{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T09:59:39Z","timestamp":1730195979499,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T00:00:00Z","timestamp":1695686400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T00:00:00Z","timestamp":1695686400000},"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":[[2023,9,26]]},"DOI":"10.1109\/allerton58177.2023.10313415","type":"proceedings-article","created":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T13:48:25Z","timestamp":1699969705000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Online Parameter Estimation in Partially Observed Markov Decision Processes"],"prefix":"10.1109","author":[{"given":"Sai Sumedh R.","family":"Hindupur","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Bombay,Department of Electrical Engineering,Mumbai,India"}]},{"given":"Vivek S.","family":"Borkar","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Bombay,Department of Electrical Engineering,Mumbai,India"}]}],"member":"263","reference":[{"key":"ref13","first-page":"67","article-title":"Model-based reinforcement learning with a generative model is minimax optimal","author":"agarwal","year":"2020","journal-title":"Conference on Learning Theory"},{"key":"ref12","article-title":"Reinforcement learning algorithm for partially observable Markov decision problems","volume":"7","author":"jaakkola","year":"1994","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"journal-title":"Stochastic Approximation A Dynamical Systems Viewpoint","year":"2022","author":"borkar","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref11","article-title":"Predictive representations of state","volume":"14","author":"littman","year":"2001","journal-title":"Advances in neural information processing systems"},{"article-title":"Planning in observable POMDPs in quasipolynomial time","year":"2022","author":"golowich","key":"ref10"},{"article-title":"POGE - Partially Observed Gridworld Environment (gridworld-gym)","year":"2022","author":"muskardin","key":"ref32"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1017\/9781009051873","author":"meyn","year":"2022","journal-title":"Reinforcement learning and control"},{"article-title":"Markovian foundations for quasi-stochastic approximation with applications to extremum seeking control","year":"2022","author":"lauand","key":"ref1"},{"key":"ref17","first-page":"183","article-title":"Reinforcement learning with perceptual aliasing: The perceptual distinctions approach","volume":"1992","author":"chrisman","year":"1992","journal-title":"AAAI"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_35"},{"key":"ref18","article-title":"Reinforcement learning with selective perception and hidden state","author":"mccallum","year":"1996","journal-title":"PhD thesis"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.681599"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1024691255"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781316471104"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2008.01.029"},{"article-title":"Reinforcement learning under partial observability guided by learned environment models","year":"2022","author":"muskardin","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(92)90141-C"},{"key":"ref21","first-page":"2117","article-title":"Deep variational reinforcement learning for POMDPs","author":"igl","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2009.00698.x"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-011-5014-9_12"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-28982-8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3564246.3585161"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1287\/moor.12.3.441"},{"key":"ref9","first-page":"5175","article-title":"When is partially observable reinforcement learning not scary?","author":"liu","year":"2022","journal-title":"Conference on Learning Theory"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-4087-0_2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/0471669784"},{"key":"ref5","first-page":"385","article-title":"Online convex optimization in the bandit setting: gradient descent without a gradient","author":"flaxman","year":"2005","journal-title":"Proceedings of the 16th Annual ACM-SIAM Symposium on Discrete Algorithms"}],"event":{"name":"2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","start":{"date-parts":[[2023,9,26]]},"location":"Monticello, IL, USA","end":{"date-parts":[[2023,9,29]]}},"container-title":["2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10313338\/10313355\/10313415.pdf?arnumber=10313415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T11:30:03Z","timestamp":1701257403000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10313415\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,26]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/allerton58177.2023.10313415","relation":{},"subject":[],"published":{"date-parts":[[2023,9,26]]}}}