{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:33:30Z","timestamp":1783701210121,"version":"3.55.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"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","award":["W911NF-17-1-0058"],"award-info":[{"award-number":["W911NF-17-1-0058"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA2386-19-1-4073"],"award-info":[{"award-number":["FA2386-19-1-4073"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1109\/tac.2020.3037046","type":"journal-article","created":{"date-parts":[[2020,11,10]],"date-time":"2020-11-10T21:08:55Z","timestamp":1605042535000},"page":"5283-5298","source":"Crossref","is-referenced-by-count":71,"title":["Learning Optimal Controllers for Linear Systems With Multiplicative Noise via Policy Gradient"],"prefix":"10.1109","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3302-0166","authenticated-orcid":false,"given":"Benjamin","family":"Gravell","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peyman Mohajerin","family":"Esfahani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0113-8912","authenticated-orcid":false,"given":"Tyler","family":"Summers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2019.2914090"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2018.2868183"},{"key":"ref33","article-title":"An input-output approach to structured stochastic uncertainty","author":"bamieh","year":"2018","journal-title":"arXiv 1806 07473"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012996301336"},{"key":"ref31","first-page":"1811","article-title":"Estimation and control of systems with multiplicative noise via linear matrix inequalities","author":"li","year":"0","journal-title":"Proc Amer Control Conf"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970777"},{"key":"ref37","first-page":"2882","article-title":"Convergence guarantees of policy optimization methods for Markovian jump linear systems","author":"jansch-porto","year":"0","journal-title":"Proc IEEE Amer Control Conf"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029946"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/09075041X"},{"key":"ref34","article-title":"Robust control design for linear systems via multiplicative noise","author":"gravell","year":"0","journal-title":"Proc 18th IFAC World Congress"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4497"},{"key":"ref27","author":"lumley","year":"2007","journal-title":"Stochastic Tools in Turbulence"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(94)00045-W"},{"key":"ref2","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1977.1101633"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref21","volume":"1","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2006.887288"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2006.887291"},{"key":"ref26","first-page":"1","article-title":"Foundations and challenges of low-inertia systems","author":"milano","year":"0","journal-title":"Proc Power Syst Comput Conf"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2006.878356"},{"key":"ref50","first-page":"795","article-title":"Linear convergence of gradient and proximal-gradient methods under the Polyak-Lojasiewicz condition","author":"karimi","year":"0","journal-title":"Machine Learning and Knowledge Discovery in Databases"},{"key":"ref51","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-011-9099-z"},{"key":"ref55","first-page":"385","article-title":"Online convex optimization in the bandit setting: Gradient descent without a gradient","author":"flaxman","year":"0","journal-title":"Proc 16th Annu ACM-SIAM Symp Discrete Algorithms"},{"key":"ref54","article-title":"LQR through the lens of first order methods: Discrete-time case","author":"bu","year":"2019","journal-title":"arXiv 1907 08921"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1971.1099755"},{"key":"ref10","article-title":"Least-squares temporal difference learning for the linear quadratic regulator","author":"tu","year":"2017","journal-title":"arXiv 1712 08642"},{"key":"ref11","first-page":"1","article-title":"Improved regret bounds for thompson sampling in linear quadratic control problems","author":"abeille","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2016.04.006"},{"key":"ref12","first-page":"9561","article-title":"Learning convex bounds for linear quadratic control policy synthesis","author":"umenberger","year":"0","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref13","article-title":"Certainty equivalent control of LQR is efficient","author":"mania","year":"2019","journal-title":"arXiv 1902 07826"},{"key":"ref14","article-title":"Recovering robustness in model-free reinforcement learning","author":"venkataraman","year":"2018","journal-title":"arXiv 1810 09337"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/0305028"},{"key":"ref16","volume":"297","author":"damm","year":"2004","journal-title":"Rational Matrix Equations in Stochastic Control"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(76)90029-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1977.1101526"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1987.1104517"},{"key":"ref4","article-title":"On the sample complexity of the linear quadratic regulator","author":"dean","year":"2017","journal-title":"arXiv 1710 01688"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1994.735224"},{"key":"ref5","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume":"80","author":"fazel","year":"0","journal-title":"Proc 35th Int Conf Mach Learning"},{"key":"ref8","first-page":"1","article-title":"Regret bounds for the adaptive control of linear quadratic systems","author":"abbasi-yadkori","year":"0","journal-title":"Proc 24th Annu Conf Learn Theory"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/267460.267481"},{"key":"ref49","article-title":"Learning robust control for LQR systems with multiplicative noise via policy gradient","author":"gravell","year":"2019","journal-title":"arXiv 1905 13547"},{"key":"ref9","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 Syst Mag"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.na.2006.07.003"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/S0898-1221(03)00073-7"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(63)90382-3"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2514\/3.20031"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029185"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(69)90060-0"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147756"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/9586335\/09254115.pdf?arnumber=9254115","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:52:37Z","timestamp":1652194357000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9254115\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11]]},"references-count":56,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tac.2020.3037046","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11]]}}}