{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T16:54:05Z","timestamp":1743267245545,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,19]],"date-time":"2024-05-19T00:00:00Z","timestamp":1716076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,19]],"date-time":"2024-05-19T00:00:00Z","timestamp":1716076800000},"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":[[2024,5,19]]},"DOI":"10.1109\/iscas58744.2024.10558623","type":"proceedings-article","created":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T17:22:52Z","timestamp":1719940972000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Model Predictive Control-Based Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Qiang","family":"Han","sequence":"first","affiliation":[{"name":"The University of Western Australia,Department of Electrical, Electronic & Computer Engineering,Perth,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farid","family":"Boussaid","sequence":"additional","affiliation":[{"name":"The University of Western Australia,Department of Electrical, Electronic & Computer Engineering,Perth,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[{"name":"The University of Western Australia,Department of Computer Science and Software Engineering,Perth,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Reinforcement learning: An introduction[M]","year":"2018","author":"Sutton","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MEC.2011.6025669"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"ref4","article-title":"Beyond regression: New tools for prediction and analysis in the behavioral sciences[J]","volume-title":"PhD thesis","author":"Werbos","year":"1974"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2417170"},{"journal-title":"Deep model-based reinforcement learning for high-dimensional problems, a survey[J]","year":"2020","author":"Plaat","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2514\/1.T5774"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13076"},{"issue":"07849","key":"ref9","volume":"2209","author":"Wannawas","year":"2022","journal-title":"Neuromuscular Reinforcement Learning to Actuate Human Limbs through FES"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3174625"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1142\/S2301385023310027"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1063\/5.0143913"},{"key":"ref13","first-page":"1","article-title":"Guided policy search","volume-title":"International Conference on Machine Learning","author":"Levine"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207398"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPEL.2023.3288499"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3273590"},{"journal-title":"Plan online, learn offline: Efficient learning and exploration via modelbased control[J]","year":"2018","author":"Lowrey","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2011.12.004"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.applthermaleng.2023.120430"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/designs7010018"},{"key":"ref21","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor[C]","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0925-2312(93)90006-O"},{"issue":"6114","key":"ref23","volume":"1312","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes[J]"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0280071"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.22266\/ijies2022.0630.06"}],"event":{"name":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","start":{"date-parts":[[2024,5,19]]},"location":"Singapore, Singapore","end":{"date-parts":[[2024,5,22]]}},"container-title":["2024 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10557746\/10557828\/10558623.pdf?arnumber=10558623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T07:03:02Z","timestamp":1719990182000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10558623\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,19]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iscas58744.2024.10558623","relation":{},"subject":[],"published":{"date-parts":[[2024,5,19]]}}}