{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T01:29:02Z","timestamp":1725586142680},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"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":[[2020,12,14]]},"DOI":"10.1109\/cdc42340.2020.9303788","type":"proceedings-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T02:27:32Z","timestamp":1610504852000},"page":"3604-3610","source":"Crossref","is-referenced-by-count":0,"title":["Expert Selection in High-Dimensional Markov Decision Processes"],"prefix":"10.1109","author":[{"given":"Vicenc","family":"Rubies-Royo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Mazumdar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roy","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claire","family":"Tomlin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S. Shankar","family":"Sastry","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"2312","article-title":"Improved algorithms for linear stochastic bandits","author":"abbasi-yadkori","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1561\/9781601986276"},{"journal-title":"Is Q-learning provably efficient","year":"2018","author":"jin","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"journal-title":"A multi-armed bandit approach for online expert selection in markov decision processes","year":"2017","author":"mazumdar","key":"ref14"},{"key":"ref15","first-page":"401","article-title":"Experts in a Markov decision process","author":"even-dar","year":"2004","journal-title":"Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems NIPS 2004 December 13-18 2004 Vancouver British Columbia Canada]"},{"key":"ref16","first-page":"89","article-title":"Near-optimal regret bounds for reinforcement learning","author":"auer","year":"2009","journal-title":"Advances in Neural Information Processing Systems 21"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921"},{"key":"ref18","article-title":"Meta-control for adaptive imagination-based optimization","author":"hamrick","year":"2017","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CoASE.2015.7294140"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-016-9556-4"},{"key":"ref3","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2049515"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2016.7498955"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"article-title":"Image denoising using interquartile range filter with local averaging","year":"2013","author":"jassim","key":"ref7"},{"key":"ref2","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"CoRR"},{"key":"ref1","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1952-09620-8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1561\/9781601986276"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2198613"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34106-9_19"},{"article-title":"OpenAI gym","year":"2016","author":"brockman","key":"ref23"}],"event":{"name":"2020 59th IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2020,12,14]]},"location":"Jeju, Korea (South)","end":{"date-parts":[[2020,12,18]]}},"container-title":["2020 59th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9303728\/9303729\/09303788.pdf?arnumber=9303788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T11:55:42Z","timestamp":1656330942000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9303788\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cdc42340.2020.9303788","relation":{},"subject":[],"published":{"date-parts":[[2020,12,14]]}}}