{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T04:11:44Z","timestamp":1785384704448,"version":"3.55.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T00:00:00Z","timestamp":1628467200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T00:00:00Z","timestamp":1628467200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T00:00:00Z","timestamp":1628467200000},"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":[[2021,8,9]]},"DOI":"10.1109\/ccta48906.2021.9659202","type":"proceedings-article","created":{"date-parts":[[2022,1,3]],"date-time":"2022-01-03T15:17:48Z","timestamp":1641223068000},"page":"57-62","source":"Crossref","is-referenced-by-count":18,"title":["Multi-agent Battery Storage Management using MPC-based Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Arash Bahari","family":"Kordabad","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqi","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastien","family":"Gros","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2913768"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/ECC54610.2021.9654852"},{"key":"ref12","first-page":"arxiv","article-title":"Reinforcement learning based on MPC\/MHE for unmodeled and partially observable dynamics","author":"nejatbakhsh esfahani","year":"2021","journal-title":"ArXiv e-prints"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483100"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2021.08.562"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/APEC.2010.5433666"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2014.2344859"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/app8101825"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2019.100837"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/PMAPS47429.2020.9183575"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1016\/j.ejcon.2020.02.004","article-title":"Stochastic model predictive control of photovoltaic battery systems using a probabilistic forecast model","author":"gro\u00df","year":"2020","journal-title":"European Journal of Control"},{"key":"ref6","author":"bertsekas","year":"2019","journal-title":"REINFORCEMENT LEARNING AND OPTIMAL CONTROL"},{"key":"ref5","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref8","first-page":"480","article-title":"Emotional learning based intelligent controller for mimo peripheral milling process","volume":"6","author":"bahari kordabad","year":"2020","journal-title":"Journal of Computational and Applied Mechanics"},{"key":"ref7","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref2","author":"rastler","year":"2010","journal-title":"Electricity Energy Storage Technology Options A white Paper primer on Applications Costs and Benefits"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2429919"},{"key":"ref9","volume":"2","author":"rawlings","year":"2017","journal-title":"Model Predictive Control Theory Computation and Design"},{"key":"ref20","first-page":"i?387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proceedings of the 31st International Conference on International Conference on Machine Learning"},{"key":"ref21","year":"2020","journal-title":"Day-ahead power prices of Trondheim Norway during November 2020"}],"event":{"name":"2021 IEEE Conference on Control Technology and Applications (CCTA)","location":"San Diego, CA, USA","start":{"date-parts":[[2021,8,9]]},"end":{"date-parts":[[2021,8,11]]}},"container-title":["2021 IEEE Conference on Control Technology and Applications (CCTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9658569\/9658587\/09659202.pdf?arnumber=9659202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T12:56:33Z","timestamp":1652187393000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9659202\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,9]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ccta48906.2021.9659202","relation":{},"subject":[],"published":{"date-parts":[[2021,8,9]]}}}