{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T11:28:00Z","timestamp":1763810880910,"version":"3.37.3"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T00:00:00Z","timestamp":1656288000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T00:00:00Z","timestamp":1656288000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6,27]]},"DOI":"10.1109\/icca54724.2022.9831914","type":"proceedings-article","created":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T20:18:44Z","timestamp":1658780324000},"page":"698-703","source":"Crossref","is-referenced-by-count":4,"title":["Near-optimal Deep Reinforcement Learning Policies from Data for Zone Temperature Control"],"prefix":"10.1109","author":[{"given":"Loris Di","family":"Natale","sequence":"first","affiliation":[{"name":"Swiss Federal Laboratories for Materials Science and Technology (Empa),Urban Energy Systems Laboratory,D&#x00FC;bendorf,Switzerland,8600"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bratislav","family":"Svetozarevic","sequence":"additional","affiliation":[{"name":"Swiss Federal Laboratories for Materials Science and Technology (Empa),Urban Energy Systems Laboratory,D&#x00FC;bendorf,Switzerland,8600"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philipp","family":"Heer","sequence":"additional","affiliation":[{"name":"Swiss Federal Laboratories for Materials Science and Technology (Empa),Urban Energy Systems Laboratory,D&#x00FC;bendorf,Switzerland,8600"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Colin N.","family":"Jones","sequence":"additional","affiliation":[{"name":"Swiss Federal Institute of Technology Lausanne (EPFL),Laboratoire d&#x2019;Automatique,Lausanne,Switzerland,1015"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Deep reinforcement learning for optimal control of space heating","year":"2018","author":"nagy","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-7788(00)00114-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2019.07.029"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.35833\/MPCE.2021.000394"},{"article-title":"Physically Consistent Neural Networks for building thermal modeling: theory and analysis","year":"2021","author":"di natale","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"year":"2021","key":"ref16","article-title":"NEST"},{"key":"ref17","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"International Conference on Machine Learning"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref18"},{"key":"ref19","first-page":"2613","article-title":"Double Q-learning","volume":"23","author":"hasselt","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.118127"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2012.06.014"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117733"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2019.106535"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3447555.3464874"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2022.104128"},{"year":"2020","key":"ref2","article-title":"Energy consumption in households"},{"year":"2019","key":"ref1","article-title":"Factsheet: The energy performance of buildings directive"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2019.03.038"},{"key":"ref20","article-title":"On the Variance of the Adaptive Learning Rate and Beyond","author":"liu","year":"2020","journal-title":"Proceedings of the Eighth International Conference on Learning Representations (ICLR 2020)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"}],"event":{"name":"2022 IEEE 17th International Conference on Control & Automation (ICCA)","start":{"date-parts":[[2022,6,27]]},"location":"Naples, Italy","end":{"date-parts":[[2022,6,30]]}},"container-title":["2022 IEEE 17th International Conference on Control &amp; Automation (ICCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9831427\/9831807\/09831914.pdf?arnumber=9831914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:05:07Z","timestamp":1660593907000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9831914\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,27]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icca54724.2022.9831914","relation":{},"subject":[],"published":{"date-parts":[[2022,6,27]]}}}