{"id":"https://openalex.org/W7214712913","doi":"https://doi.org/10.48550/arxiv.2609.35698","title":"Provable Benefits of Regularization: Fast Rates for Adversarial Imitation Learning","display_name":"Provable Benefits of Regularization: Fast Rates for Adversarial Imitation Learning","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214712913","doi":"https://doi.org/10.48550/arxiv.2609.35698"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.35698","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35698","pdf_url":"https://arxiv.org/pdf/2609.35698","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.35698","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153448021","display_name":"Hanbin Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhou, Hanbin","raw_affiliation_strings":["HKUST(GZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST(GZ","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153429193","display_name":"Shangzhe Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Shangzhe","raw_affiliation_strings":["UNC Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153464674","display_name":"Alexander Braverman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Braverman, Alexander","raw_affiliation_strings":["Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153483023","display_name":"Weitong Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Weitong","raw_affiliation_strings":["UNC Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":9.999999747378752e-05,"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/adversarial-imitation-learning","display_name":"adversarial imitation learning","score":1.0},{"id":"https://openalex.org/keywords/policy-regularization","display_name":"policy regularization","score":0.7609999775886536},{"id":"https://openalex.org/keywords/kl-divergence-regularization","display_name":"KL divergence regularization","score":0.6200000047683716},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"sample complexity","score":0.5789999961853027},{"id":"https://openalex.org/keywords/nonasymptotic-bounds","display_name":"non-asymptotic bounds","score":0.6389999985694885},{"id":"https://openalex.org/keywords/online-mirror-descent","display_name":"online mirror descent","score":0.6869999766349792},{"id":"https://openalex.org/keywords/finite-horizon-markov-decision-processes","display_name":"finite-horizon Markov decision processes","score":0.8299999833106995},{"id":"https://openalex.org/keywords/expert-demonstrations","display_name":"expert demonstrations","score":0.49300000071525574},{"id":"https://openalex.org/keywords/gail","display_name":"GAIL","score":0.5849999785423279}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7251999974250793},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6608999967575073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5748000144958496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5737000107765198},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.506600022315979},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4180000126361847},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.38280001282691956},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35040000081062317},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2815000116825104},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.27720001339912415},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C79248915","wikidata":"https://www.wikidata.org/wiki/Q17086776","display_name":"Proximal gradient methods for learning","level":5,"score":0.2556000053882599},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.35698","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35698","pdf_url":"https://arxiv.org/pdf/2609.35698","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.35698","doi":"https://doi.org/10.48550/arxiv.2609.35698","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.35698","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.35698","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35698","pdf_url":"https://arxiv.org/pdf/2609.35698","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214712913.pdf","grobid_xml":"https://content.openalex.org/works/W7214712913.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W1999874108","https://openalex.org/W2973115103","https://openalex.org/W3194200810"],"related_works":["https://openalex.org/W4386043381","https://openalex.org/W4301351599","https://openalex.org/W4415797316","https://openalex.org/W4417134195","https://openalex.org/W3192378636","https://openalex.org/W4416159171","https://openalex.org/W4290074427","https://openalex.org/W7125768074","https://openalex.org/W3174148175","https://openalex.org/W2890026535"],"abstract_inverted_index":{"We":[0,54],"study":[1],"adversarial":[2,21],"imitation":[3,108],"learning":[4],"(AIL),":[5],"in":[6,62,167,199],"which":[7],"an":[8,20,117],"agent":[9],"learns":[10],"to":[11,127,161],"imitate":[12],"expert":[13,25,88,98,133,169],"demonstrations":[14,170],"by":[15,87],"optimizing":[16],"a":[17,82,102,140,186],"policy":[18,34,79,146,197],"against":[19],"reward":[22,30,84,125,195],"that":[23],"distinguishes":[24],"and":[26,32,46,89,96,135,171,196],"learner":[27,90,137],"behavior.":[28],"Historically,":[29],"regularization":[31,35,80,112,198],"entropy-based":[33],"are":[36],"key":[37],"components":[38],"of":[39,143,151,189,194],"empirically":[40],"successful":[41],"methods":[42],"such":[43],"as":[44],"GAIL":[45],"LS-IQ,":[47],"yet":[48],"their":[49],"finite-sample":[50],"benefits":[51,193],"remain":[52],"underexplored.":[53],"establish":[55],"fast":[56],"rates":[57],"for":[58,110,122,174],"jointly":[59],"regularized":[60,107,176],"AIL":[61,156,177],"finite-horizon":[63],"Markov":[64],"decision":[65],"processes":[66],"with":[67,81,139,180],"general":[68,123],"function":[69],"approximation.":[70],"Our":[71,114],"model-free":[72],"algorithm,":[73],"Dually":[74,154],"Regularized":[75,155],"AIL,":[76],"combines":[77,116],"KL":[78],"quadratic":[83],"penalty":[85],"weighted":[86],"occupancies.":[91],"With":[92],"K":[93],"online":[94,118,172],"episodes":[95],"N":[97],"trajectories,":[99],"we":[100],"prove":[101],"$\\widetilde{O}\\left(\\frac{1}{K}+\\frac{1}{N}\\right)$":[103],"bound":[104],"on":[105],"the":[106,149,158,190],"gap":[109],"fixed":[111],"parameters.":[113],"analysis":[115,142],"mirror":[119],"descent":[120],"construction":[121],"convex":[124],"classes":[126],"control":[128],"estimation":[129],"error":[130],"from":[131],"finite":[132],"data":[134],"stochastic":[136,181],"feedback,":[138],"sharp":[141],"optimistic":[144],"KL-regularized":[145],"learning.":[147],"To":[148],"best":[150],"our":[152],"knowledge,":[153],"is":[157],"first":[159],"algorithm":[160],"simultaneously":[162],"achieve":[163],"$\\widetilde{O}\\left(\\frac{1}\u03b5\\right)$":[164],"sample":[165],"complexity":[166],"both":[168],"interactions":[173],"this":[175],"objective,":[178],"even":[179],"experts.":[182],"These":[183],"results":[184],"provide":[185],"rigorous":[187],"characterization":[188],"complementary":[191],"statistical":[192],"AIL.":[200]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}