{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T01:52:00Z","timestamp":1787363520156,"version":"build-2736575974"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T00:00:00Z","timestamp":1720310400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T00:00:00Z","timestamp":1720310400000},"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":[[2024,7,7]]},"DOI":"10.1109\/isit57864.2024.10619668","type":"proceedings-article","created":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T13:25:01Z","timestamp":1724073901000},"page":"232-237","source":"Crossref","is-referenced-by-count":2,"title":["Reinforcement Learning for Near-Optimal Design of Zero-Delay Codes for Markov Sources"],"prefix":"10.1109","author":[{"given":"Liam","family":"Cregg","sequence":"first","affiliation":[{"name":"Queen&#x0027;s University,Department of Mathematics and Statistics,Kingston,ON,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tam\u00e1s","family":"Linder","sequence":"additional","affiliation":[{"name":"Queen&#x0027;s University,Department of Mathematics and Statistics,Kingston,ON,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Serdar","family":"Y\u00fcksel","sequence":"additional","affiliation":[{"name":"Queen&#x0027;s University,Department of Mathematics and Statistics,Kingston,ON,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-7085-4"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1979.tb02263.x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(83)90012-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.880067"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2030462"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2212874"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2014.2346780"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2692215"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2008.2008147"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2021.3138769"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref13","volume-title":"Learning via stochastic approximation in function space","author":"Baker","year":"1997"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016070"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01551-9"},{"key":"ref16","volume-title":"Neuro-Dynamic Programming","author":"Bertsekas","year":"1996"},{"issue":"199","key":"ref17","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"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1331"},{"key":"ref19","article-title":"Near-optimality of finite-memory codes and reinforcement learning for zero-delay coding of Markov sources","volume-title":"Proc. 2024 American Control Conf","author":"Cregg"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383642"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2010.2098070"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2500658"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2855046"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2022.3232060"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2004.834430"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2601148"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2184669"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3099444"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(89)90024-1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2941444"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2912256"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933969"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3626-0"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2024.3416063"},{"key":"ref35","first-page":"333","article-title":"An algorithm for quantization of dicrete probability distri-butions","author":"Reznik","year":"2011","journal-title":"DCC 2011"},{"key":"ref36","first-page":"1","article-title":"Learning rates for Q-Iearning","volume":"5","author":"Even-Dar","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3302208"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1214\/08-AOP448"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.4064\/am-22-1-25-38"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2907172"}],"event":{"name":"2024 IEEE International Symposium on Information Theory (ISIT)","location":"Athens, Greece","start":{"date-parts":[[2024,7,7]]},"end":{"date-parts":[[2024,7,12]]}},"container-title":["2024 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10619013\/10619074\/10619668.pdf?arnumber=10619668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:28:44Z","timestamp":1773347324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10619668\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,7]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/isit57864.2024.10619668","relation":{},"subject":[],"published":{"date-parts":[[2024,7,7]]}}}