{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T10:40:34Z","timestamp":1770460834384,"version":"3.49.0"},"reference-count":32,"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\/cdc51059.2022.9992857","type":"proceedings-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:26:56Z","timestamp":1673378816000},"page":"2313-2318","source":"Crossref","is-referenced-by-count":5,"title":["Deterministic Sequencing of Exploration and Exploitation for Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Piyush","family":"Gupta","sequence":"first","affiliation":[{"name":"Michigan State University,Department of Electrical and Computer Engineering,East Lansing,Michigan,USA,48824"}]},{"given":"Vaibhav","family":"Srivastava","sequence":"additional","affiliation":[{"name":"Michigan State University,Department of Electrical and Computer Engineering,East Lansing,Michigan,USA,48824"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CAC.2017.8244061"},{"key":"ref2","article-title":"Towards safer self-driving through great PAIN (Physically Adversarial Intelligent Networks)","author":"Gupta","year":"2020"},{"key":"ref3","article-title":"Some recent applications of reinforcement learning","volume-title":"Proceedings of the Eighteenth Yale Workshop on Adaptive and Learning Systems","author":"Barto"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2016.02.008"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2023.111388"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814842"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref8","article-title":"Robust Decision-Making with Model Uncertainty in Aerospace Systems","volume-title":"Ph.D. dissertation","author":"Bertuccelli","year":"2008"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/ECC54610.2021.9654941"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1120.0566"},{"key":"ref11","article-title":"Robust Markov Decision Processes with Uncertain Transition Matrices","volume-title":"Ph.D. dissertation","author":"Nilim","year":"2004"},{"key":"ref12","article-title":"Learning from Delayed Rewards","volume-title":"Ph.D. dissertation","author":"Watkins","year":"1989"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2007.08.009"},{"key":"ref15","article-title":"On the Sample Complexity of Reinforcement Learning","volume-title":"Ph.D. dissertation","author":"Kakade","year":"2003"},{"issue":"51","key":"ref16","first-page":"1563","article-title":"Near-optimal regret bounds for reinforcement learning","volume":"11","author":"Jaksch","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2263494"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2230215"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431265"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2016.2635380"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560851"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2012.2205478"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1017\/9781108627771"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1040.0129"},{"key":"ref26","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming.","author":"Puterman","year":"2014"},{"key":"ref27","volume-title":"Inequalities for the L1 deviation of the empirical distribution","author":"Weissman","year":"2003"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426504"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992857"},{"key":"ref30","article-title":"Chernoff-Hoeffding bounds for Markov chains: Generalized and simplified","author":"Chung","year":"2012"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-4149(97)00037-9"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2008.01.003"}],"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\/09992857.pdf?arnumber=9992857","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T12:08:11Z","timestamp":1706789291000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9992857\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/cdc51059.2022.9992857","relation":{},"subject":[],"published":{"date-parts":[[2022,12,6]]}}}