{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T13:00:22Z","timestamp":1763643622248,"version":"3.28.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6,8]]},"DOI":"10.23919\/acc53348.2022.9867674","type":"proceedings-article","created":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T20:24:10Z","timestamp":1662409450000},"page":"3335-3341","source":"Crossref","is-referenced-by-count":3,"title":["Model-Free \u03bc Synthesis via Adversarial Reinforcement Learning"],"prefix":"10.23919","author":[{"given":"Darioush","family":"Keivan","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign,Coordinated Science Laboratory (CSL),Department of Mechanical Science & Engineering"}]},{"given":"Aaron","family":"Havens","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign,Coordinated Science Laboratory (CSL),Department of Electrical and Computer Engineering"}]},{"given":"Peter","family":"Seiler","sequence":"additional","affiliation":[{"name":"University of Michigan,Department of Electrical Engineering and Computer Science"}]},{"given":"Geir","family":"Dullerud","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign,Coordinated Science Laboratory (CSL),Department of Mechanical Science & Engineering"}]},{"given":"Bin","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign,Coordinated Science Laboratory (CSL),Department of Electrical and Computer Engineering"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1535","article-title":"Gain estimation of linear dynamical systems using Thompson sampling","volume":"89","author":"m\u00fcller","year":"2019","journal-title":"International Conference on Artificial Intelligence and Statistics (AISTATS)"},{"key":"ref38","first-page":"1867","article-title":"On the approximation of Toeplitz operators for nonparametric -norm estimation","author":"tu","year":"2018","journal-title":"American Control Conference"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(88)90055-2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1080\/00207178908953406"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0008864"},{"journal-title":"H? Optimal Control and Related Minimax Design Problems A Dynamic Game Approach","year":"1995","author":"ba?ar","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2014.2303047"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.05.012"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.08.025"},{"article-title":"Model-free ? synthesis via adversarial reinforcement learning","year":"2021","author":"keivan","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147571"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814311"},{"key":"ref11","first-page":"947","article-title":"Policy learning of MDPs with mixed continuous\/discrete variables: A case study on model-free control of Markovian jump systems","author":"jansch-porto","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref12","article-title":"Learning optimal controllers for linear systems with multiplicative noise via policy gradient","author":"gravell","year":"2020","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3006256"},{"key":"ref14","article-title":"Convergence and sample complexity of gradient methods for the model-free linear quadratic regulator problem","author":"mohammadi","year":"2021","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029916"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref17","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref18","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":"ref19","article-title":"Derivative-free policy optimization for linear risk-sensitive and robust control design: Implicit regularization and sample complexity","author":"zhang","year":"2021","journal-title":"Thirty-Fifth Conference on Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(93)90175-S"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref4"},{"key":"ref27","volume":"40","author":"zhou","year":"1996","journal-title":"Robust and Optimal Control"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"schulman","key":"ref3"},{"key":"ref6","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume":"80","author":"fazel","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1991.261577"},{"key":"ref5","first-page":"6550","article-title":"Towards generalization and simplicity in continuous control","author":"rajeswaran","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"On the global convergence of actor-critic: A case for linear quadratic regulator with ergodic cost","year":"2019","author":"yang","key":"ref8"},{"key":"ref7","first-page":"8514","article-title":"Finite-time analysis of approximate policy iteration for the linear quadratic regulator","volume":"32","author":"krauth","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref9","first-page":"287","article-title":"Learning the globally optimal distributed LQ regulator","author":"furieri","year":"2020","journal-title":"Learning for Dynamics and Control"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/20M1347942"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2014.6859514"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1115\/1.2899083"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304202"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3047577"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2013.6580892"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3004506"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/0024-3795(93)90465-Z"},{"journal-title":"A Course in Robust Control Theory A Convex Approach","year":"2013","author":"dullerud","key":"ref26"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970777"},{"article-title":"Combining prior knowledge and data for robust controller design","year":"2020","author":"berberich","key":"ref25"}],"event":{"name":"2022 American Control Conference (ACC)","start":{"date-parts":[[2022,6,8]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2022,6,10]]}},"container-title":["2022 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9866948\/9867142\/09867674.pdf?arnumber=9867674","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T20:38:07Z","timestamp":1664829487000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9867674\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,8]]},"references-count":44,"URL":"https:\/\/doi.org\/10.23919\/acc53348.2022.9867674","relation":{},"subject":[],"published":{"date-parts":[[2022,6,8]]}}}