{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T12:49:01Z","timestamp":1763642941748,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.23919\/acc45564.2020.9147749","type":"proceedings-article","created":{"date-parts":[[2020,7,27]],"date-time":"2020-07-27T22:02:33Z","timestamp":1595887353000},"page":"4798-4803","source":"Crossref","is-referenced-by-count":9,"title":["Random search for learning the linear quadratic regulator"],"prefix":"10.23919","author":[{"given":"Hesameddin","family":"Mohammadi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahdi","family":"Soltanolkotabi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mihailo R.","family":"Jovanovic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1561\/2200000048"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3290-0"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147571"},{"key":"ref11","article-title":"Convergence and sample complexity of gradient methods for the modelfree linear quadratic regulator problem","author":"mohammadi","year":"2019","journal-title":"IEEE Trans Automat Control"},{"key":"ref12","article-title":"On the linear convergence of random search for discrete-time lqr","author":"mohammadi","year":"2020","journal-title":"Syst Contr Lett"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1968.1098829"},{"journal-title":"The Riccati Equation","year":"2012","author":"bittanti","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/9.273368"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2002.806652"},{"article-title":"LQR through the lens of first order methods: Discrete-time case","year":"2019","author":"bu","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2160022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2257618"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"ref4","first-page":"3108","article-title":"Model-free linear quadratic control via reduction to expert prediction","volume":"89","author":"abbasi-yadkori","year":"2019","journal-title":"Mach Learn Res"},{"key":"ref27","first-page":"643","article-title":"Gradient methods for minimizing functionals","volume":"3","author":"polyak","year":"1963","journal-title":"Zh Vychisl Mat Mat Fiz"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-011-1005-3"},{"journal-title":"Optimal Control Linear Quadratic Methods","year":"1990","author":"anderson","key":"ref6"},{"key":"ref29","first-page":"385","article-title":"Online convex optimization in the bandit setting: gradient descent without a gradient","author":"flaxman","year":"2005","journal-title":"ACM-SIAM Symp Discrete Algorithms (SODA)"},{"key":"ref5","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","author":"fazel","year":"2018","journal-title":"Proc Int’l Conf Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029985"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1980.1102505"},{"article-title":"Playing Atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref2"},{"article-title":"Policy optimization for linear control with robustness guarantee: Implicit regularization and global convergence","year":"2018","author":"zhang","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejcon.2016.05.003"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2013.6669578"},{"key":"ref24","article-title":"Simple random search provides a competitive approach to reinforcement learning","author":"mania","year":"2018","journal-title":"Proc Neural Information Processing (NeurIPS)"},{"key":"ref23","article-title":"Proximal algorithms for large-scale statistical modeling and sensor\/actuator selection","author":"zare","year":"2019","journal-title":"IEEE Trans Automat Control"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1974.1100585"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"}],"event":{"name":"2020 American Control Conference (ACC)","start":{"date-parts":[[2020,7,1]]},"location":"Denver, CO, USA","end":{"date-parts":[[2020,7,3]]}},"container-title":["2020 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9140048\/9147203\/09147749.pdf?arnumber=9147749","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,31]],"date-time":"2020-08-31T21:46:44Z","timestamp":1598910404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9147749\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":31,"URL":"https:\/\/doi.org\/10.23919\/acc45564.2020.9147749","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}