{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T02:35:56Z","timestamp":1730342156980,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.23919\/acc60939.2024.10645022","type":"proceedings-article","created":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:56:19Z","timestamp":1725558979000},"page":"4170-4175","source":"Crossref","is-referenced-by-count":0,"title":["Near-Optimality of Finite-Memory Codes and Reinforcement Learning for Zero-Delay Coding of Markov Sources"],"prefix":"10.23919","author":[{"given":"Liam","family":"Cregg","sequence":"first","affiliation":[{"name":"Queen's University,Department of Mathematics and Statistics,Kingston,ON,Canada"}]},{"given":"Fady","family":"Alajaji","sequence":"additional","affiliation":[{"name":"Queen's University,Department of Mathematics and Statistics,Kingston,ON,Canada"}]},{"given":"Serdar","family":"Y\u00fcksel","sequence":"additional","affiliation":[{"name":"Queen's University,Department of Mathematics and Statistics,Kingston,ON,Canada"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TIT.1956.1056798"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1017\/CBO9780511921889"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1007\/978-1-4615-5719-7"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/JSAIT.2020.2987203"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/JSAC.2022.3221963"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/TIT.1983.1056760"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TIT.2006.880067"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/TIT.2017.2692215"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ISIT.2013.6620179"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/TIT.2009.2030462"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1137\/S0363012999365261"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/tit.2014.2346780"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1287\/moor.2016.0832"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/TAC.2019.2907172"},{"key":"ref15","first-page":"1","article-title":"Q-Iearning for MDPs with general spaces: Convergence and near optimality via quantization under weak continuity","volume":"24","author":"Kara","year":"2023","journal-title":"Journal of Machine Learning Research"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/cdc49753.2023.10383642"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1287\/moor.2022.1331"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/tit.2024.3416063"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1214\/105051604000000873"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1214\/20-ECP333"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/TAC.2023.3302208"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1137\/21m1417442"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1287\/moor.1070.0279"},{"issue":"11","key":"ref24","first-page":"1","article-title":"Near optimality of finite memory feedback policies in partially observed Markov decision processes","volume":"23","author":"Kara","year":"2022","journal-title":"Journal of Machine Learning Research"},{"year":"2024","author":"Cregg","journal-title":"Reinforcement learning for optimal zero-delay coding of Markov sources over noisy channels: Belief quantization vs. finite memory codes","key":"ref25"},{"year":"2023","author":"Yuksel","article-title":"Optimization and control of stochastic systems","key":"ref26"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1007\/0-387-28982-8"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/TIT.2021.3138769"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1007\/978-1-4612-0729-0"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1023\/A:1022676722315"},{"key":"ref31","article-title":"Q-Iearning for stochastic control under general information structures and non-Markovian environments","author":"Kara","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2024 American Control Conference (ACC)","start":{"date-parts":[[2024,7,10]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2024,7,12]]}},"container-title":["2024 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10644130\/10644150\/10645022.pdf?arnumber=10645022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T04:36:22Z","timestamp":1725770182000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645022\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":31,"URL":"https:\/\/doi.org\/10.23919\/acc60939.2024.10645022","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]}}}