{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:53:51Z","timestamp":1773377631920,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"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":[[2020,6]]},"DOI":"10.1109\/isit44484.2020.9173931","type":"proceedings-article","created":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T17:28:01Z","timestamp":1598290081000},"page":"2777-2782","source":"Crossref","is-referenced-by-count":8,"title":["A Hoeffding Inequality for Finite State Markov Chains and its Applications to Markovian Bandits"],"prefix":"10.1109","author":[{"given":"Vrettos","family":"Moulos","sequence":"first","affiliation":[{"name":"University of California,Department of Electrical Engineering and Computer Sciences,Berkeley"}]}],"member":"263","reference":[{"key":"ref38","author":"moulos","year":"2020","journal-title":"Finite-time Analysis of Kullback-Leibler Upper Confidence Bounds for Optimal Adaptive Allocation with Multiple Plays and Markovian Rewards"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1561\/2200000068"},{"key":"ref32","author":"lattimore","year":"2019","journal-title":"Bandit Algorithms"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1561\/2200000024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2010.5707118"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1987.1104485"},{"key":"ref35","first-page":"623","article-title":"The sample complexity of exploration in the multi-armed bandit problem","volume":"5","author":"mannor","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-0125-7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1214\/aoap\/1177004826"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1017\/S0963548397003209"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1214\/aoap\/1028903453"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1214\/105051604000000170"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.spl.2014.01.013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1214\/EJP.v20-4039"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1214\/19-ECP219"},{"key":"ref17","author":"fan","year":"2018","journal-title":"Hoeffding's lemma for Markov Chains and its applications to statistical learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1190095.1190152"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-7152(01)00158-4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10500830"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1214\/07-AOP384"},{"key":"ref3","article-title":"Optimal Best Markovian Arm Identification with Fixed Confidence","author":"moulos","year":"2019","journal-title":"Annual Conference on Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1981.1056377"},{"key":"ref29","first-page":"1079","article-title":"Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems","volume":"7","author":"even-dar","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref5","article-title":"Reversible markov chains and random walks on graphs","author":"aldous","year":"2002"},{"key":"ref8","author":"moulos","year":"2019","journal-title":"Optimal Chernoff and Hoeffding Bounds for Finite State Markov Chains"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1214\/16-AAP1216"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/380752.380877"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1993.366819"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1063\/1.1699114"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1214\/10-AOS834"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/BF02249263"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1214\/aop\/1039639365"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1214\/aop\/1019160125"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s004400050154"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s00440-006-0026-1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1556\/SScMath.40.2003.1-2.8"}],"event":{"name":"2020 IEEE International Symposium on Information Theory (ISIT)","location":"Los Angeles, CA, USA","start":{"date-parts":[[2020,6,21]]},"end":{"date-parts":[[2020,6,26]]}},"container-title":["2020 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9166581\/9173928\/09173931.pdf?arnumber=9173931","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:34:41Z","timestamp":1773347681000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9173931\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/isit44484.2020.9173931","relation":{},"subject":[],"published":{"date-parts":[[2020,6]]}}}