{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:11:12Z","timestamp":1730203872392,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"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":[[2019,8]]},"DOI":"10.1109\/ccta.2019.8920406","type":"proceedings-article","created":{"date-parts":[[2019,12,6]],"date-time":"2019-12-06T04:11:37Z","timestamp":1575605497000},"page":"308-313","source":"Crossref","is-referenced-by-count":10,"title":["Model Predictive Control Based on Deep Reinforcement Learning Method with Discrete-Valued Input"],"prefix":"10.1109","author":[{"given":"Yoshio","family":"Tange","sequence":"first","affiliation":[]},{"given":"Satoshi","family":"Kiryu","sequence":"additional","affiliation":[]},{"given":"Tetsuro","family":"Matsui","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"1369","article-title":"Linearly-solvable Markov decision problems","volume":"19","author":"todorov","year":"2007","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1287\/ijoc.1080.0305"},{"key":"ref12","first-page":"1071","article-title":"Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics","volume":"27","author":"levine","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"2094","article-title":"Deep Reinforcement Learning with Double Q-Learning","author":"hasselt","year":"2016","journal-title":"Proc AAAI Conf Artificial Intelligence"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/MSP.2017.2743240"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1016\/0005-1098(89)90002-2"},{"year":"2002","author":"maciejowski","journal-title":"Predictive Control with Constraints","key":"ref16"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1016\/S0967-0661(02)00186-7"},{"year":"2009","author":"wang","journal-title":"Model Predictive Control System Design and Implementation Using MATLAB","key":"ref18"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/S0005-1098(01)00174-1","article-title":"The explicit linear quadratic regulator for constrained systems","volume":"38","author":"bemporad","year":"2002","journal-title":"Automatica"},{"key":"ref28","first-page":"1476","article-title":"Data-driven Tuning for LSTM Recurrent Neural Network-based Controllers","author":"wakasa","year":"2018","journal-title":"Proc SICE Annu Conf 2018"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref27","first-page":"1376","article-title":"Synthesizing Chemical Plant Operation Procedures using Knowledge, Dynamic Simulation and Deep Reinforcement Learning","author":"kubosawa","year":"2018","journal-title":"Proc SICE Annu Conf 2018"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"hinton","year":"2006","journal-title":"Science"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1016\/j.neucom.2016.12.038"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1017\/atsip.2013.9"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1007\/BF02743935"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/JPROC.2017.2761740"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1038\/nature24270"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1613\/jair.301"},{"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"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1080\/00207170600892949"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/MED.2014.6961403"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1016\/j.automatica.2008.11.023"},{"year":"0","journal-title":"Chainer","key":"ref24"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ASCC.2015.7244532"},{"key":"ref26","first-page":"1035","article-title":"A Study on Vision-based Behavior Learning of Real Mobile Robot by Deep Q-network","author":"kato","year":"2018","journal-title":"Proc SICE Annu Conf 2018"},{"key":"ref25","first-page":"567","article-title":"Deep reinforcement learning based finite-horizon optimal control for a discrete-time affine nonlinear system","author":"kim","year":"2018","journal-title":"Proc SICE Annu Conf 2018"}],"event":{"name":"2019 IEEE Conference on Control Technology and Applications (CCTA)","start":{"date-parts":[[2019,8,19]]},"location":"Hong Kong, China","end":{"date-parts":[[2019,8,21]]}},"container-title":["2019 IEEE Conference on Control Technology and Applications (CCTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8911117\/8920394\/08920406.pdf?arnumber=8920406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T10:46:07Z","timestamp":1658141167000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8920406\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ccta.2019.8920406","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}