{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T05:21:57Z","timestamp":1785129717438,"version":"3.55.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"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":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1109\/tetci.2021.3066999","type":"journal-article","created":{"date-parts":[[2021,4,26]],"date-time":"2021-04-26T21:30:58Z","timestamp":1619472658000},"page":"255-266","source":"Crossref","is-referenced-by-count":18,"title":["An Enhanced Adaptivity of Reinforcement Learning-Based Temperature Control in Buildings Using Generalized Training"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8060-4407","authenticated-orcid":false,"given":"Vincent","family":"Taboga","sequence":"first","affiliation":[{"name":"Mathematics and industrial engineering, Polytechnique Montréal, Montréal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3400-3766","authenticated-orcid":false,"given":"Amine","family":"Bellahsen","sequence":"additional","affiliation":[{"name":"Mathematics and industrial engineering, Polytechnique Montréal, Montréal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7500-0468","authenticated-orcid":false,"given":"Hanane","family":"Dagdougui","sequence":"additional","affiliation":[{"name":"Mathematics and industrial engineering, Polytechnique Montréal, Montréal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1072","article-title":"Reinforcement learning for demand response: A review of algorithms and modeling techniques","volume-title":"Appl. Energy","volume":"235","author":"Vzquez-Canteli","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2020.109831"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/en11030631"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.2991728"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2019.2907718"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2640184"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2834219"},{"key":"ref8","first-page":"30","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2517211"},{"key":"ref10","first-page":"472","article-title":"Whole building energy model for hvac optimal control: A practical framework based on deep reinforcement learning","volume-title":"Energy Buildings","volume":"199","author":"Zhang","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2014.05.056"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2552169"},{"key":"ref13","article-title":"Deep reinforcement learning to optimise indoor temperature control and heating energy consumption in buildings","volume-title":"Energy Buildings","volume":"224","author":"Brandi","year":"2020"},{"key":"ref14","article-title":"Reinforcement learning for building controls: The opportunities and challenges","volume-title":"Appl. Energy","volume":"269","author":"Wang","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2769104"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-22734-0_9"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2012.2214069"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848048"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848075"},{"key":"ref20","article-title":"Assessing generalization in deep reinforcement learning","volume-title":"CoRR","volume":"abs\/1810.12282","author":"Packer","year":"2018"},{"key":"ref21","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Cobbe","year":"2018"},{"key":"ref22","article-title":"Deep reinforcement learning that matters","volume-title":"CoRR","author":"Henderson","year":"2017"},{"key":"ref23","article-title":"Stable baselines","volume-title":"GitHub Repository","author":"Hill","year":"2018"},{"key":"ref24","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref25","first-page":"5279","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu","year":"2017"},{"key":"ref26","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.egypro.2017.09.692"},{"key":"ref28","first-page":"45","article-title":"Reinforcement learning testbed for power-consumption optimization","volume-title":"Proc. Methods Applicat. Modeling Simulation Complex Syst.","volume":"08","author":"Takao","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s40565-018-0431-3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_72229"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"ref32","article-title":"Household appliances wasted heat storage by means of a packed bed tes with encapsulated PCM","volume-title":"Proc. 13th Int. Conf. Sustainable Energy Techno.","author":"Simone","year":"2018"},{"key":"ref33","article-title":"Robust reinforcement learning using adversarial populations","author":"Vinitsky","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/en10111846"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.1995.598994"},{"key":"ref36","first-page":"343","article-title":"Theory and applications of HVAC control systems - A review of model predictive control (MPC)","volume-title":"Building Environ.","volume":"72","author":"Afram","year":"2014"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2909266"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2629450"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/9741092\/09415466.pdf?arnumber=9415466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:30:04Z","timestamp":1704843004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9415466\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4]]},"references-count":38,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2021.3066999","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4]]}}}