{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:55:49Z","timestamp":1778604949820,"version":"3.51.4"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"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":[[2024,12,16]]},"DOI":"10.1109\/cdc56724.2024.10886003","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T18:43:32Z","timestamp":1740595412000},"page":"3309-3316","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement Learning Design for Quickest Change Detection"],"prefix":"10.1109","author":[{"given":"Austin","family":"Cooper","sequence":"first","affiliation":[{"name":"University of Florida,Department of Electrical and Computer Engineering,Gainesville FL,USA,32611"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sean","family":"Meyn","sequence":"additional","affiliation":[{"name":"University of Florida,Department of Electrical and Computer Engineering,Gainesville FL,USA,32611"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"The ODE method for asymptotic statistics in stochastic approximation and reinforcement learning","volume-title":"arXiv e-prints:2110.14427","author":"Borkar"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147481"},{"key":"ref3","first-page":"16879","article-title":"Zap Q-Learning with nonlinear function approximation","volume-title":"Proc. Conference on Neural Information Processing Systems (NeurIPS), and arXiv e-prints 1910.05405","volume":"33","author":"Chen"},{"key":"ref4","article-title":"Quickest change detection using mismatched CUSUM","author":"Cooper","year":"2024","journal-title":"arXiv 2409.07948"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton63246.2024.10735265"},{"key":"ref6","article-title":"Reinforcement learning design for quickest change detection-extended paper","author":"Cooper","year":"2024","journal-title":"arXiv preprint arXiv:2403.14109"},{"key":"ref7","article-title":"Hidden Markov models","volume-title":"Applications of Mathematics","volume":"29","author":"Elliott"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2283266"},{"key":"ref9","article-title":"Structural results for partially observed Markov decision processes","author":"Krishnamurthy","year":"2015","journal-title":"ArXiv e-prints"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2878570"},{"key":"ref11","first-page":"16","article-title":"Learning exercise policies for American options","volume-title":"Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics","volume":"5","author":"Li"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2022.3230583"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2022.3191957"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1017\/9781009051873"},{"key":"ref15","article-title":"Stability of Q-learning through design and optimism","author":"Meyn","year":"2023","journal-title":"arXiv 2307.02632"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176350164"},{"issue":"4","key":"ref17","first-page":"1729","article-title":"On optimality properties of the Shiryaev-Roberts procedure","volume":"19","author":"Pollak","year":"2009","journal-title":"Statistica Sinica"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1214\/09-AOS775"},{"key":"ref19","article-title":"Optimal stopping rules","volume":"8","author":"Shiryaev","year":"2007","journal-title":"Springer Science & Business Media"},{"issue":"1","key":"ref20","first-page":"483","article-title":"Approximate information state for approximate planning and reinforcement learning in partially observed systems","volume":"23","author":"Subramanian","year":"2022","journal-title":"The Journal of Machine Learning Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/9.793723"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2104670"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-411597-2.00006-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3072962"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT54713.2023.10206588"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096555"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2012.2206718"}],"event":{"name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","location":"Milan, Italy","start":{"date-parts":[[2024,12,16]]},"end":{"date-parts":[[2024,12,19]]}},"container-title":["2024 IEEE 63rd Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10885784\/10885785\/10886003.pdf?arnumber=10886003","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T07:08:27Z","timestamp":1740640107000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10886003\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/cdc56724.2024.10886003","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]}}}