{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:21:23Z","timestamp":1740100883533,"version":"3.37.3"},"reference-count":33,"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"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6,8]]},"DOI":"10.23919\/acc53348.2022.9867458","type":"proceedings-article","created":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T20:24:10Z","timestamp":1662409450000},"page":"2136-2141","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Gradient Online Control"],"prefix":"10.23919","author":[{"given":"Deepan","family":"Muthirayan","sequence":"first","affiliation":[{"name":"University of California Irvine,Department of Electrical Engineering and Computer Sciences,Irvine,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianjun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Expedia Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pramod P.","family":"Khargonekar","sequence":"additional","affiliation":[{"name":"University of California Irvine,Department of Electrical Engineering and Computer Sciences,Irvine,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2021","author":"muthirayan","article-title":"Adaptive gradient online control","key":"ref33"},{"key":"ref32","first-page":"65","article-title":"Adaptive online gradient descent","author":"hazan","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref31","first-page":"784","article-title":"Online learning for adversaries with memory: price of past mistakes","author":"anava","year":"2015","journal-title":"Advances in neural information processing systems"},{"year":"2017","author":"berkenkamp","article-title":"Safe model-based reinforcement learning with stability guarantees","key":"ref30"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1002\/rnc.3144"},{"year":"2013","author":"\u00e5str\u00f6m","journal-title":"Adaptive Control","key":"ref11"},{"key":"ref12","first-page":"1","article-title":"Regret bounds for the adaptive control of linear quadratic systems","author":"abbasi-yadkori","year":"2011","journal-title":"Proceedings of the 24th Annual Conference on Learning Theory JMLR Workshop and Conference Proceedings"},{"key":"ref13","first-page":"4188","article-title":"Regret bounds for robust adaptive control of the linear quadratic regulator","author":"dean","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"1300","article-title":"Learning linear-quadratic regulators efficiently with only $\\sqrt T$ regret","author":"cohen","year":"2019","journal-title":"International Conference on Machine Learning"},{"year":"2019","author":"mania","article-title":"Certainty equivalent control of lqr is efficient","key":"ref15"},{"key":"ref16","first-page":"1029","article-title":"Online linear quadratic control","author":"cohen","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref17","first-page":"8937","article-title":"Naive exploration is optimal for online lqr","author":"simchowitz","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref18","first-page":"111","article-title":"Online control with adversarial disturbances","author":"agarwal","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref19","first-page":"10 175","article-title":"Logarithmic regret for online control","author":"agarwal","year":"2019","journal-title":"Advances in neural information processing systems"},{"year":"2019","author":"zhang","article-title":"Policy optimization for 2 control with guarantee: $\\mathcal{H}$ linear ${\\mathcal{H}_\\infty }$ robustness Implicit regularization and global convergence","key":"ref28"},{"year":"2011","author":"sastry","journal-title":"Adaptive Control Stability Convergence and Robustness","key":"ref4"},{"key":"ref27","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":"ref3","volume":"2","author":"skogestad","year":"2007","journal-title":"Multivariable Feedback Control Analysis and Design"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1016\/j.automatica.2014.10.015"},{"year":"2020","author":"molybog","article-title":"Global convergence of MAML for LQR","key":"ref29"},{"year":"2012","author":"ioannou","journal-title":"Robust Adaptive Control","key":"ref5"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1016\/j.ifacol.2017.08.512"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1016\/j.automatica.2017.01.030"},{"year":"2012","author":"\u00e5str\u00f6m","journal-title":"Introduction to Stochastic Control Theory","key":"ref2"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1002\/rnc.1720"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1137\/1.9781611974263"},{"key":"ref20","first-page":"408","article-title":"The nonstochastic control problem","author":"hazan","year":"2020","journal-title":"Algorithmic Learning Theory"},{"key":"ref22","first-page":"928","article-title":"Online convex programming and generalized infinitesimal gradient ascent","author":"zinkevich","year":"2003","journal-title":"International Conference on Machine Learning"},{"year":"2020","author":"simchowitz","article-title":"Improper learning for non-stochastic control","key":"ref21"},{"key":"ref24","article-title":"A stochastic view of optimal regret through minimax duality","author":"abernethy","year":"2009","journal-title":"Proceedings of the 22nd Annual Conference on Learning Theory"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1007\/11776420_37","article-title":"Logarithmic regret algorithms for online convex optimization","author":"hazan","year":"2006","journal-title":"Conference on Computational Learning Theory"},{"key":"ref26","first-page":"6137","article-title":"Online convex optimization for cumulative constraints","author":"yuan","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref25","first-page":"402","article-title":"Adaptive algorithms for online convex optimization with long-term constraints","author":"jenatton","year":"2016","journal-title":"International Conference on Machine Learning"}],"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\/09867458.pdf?arnumber=9867458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T20:24:19Z","timestamp":1665433459000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9867458\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,8]]},"references-count":33,"URL":"https:\/\/doi.org\/10.23919\/acc53348.2022.9867458","relation":{},"subject":[],"published":{"date-parts":[[2022,6,8]]}}}