{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:04:24Z","timestamp":1740099864837,"version":"3.37.3"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,14]]},"DOI":"10.1109\/cdc42340.2020.9304458","type":"proceedings-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T07:27:32Z","timestamp":1610522852000},"page":"3731-3738","source":"Crossref","is-referenced-by-count":1,"title":["Safety-Critical Online Control with Adversarial Disturbances"],"prefix":"10.1109","author":[{"given":"Bhaskar","family":"Ramasubramanian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baicen","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linda","family":"Bushnell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Radha","family":"Poovendran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"3036","article-title":"The gap between model-based and model-free methods on the linear quadratic regulator: An asymptotic viewpoint","author":"tu","year":"2019","journal-title":"Conference on Learning Theory"},{"key":"ref38","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","author":"fazel","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"journal-title":"The handbook of model predictive control","year":"2018","author":"rakovi?","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0109870"},{"key":"ref30","volume":"40","author":"zhou","year":"1996","journal-title":"Robust and Optimal Control"},{"key":"ref37","first-page":"435","article-title":"Sample complexity of Kalman filtering for unknown systems","author":"tsiamis","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-019-09426-y"},{"article-title":"Online learning of the Kalman filter with logarithmic regret","year":"2020","author":"tsiamis","key":"ref35"},{"article-title":"An iterative Ric-cati algorithm for online linear quadratic control","year":"2019","author":"akbari","key":"ref34"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-1239(199610)6:8<789::AID-RNC191>3.0.CO;2-J"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(93)90104-E"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(00)00022-4"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5235-x"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref1"},{"key":"ref20","article-title":"Logarithmic regret for adversarial online control","author":"foster","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0098-1354(93)80018-I"},{"key":"ref21","first-page":"1029","article-title":"Online linear quadratic control","author":"cohen","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-22673-5","author":"wonham","year":"1974","journal-title":"Linear Multivariable Control a Geometric Approach"},{"key":"ref23","article-title":"Discrete-time mixed H2\/H ? nonlinear filtering","author":"aliyu","year":"2008","journal-title":"Proc American Control Conference"},{"journal-title":"Controlled and Conditioned Invariants in Linear System Theory","year":"1992","author":"basile","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1981.1102551"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.ece.2019.09.002"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/MCS.2012.2214134","article-title":"Reinforcement learning and feedback control: Using natural decision methods to design optimal adaptive controllers","volume":"32","author":"lewis","year":"2012","journal-title":"IEEE Control Systems Magazine"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2011.2165689"},{"article-title":"Learning robust control for linear quadratic systems with multiplicative noise via policy gradient","year":"2019","author":"gravell","key":"ref40"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.tej.2017.02.006"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(91)90011-3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/014233129101300507"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/0005-1098(93)90174-R","article-title":"Mixed H2\/H? control for discrete-time systems via convex optimization","volume":"29","author":"kaminer","year":"1993","journal-title":"Automatica"},{"key":"ref16","article-title":"Logarithmic regret for online control","author":"agarwal","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"111","article-title":"Online control with adversarial disturbances","author":"agarwal","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref18","first-page":"408","article-title":"The nonstochastic control problem","author":"hazan","year":"2020","journal-title":"Algorithmic Learning Theory"},{"key":"ref19","article-title":"Improper learning for non-stochastic control","author":"simchowitz","year":"2020","journal-title":"Conference on Learning Theory"},{"key":"ref4","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2904897"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2881359"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.029"},{"key":"ref49","article-title":"Model predictive control of a continuous, nonlinear, two-phase reactor","volume":"3","author":"ricker","year":"1993","journal-title":"Journal of Process Control"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.01.003"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TEST.2016.7805855"},{"journal-title":"Linear System Theory","year":"1996","author":"rugh","key":"ref45"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2019.101660"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2830338"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814865"},{"key":"ref41","first-page":"179","article-title":"Policy optimization for H2 linear control with H? robustness guarantee: Implicit regularization and global convergence","author":"zhang","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1971.1099755"},{"journal-title":"Linear Robust Control","year":"2012","author":"green","key":"ref43"}],"event":{"name":"2020 59th IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2020,12,14]]},"location":"Jeju, Korea (South)","end":{"date-parts":[[2020,12,18]]}},"container-title":["2020 59th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9303728\/9303729\/09304458.pdf?arnumber=9304458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T16:03:50Z","timestamp":1656345830000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9304458\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,14]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/cdc42340.2020.9304458","relation":{},"subject":[],"published":{"date-parts":[[2020,12,14]]}}}