42,112,165],"impede":[43],"implementation.":[45,161],"This":[46,55],"creates":[47],"substantial":[49],"gap":[50,59],"between":[51],"theory":[52],"practice.":[54],"paper":[56],"bridges":[57],"this":[58,96],"exploring":[61],"the":[62,128,135,152],"underpinnings":[64],"online":[66,83],"with":[68,89],"general":[69,142],"We":[72],"introduce":[73],"novel":[75],"framework":[76],"called":[77],"optimization-based":[78],"(OPT-AIL),":[80],"which":[81],"performs":[82],"optimization":[84,91,154],"for":[85,92,123],"reward":[86],"coupled":[88],"optimism-regularized":[90],"policy":[93],"learning.":[94],"Within":[95],"framework,":[97],"we":[98],"develop":[99],"two":[100,156],"concrete":[101],"methods:":[102],"model-free":[103],"OPT-AIL":[104,149,166],"model-based":[106],"OPT-AIL.":[107],"Our":[108],"analysis":[110],"demonstrates":[111],"both":[113],"variants":[114],"achieve":[115],"polynomial":[116],"expert":[117],"sample":[118],"complexity":[119,122],"interaction":[121],"near-expert":[125],"policies.":[126],"To":[127],"best":[129],"our":[131],"knowledge,":[132],"they":[133],"represent":[134],"first":[136],"provably":[137],"efficient":[138],"methods":[140,172],"under":[141],"From":[145],"standpoint,":[148],"requires":[150],"only":[151],"approximate":[153],"objectives,":[157],"thereby":[158],"facilitating":[159],"Empirical":[162],"studies":[163],"demonstrate":[164],"outperforms":[167],"previous":[168],"state-of-the-art":[169],"deep":[170],"across":[173],"several":[174],"challenging":[175],"tasks.":[176]},"counts_by_year":[],"updated_date":"2026-05-09T06:09:20.037420","created_date":"2026-01-28T00:00:00"}