{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:20:47Z","timestamp":1730204447980,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/cdc40024.2019.9029841","type":"proceedings-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T00:43:11Z","timestamp":1584060191000},"page":"2436-2441","source":"Crossref","is-referenced-by-count":1,"title":["Modelling uncertainty in reinforcement learning"],"prefix":"10.1109","author":[{"given":"Ryan","family":"Murray","sequence":"first","affiliation":[]},{"given":"Michele","family":"Palladino","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Learning and control using gaussian processes","author":"jain","year":"2017","journal-title":"Proc of the ACM\/IEEE International Conference on Cyber-Physical Systems"},{"key":"ref11","first-page":"6251","article-title":"Robust and efficient transfer learning with hidden parameter Markov decision processes","author":"killian","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28872-7_35"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/37.126844","article-title":"Reinforcement learning is direct adaptive optimal control","volume":"12","author":"sutton","year":"1992","journal-title":"IEEE Control Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4757-5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-8152-4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/0329038"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11228-016-0364-9"},{"key":"ref18","first-page":"1240","article-title":"Dual control theory. i-iv","volume":"21","author":"feldbaum","year":"1960","journal-title":"Avtomatika i Telemekhanika"},{"key":"ref19","first-page":"1","article-title":"Dual control for approximate Bayesian reinforcement learning","volume":"17","author":"klenske","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2009.01.016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007686309208"},{"key":"ref6","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1561\/2200000049"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143932"},{"key":"ref7","article-title":"Optimal learning: Computational procedures for Bayes-adaptive Markov decision processes","author":"duff","year":"2002","journal-title":"Ph D Dissertation"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2018.09.011"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6759992"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2514\/1.G000505"},{"key":"ref22","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref21","first-page":"3598","article-title":"Q-learning and Pontryagin’s minimum principle","author":"mehta","year":"2009","journal-title":"Decision and Control 2009 Held Jointly with the 2009 28th Chinese Control Conference CDC\/CCC 2009 Proceedings of the 48th IEEE Conference on"},{"key":"ref24","first-page":"2249","article-title":"An empirical evaluation of Thompson sampling","author":"chapelle","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref23","first-page":"4026","article-title":"Deep exploration via bootstrapped DQN","author":"osband","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.11.012"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.06.018"}],"event":{"name":"2019 IEEE 58th Conference on Decision and Control (CDC)","start":{"date-parts":[[2019,12,11]]},"location":"Nice, France","end":{"date-parts":[[2019,12,13]]}},"container-title":["2019 IEEE 58th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8977134\/9028853\/09029841.pdf?arnumber=9029841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T16:24:32Z","timestamp":1658247872000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9029841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/cdc40024.2019.9029841","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}