{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T16:24:19Z","timestamp":1769531059821,"version":"3.49.0"},"reference-count":31,"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"}],"funder":[{"DOI":"10.13039\/100016311","name":"Arm","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,6]]},"DOI":"10.1109\/cdc51059.2022.9993316","type":"proceedings-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:26:56Z","timestamp":1673378816000},"page":"1460-1465","source":"Crossref","is-referenced-by-count":4,"title":["Stochastic Multi-Armed Bandits with Non-Stationary Rewards Generated by a Linear Dynamical System"],"prefix":"10.1109","author":[{"given":"Jonathan","family":"Gornet","sequence":"first","affiliation":[{"name":"Washington University in St. Louis,Department of Electrical and Systems Engineering,St. Louis,MO,USA,63130"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehdi","family":"Hosseinzadeh","sequence":"additional","affiliation":[{"name":"Washington State University,School of Mechanical and Materials Engineering,Pullman,WA,USA,99164"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bruno","family":"Sinopoli","sequence":"additional","affiliation":[{"name":"Washington University in St. Louis,Department of Electrical and Systems Engineering,St. Louis,MO,USA,63130"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/1427934"},{"issue":"2","key":"ref2","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1023\/A:1013689704352","article-title":"Finite-time analysis of the multiarmed bandit problem","volume":"47","author":"Auer","year":"2002","journal-title":"Machine learning"},{"issue":"1","key":"ref3","first-page":"6765","article-title":"Hyperband: A novel bandit-based approach to hyperparameter optimization","volume":"18","author":"Li","year":"2017","journal-title":"The Journal of Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13800-3_7"},{"key":"ref5","article-title":"Low-rank bandit methods for high-dimensional dynamic pricing","volume":"32","author":"Mueller","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","article-title":"Portfolio choices with orthogonal bandit learning","volume-title":"Twenty-fourth international joint conference on artificial intelligence","author":"Shen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.171377"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3465456.3467546"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2307\/1913811"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.1982.tb03584.x"},{"key":"ref12","first-page":"1079","article-title":"Learning to optimize under non-stationarity","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics","author":"Cheung"},{"issue":"1","key":"ref13","first-page":"1714","article-title":"Perishability of data: dynamic pricing under varying-coefficient models","volume":"18","author":"Javanmard","year":"2017","journal-title":"The Journal of Machine Learning Research"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/OJCSYS.2022.3178540"},{"key":"ref15","article-title":"Representation learning for stochastic sequential linear bandits","volume-title":"IEEE Conference on Decision and Control","author":"Qin"},{"key":"ref16","article-title":"On upper-confidence bound policies for non-stationary bandit problems","author":"Garivier","year":"2008"},{"key":"ref17","first-page":"237","article-title":"Change point detection and meta-bandits for online learning in dynamic environments","volume-title":"CAp 2007: 9\u00e8 Conf\u00e9rence francophone sur l\u2019apprentissage automatique","author":"Hartland"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11746"},{"key":"ref19","first-page":"418","article-title":"Nearly optimal adaptive procedure with change detection for piecewise-stationary bandit","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics","author":"Cao"},{"key":"ref20","first-page":"442","article-title":"Thompson sampling in switching environments with bayesian online change detection","author":"Mellor","year":"2013","journal-title":"Artificial intelligence and statistics."},{"key":"ref21","article-title":"Nonstationary stochastic multi-armed bandits: Ucb policies and minimax regret","author":"Wei","year":"2021"},{"key":"ref22","first-page":"199","article-title":"Stochastic multi-armed-bandit problem with non-stationary rewards","volume":"27","author":"Besbes","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Adaptive regret for control of time-varying dynamics","author":"Gradu","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029499"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref26","volume-title":"Econometric analysis of cross section and panel data.","author":"Wooldridge","year":"2010"},{"key":"ref27","article-title":"Improved algorithms for linear stochastic bandits","volume-title":"Advances in Neural Information Processing Systems","volume":"24","author":"Abbasi-yadkori","year":"2011"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199535255.001.0001"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1996.548512"},{"key":"ref30","volume-title":"Applied optimal estimation","author":"Gelb","year":"1974"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1978.1101743"}],"event":{"name":"2022 IEEE 61st Conference on Decision and Control (CDC)","location":"Cancun, Mexico","start":{"date-parts":[[2022,12,6]]},"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\/09993316.pdf?arnumber=9993316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T10:58:24Z","timestamp":1709377104000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9993316\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/cdc51059.2022.9993316","relation":{},"subject":[],"published":{"date-parts":[[2022,12,6]]}}}