{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T05:42:58Z","timestamp":1770270178445,"version":"3.49.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,12]],"date-time":"2024-05-12T00:00:00Z","timestamp":1715472000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,12]],"date-time":"2024-05-12T00:00:00Z","timestamp":1715472000000},"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":[[2024,5,12]]},"DOI":"10.1109\/icps59941.2024.10640031","type":"proceedings-article","created":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T17:24:30Z","timestamp":1724693070000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Deep reinforcement learning-based model predictive control of uncertain linear systems"],"prefix":"10.1109","author":[{"given":"Pengcheng","family":"Hu","sequence":"first","affiliation":[{"name":"University of Victoria,Department of Mechanical Engineering,Victoria,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyuan","family":"Cao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunwu","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Victoria,Department of Mechanical Engineering,Victoria,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Shi","sequence":"additional","affiliation":[{"name":"University of Victoria,Department of Mechanical Engineering,Victoria,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref2","article-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref3","first-page":"1167","article-title":"Classes of multiagent q-learning dynamics with epsilon-greedy exploration","volume-title":"Proceedings of 2010 International Conference on Machine Learning","author":"Wunder"},{"key":"ref4","first-page":"2753","article-title":"#Exploration: A study of count-based exploration for deep reinforcement learning","volume-title":"Proceedings of 2017 Advances in Neural Information Processing Systems","author":"Tang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref6","article-title":"On-line Q-learning Using Connectionist Systems","volume":"37","author":"Rummery","year":"1994"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref9","first-page":"1861","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 2018 International Conference on Machine Learning","author":"Haarnoja"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref11","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint arXiv:1312.5602"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48290-3"},{"key":"ref13","article-title":"Model Predictive Control: Classical, Robust and Stochastic, ser. Advanced Textbooks in Control and Signal Processing","author":"Kouvaritakis","year":"2015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2012.2198478"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2021.10.008"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19354-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2779442"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.02.003"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3024161"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref21","article-title":"Model predictive path integral control using covariance variable importance sampling","author":"Williams","year":"2015","journal-title":"arXiv preprint arXiv:1509.01149"},{"key":"ref22","first-page":"01","article-title":"SARSA-based model predictive contro with improved performance and computational complexity","volume-title":"Proceedings of 2022 IEEE International Conference on Industrial CyberPhysical Systems","author":"Lu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CoDIT58514.2023.10284335"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2913768"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.08.019"},{"key":"ref26","article-title":"Set-Theoretic Methods in Control","volume":"78","author":"Blanchini","year":"2008"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(99)00214-9"},{"key":"ref28","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proceedings of 1999 Advances in Neural Information Processing Systems","author":"Konda"},{"key":"ref29","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"In Proceedings of 2008 AAAI Conference on Artificial Intelligence","volume":"8","author":"Ziebart"}],"event":{"name":"2024 IEEE 7th International Conference on Industrial Cyber-Physical Systems (ICPS)","location":"St. Louis, MO, USA","start":{"date-parts":[[2024,5,12]]},"end":{"date-parts":[[2024,5,15]]}},"container-title":["2024 IEEE 7th International Conference on Industrial Cyber-Physical Systems (ICPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10639954\/10639940\/10640031.pdf?arnumber=10640031","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T06:33:10Z","timestamp":1725431590000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10640031\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,12]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icps59941.2024.10640031","relation":{},"subject":[],"published":{"date-parts":[[2024,5,12]]}}}