{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,30]],"date-time":"2025-08-30T17:07:42Z","timestamp":1756573662259,"version":"3.28.0"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF-CAREER-EPCN-2045783,NSF-CNS 1955696"],"award-info":[{"award-number":["NSF-CAREER-EPCN-2045783,NSF-CNS 1955696"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10383976","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:36Z","timestamp":1705689516000},"page":"1342-1347","source":"Crossref","is-referenced-by-count":1,"title":["Distributionally Robust Behavioral Cloning for Robust Imitation Learning"],"prefix":"10.1109","author":[{"given":"Kishan","family":"Panaganti","sequence":"first","affiliation":[{"name":"Texas A&M University,Department of Electrical and Computer Engineering,College Station,TX,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zaiyan","family":"Xu","sequence":"additional","affiliation":[{"name":"Texas A&M University,Department of Electrical and Computer Engineering,College Station,TX,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dileep","family":"Kalathil","sequence":"additional","affiliation":[{"name":"Texas A&M University,Department of Electrical and Computer Engineering,College Station,TX,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad","family":"Ghavamzadeh","sequence":"additional","affiliation":[{"name":"Google Research,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10071-014-0803-7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918770733"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2018.8460528"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/s21010073"},{"key":"ref6","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume-title":"Advances in Neural Information Processing Systems","author":"Pomerleau","year":"1988"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538677.003.0006"},{"key":"ref8","article-title":"Efficient reductions for imitation learning","volume-title":"13th international conference on artificial intelligence and statistics","author":"Ross","year":"2010"},{"key":"ref9","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"14th international conference on artificial intelligence and statistics","author":"Ross","year":"2011"},{"key":"ref10","article-title":"Disagreement-regularized imitation learning","volume-title":"International Conference on Learning Representations","author":"Brantley","year":"2019"},{"key":"ref11","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"15737","article-title":"Error bounds of imitating policies and environments","volume":"33","author":"Xu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","first-page":"24404","article-title":"Distributionally robust imitation learning","volume":"34","author":"Bashiri","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1040.0129"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1050.0216"},{"volume-title":"Closing the sim2real gap with nvidia isaac sim and nvidia isaac replicator","year":"2021","author":"Corporation","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1120.0540"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1120.0566"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2495174"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2016.0786"},{"key":"ref21","article-title":"Beyond confidence regions: Tight bayesian ambiguity sets for robust mdps","volume-title":"Advances in Neural Information Processing Systems","author":"Russel","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1214\/22-AOS2225"},{"key":"ref23","article-title":"Sample complexity of robust reinforcement learning with a generative model","volume-title":"Proceedings of The 25th International Conference on Artificial Intelligence and Statistics","author":"Panaganti","year":"2022"},{"key":"ref24","article-title":"Improved sample complexity bounds for distributionally robust reinforcement learning","volume-title":"Conference on Artificial Intelligence and Statistics","author":"Xu","year":"2023"},{"key":"ref25","first-page":"511","article-title":"Robust reinforcement learning using least squares policy iteration with provable performance guarantees","volume-title":"International Conference on Machine Learning (ICML)","author":"Panaganti","year":"2021"},{"key":"ref26","article-title":"Robust reinforcement learning using offline data","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Panaganti","year":"2022"},{"key":"ref27","first-page":"7193","article-title":"Online robust reinforcement learning with model uncertainty","volume":"34","author":"Wang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1214\/20-aos2004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/16M1058297"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1275"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1125-8"},{"key":"ref32","article-title":"Stochastic gradient methods for distributionally robust optimization with f-divergences","volume":"29","author":"Namkoong","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1017\/jpr.2019.49"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/en13184826"},{"volume-title":"10 best healthcare data sets & examples","year":"2021","author":"Travers","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00957"},{"journal-title":"Openai gym","year":"2016","author":"Brockman","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref39","first-page":"2914","article-title":"Toward the fundamental limits of imitation learning","volume":"33","author":"Rajaraman","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1214\/22-AOS2225"},{"key":"ref41","first-page":"9582","article-title":"Sample complexity of robust reinforcement learning with a generative model","volume-title":"International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"Panaganti","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1561\/2400000026"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611.ch15"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.2307\/1403865"},{"volume-title":"Reinforcement learning: Theory and algorithms","year":"2019","author":"Agarwal","key":"ref45"},{"key":"ref46","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International Conference on Machine Learning","author":"Fujimoto","year":"2018"},{"volume-title":"Rl baselines3 zoo","year":"2020","author":"Raffin","key":"ref47"},{"key":"ref48","first-page":"965","article-title":"Mitigating covariate shift in imitation learning via offline data with partial coverage","volume":"34","author":"Chang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","article-title":"A software package for sequential quadratic programming","author":"Kraft","year":"1988","journal-title":"Forschungsbericht- Deutsche Forschungs- und Versuchsanstalt fur Luft-und Raumfahrt"},{"journal-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref50"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2023,12,13]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10383976.pdf?arnumber=10383976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:39:34Z","timestamp":1706027974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10383976\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10383976","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}