{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:25:55Z","timestamp":1767338755768,"version":"3.37.3"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"ISF","award":["1644\/18"],"award-info":[{"award-number":["1644\/18"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tsp.2021.3054344","type":"journal-article","created":{"date-parts":[[2021,1,25]],"date-time":"2021-01-25T21:58:09Z","timestamp":1611611889000},"page":"1108-1123","source":"Crossref","is-referenced-by-count":5,"title":["The Restless Hidden Markov Bandit With Linear Rewards and Side Information"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2087-1183","authenticated-orcid":false,"given":"Michal","family":"Yemini","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2265-7463","authenticated-orcid":false,"given":"Amir","family":"Leshem","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anelia","family":"Somekh-Baruch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2020.1051"},{"journal-title":"Markov Chains and Mixing Times","year":"2009","author":"levin","key":"ref38"},{"key":"ref33","first-page":"1763","article-title":"Minimal exploration in structured stochastic bandits","author":"combes","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2019.2935256"},{"key":"ref31","first-page":"521","article-title":"Unimodal bandits: Regret lower bounds and optimal algorithms","author":"combes","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","first-page":"1602","article-title":"Multi-armed bandits on implicit metric spaces","author":"slivkins","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1214\/aoap\/1028903453","article-title":"Chernoff-type bound for finite Markov chains","volume":"8","author":"lezaud","year":"1998","journal-title":"Ann Appl Probab"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1214\/07-AOP384"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619134"},{"key":"ref34","first-page":"8874","article-title":"Exploration in structured reinforcement learning","author":"ok","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11316"},{"key":"ref11","first-page":"397","article-title":"Using confidence bounds for exploitation-exploration trade-offs","volume":"3","author":"auer","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref12","first-page":"355","article-title":"Stochastic linear optimization under bandit feedback","author":"dani","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1100.0446"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472588"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"ref16","first-page":"208","article-title":"Contextual bandits with linear payoff functions","author":"chu","year":"0","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"article-title":"A survey on contextual multi-armed bandits","year":"2015","author":"zhou","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton.2011.6120273"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2014.09.026"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1374376.1374475"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2198613"},{"key":"ref27","first-page":"1926","article-title":"The continuum-armed bandit problem","volume":"33","author":"r","year":"1995","journal-title":"Soc Ind Appl Math J Control Optim"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2058091"},{"key":"ref6","first-page":"35","article-title":"REGAL: A regularization based algorithm for reinforcement learning in weakly communicating MDPs","author":"bartlett","year":"0","journal-title":"Proc 25th Conf Uncertainty Artif Intell"},{"key":"ref29","first-page":"975","article-title":"Lipschitz bandits: Regret lower bound and optimal algorithms","author":"magureanu","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref5","first-page":"49","article-title":"Logarithmic online regret bounds for undiscounted reinforcement learning","author":"auer","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","first-page":"4890","article-title":"Exploration bonus for regret minimization in discrete and continuous average reward MDPs","volume":"32","author":"qian","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","first-page":"1563","article-title":"Near-optimal regret bounds for reinforcement learning","volume":"11","author":"jaksch","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1987.1104485"},{"key":"ref9","first-page":"2998","article-title":"Near optimal exploration-exploitation in non-communicating Markov decision processes","author":"fruit","year":"0","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst Ser"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21236\/ADA575936"},{"key":"ref20","first-page":"335","article-title":"A hidden Markov restless multi-armed bandit model for playout recommendation systems","author":"meshram","year":"0","journal-title":"Proc Int Conf Commun Syst Netw"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2912492"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/78.969499"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1080.0371"},{"key":"ref26","article-title":"Nonparametric Gaussian mixture models for the multi-armed contextual bandit","volume":"abs 1808 2932","author":"urteaga","year":"2018","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7799449"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/78\/9307529\/09335534.pdf?arnumber=9335534","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:32Z","timestamp":1652194232000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9335534\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/tsp.2021.3054344","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"type":"print","value":"1053-587X"},{"type":"electronic","value":"1941-0476"}],"subject":[],"published":{"date-parts":[[2021]]}}}