{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T16:44:48Z","timestamp":1776789888200,"version":"3.51.2"},"reference-count":25,"publisher":"IEEE","funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CAREER-2048168"],"award-info":[{"award-number":["CAREER-2048168"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,25]]},"DOI":"10.23919\/acc50511.2021.9483019","type":"proceedings-article","created":{"date-parts":[[2021,7,28]],"date-time":"2021-07-28T20:29:16Z","timestamp":1627504156000},"page":"882-887","source":"Crossref","is-referenced-by-count":8,"title":["On Imitation Learning of Linear Control Policies: Enforcing Stability and Robustness Constraints via LMI Conditions"],"prefix":"10.23919","author":[{"given":"Aaron","family":"Havens","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2012.08.012"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2319577"},{"key":"ref12","article-title":"Hoo model-free reinforcement learning with robust stability guarantee","author":"han","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref13","article-title":"Policy optimization for H2 linear control with H? robustness guarantee: Implicit regularization and global convergence","author":"zhang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref14","article-title":"On the stability and convergence of robust adversarial reinforcement learning: A case study on linear quadratic systems","volume":"33","author":"zhang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Derivative-free policy optimization for risk-sensitive and robust control design: Implicit regularization and sample complexity","author":"zhang","year":"0","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"Enforcing robust control guarantees within neural network policies","author":"donti","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1966.1098316"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1201\/b15060"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989382"},{"key":"ref4","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2300000053"},{"key":"ref6","volume":"104","author":"zhou","year":"1998","journal-title":"Essentials of Robust Control"},{"key":"ref5","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Imitation learning with stability and safety guarantees","author":"yin","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref7","first-page":"374","article-title":"Fitting a linear control policy to demonstrations with a Kalman constraint","volume":"120","author":"palan","year":"2020","journal-title":"ser Proceedings of Machine Learning Research"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref9","article-title":"Closing the closed-loop distribution shift in safe imitation learning","author":"tu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970777"},{"key":"ref22","article-title":"An overview of gradient descent optimization algorithms","author":"ruder","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref21","article-title":"LMI properties and applications in systems, stability, and control theory","author":"caverly","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/978-1-4757-3216-0_8","article-title":"The mosek interior point optimizer for linear programming: an implementation of the homogeneous algorithm","author":"andersen","year":"2000","journal-title":"High Performance Optimization"},{"key":"ref23","first-page":"1","article-title":"CVXPY: A Python-embedded modeling language for convex optimization","volume":"17","author":"diamond","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2019.1683553"}],"event":{"name":"2021 American Control Conference (ACC)","location":"New Orleans, LA, USA","start":{"date-parts":[[2021,5,25]]},"end":{"date-parts":[[2021,5,28]]}},"container-title":["2021 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9482409\/9482614\/09483019.pdf?arnumber=9483019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T10:51:28Z","timestamp":1633517488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9483019\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,25]]},"references-count":25,"URL":"https:\/\/doi.org\/10.23919\/acc50511.2021.9483019","relation":{},"subject":[],"published":{"date-parts":[[2021,5,25]]}}}