{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:48:52Z","timestamp":1768340932528,"version":"3.49.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,10]]},"DOI":"10.1109\/allerton.2017.8262873","type":"proceedings-article","created":{"date-parts":[[2018,1,18]],"date-time":"2018-01-18T18:03:47Z","timestamp":1516298627000},"page":"1198-1205","source":"Crossref","is-referenced-by-count":18,"title":["Control of unknown linear systems with Thompson sampling"],"prefix":"10.1109","author":[{"given":"Yi","family":"Ouyang","sequence":"first","affiliation":[]},{"given":"Mukul","family":"Gagrani","sequence":"additional","affiliation":[]},{"given":"Rahul","family":"Jain","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"355","article-title":"Stochastic linear optimization under bandit feedback","author":"dani","year":"2008","journal-title":"COLT"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/asmb.874"},{"key":"ref12","article-title":"An empirical evaluation of thompson sampling","author":"chapelle","year":"2011","journal-title":"NIPS"},{"key":"ref13","first-page":"39","article-title":"Analysis of thompson sampling for the multi-armed bandit problem","author":"agrawal","year":"2012","journal-title":"Conference on Learning Theory"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34106-9_18"},{"key":"ref15","first-page":"127","article-title":"Thompson sampling for contextual bandits with linear payoffs","author":"agrawal","year":"2013","journal-title":"ICML (3)"},{"key":"ref16","article-title":"(More) efficient reinforcement learning via posterior sampling","author":"osband","year":"2013","journal-title":"NIPS"},{"key":"ref17","article-title":"Bayesian optimal control of smoothly parameterized systems","author":"abbasi-yadkori","year":"2015","journal-title":"UAI"},{"key":"ref18","article-title":"Thompson sampling for learning parameterized markov decision processes","author":"gopalan","year":"2015","journal-title":"COLT"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2307\/2332286"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/00207178608933679"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1985.1103963"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997317499"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/9.481609"},{"key":"ref8","first-page":"2636","article-title":"Efficient reinforcement learning for high dimensional linear quadratic systems","author":"ibrahimi","year":"2012","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref7","first-page":"1","article-title":"Regret bounds for the adaptive control of linear quadratic systems","author":"abbasi-yadkori","year":"2011","journal-title":"Proc 24th Annu Conf Learn Theory"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974263"},{"key":"ref1","author":"goodwin","year":"2014","journal-title":"Adaptive Filtering Prediction and Control"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"ref20","author":"abeille","year":"2017","journal-title":"Thompson sampling for linear-quadratic control problems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1977.1101497"},{"key":"ref21","author":"osband","year":"2016","journal-title":"Posterior sampling for reinforcement learning without episodes"},{"key":"ref24","author":"dasarathy","year":"0","journal-title":"A simple probability trick for bounding the expected maximum of n random variables"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2014.0650"}],"event":{"name":"2017 55th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","location":"Monticello, IL, USA","start":{"date-parts":[[2017,10,3]]},"end":{"date-parts":[[2017,10,6]]}},"container-title":["2017 55th Annual Allerton Conference on Communication, Control, and Computing (Allerton)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8253908\/8262705\/08262873.pdf?arnumber=8262873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,2,28]],"date-time":"2018-02-28T16:35:54Z","timestamp":1519835754000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8262873\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/allerton.2017.8262873","relation":{},"subject":[],"published":{"date-parts":[[2017,10]]}}}