{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T12:18:23Z","timestamp":1725711503811},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"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":[[2022,12,6]]},"DOI":"10.1109\/cdc51059.2022.9992683","type":"proceedings-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:26:56Z","timestamp":1673378816000},"page":"6658-6665","source":"Crossref","is-referenced-by-count":1,"title":["A modified Thompson sampling-based learning algorithm for unknown linear systems"],"prefix":"10.1109","author":[{"given":"Mukul","family":"Gagrani","sequence":"first","affiliation":[{"name":"Qualcomm AI Research,San Diego"}]},{"given":"Sagar","family":"Sudhakara","sequence":"additional","affiliation":[{"name":"University of Southern California,Department of Electrical and Computer Engineering,Los Angeles,CA,USA"}]},{"given":"Aditya","family":"Mahajan","sequence":"additional","affiliation":[{"name":"McGill University,Department of Electrical and Computer Engineering,Montreal,QC,Canada"}]},{"given":"Ashutosh","family":"Nayyar","sequence":"additional","affiliation":[{"name":"University of Southern California,Department of Electrical and Computer Engineering,Los Angeles,CA,USA"}]},{"given":"Yi","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Preferred Networks America,Burlingame,CA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2950156"},{"volume-title":"Adaptive Control.","year":"1994","author":"Astrom","key":"ref2"},{"volume-title":"Linear Stochastic Systems.","year":"1988","author":"Caines","key":"ref3"},{"key":"ref4","first-page":"295","article-title":"Reinforcement learning applied to linear quadratic regulation","author":"Bradtke","year":"1993","journal-title":"Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1994.735224"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997317499"},{"key":"ref7","first-page":"1","article-title":"Regret bounds for the adaptive control of linear quadratic systems","volume-title":"Annual Conference on Learning Theory","author":"Abbasi-Yadkori"},{"key":"ref8","first-page":"1300","article-title":"Learning linear-quadratic regulators efficiently with only $\\sqrt T $ regret","volume-title":"International Conference on Machine Learning","author":"Cohen"},{"key":"ref9","first-page":"23","article-title":"Efficient optimistic exploration in linear-quadratic regulators via lagrangian relaxation","volume-title":"International Conference on Machine Learning","author":"Abeille"},{"key":"ref10","first-page":"4192","article-title":"Regret bounds for robust adaptive control of the linear quadratic regulator","author":"Dean","year":"2018","journal-title":"Neural Information Processing Systems"},{"journal-title":"Certainty equivalent control of LQR is efficient","year":"2019","author":"Mania","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.108950"},{"key":"ref13","first-page":"8937","article-title":"Naive exploration is optimal for online lqr","volume-title":"International Conference on Machine Learning","author":"Simchowitz"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.108982"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2017.8262873"},{"key":"ref16","first-page":"1","article-title":"Improved regret bounds for thompson sampling in linear quadratic control problems","volume-title":"International Conference on Machine Learning","author":"Abeille"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683030"},{"volume-title":"Introduction to stochastic control theory.","year":"1970","author":"Astrom","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1977.1101497"},{"key":"ref20","article-title":"Stochastic orderings and the growth of expected extremes","volume-title":"tech. rep., Tech. Report 90-9","author":"Downey","year":"1990"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1214\/lnms\/1215461943"},{"journal-title":"Bayesian optimal control of smoothly parameterized systems: The lazy posterior sampling algorithm","year":"2014","author":"Abbasi-Yadkori","key":"ref22"}],"event":{"name":"2022 IEEE 61st Conference on Decision and Control (CDC)","start":{"date-parts":[[2022,12,6]]},"location":"Cancun, Mexico","end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 IEEE 61st Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9992315\/9992317\/09992683.pdf?arnumber=9992683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T11:51:41Z","timestamp":1706788301000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9992683\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/cdc51059.2022.9992683","relation":{},"subject":[],"published":{"date-parts":[[2022,12,6]]}}}