{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T01:23:20Z","timestamp":1783473800421,"version":"3.55.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T00:00:00Z","timestamp":1697414400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T00:00:00Z","timestamp":1697414400000},"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":[[2023,10,16]]},"DOI":"10.1109\/iecon51785.2023.10312131","type":"proceedings-article","created":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T18:52:10Z","timestamp":1700160730000},"page":"1-6","source":"Crossref","is-referenced-by-count":8,"title":["Reinforcement Learning for Optimal HVAC Control: From Theory to Real-World Applications"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2680-3935","authenticated-orcid":false,"given":"Khalil","family":"Al Sayed","sequence":"first","affiliation":[{"name":"ENSAM,Paris"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9179-2581","authenticated-orcid":false,"given":"Abhinandana","family":"Boodi","sequence":"additional","affiliation":[{"name":"CESI Brest Campus,CESI LINEACT (UR 7527),Brest,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6101-9819","authenticated-orcid":false,"given":"Roozbeh","family":"Sadeghian Broujeny","sequence":"additional","affiliation":[{"name":"CESI LINEACT (UR 7527), CESI Arras Campus,Arras,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2031-4088","authenticated-orcid":false,"given":"Karim","family":"Beddiar","sequence":"additional","affiliation":[{"name":"CESI LINEACT (UR 7527), CESI Nantes Campus,Nantes,France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Buildings, IEA","year":"2022"},{"key":"ref2","volume-title":"Electricity Sector, IEA","year":"2022"},{"key":"ref3","article-title":"2022 global status report for buildings and construction: Towards a zero-emission, efficient and resilient buildings and construction sector","year":"2022","journal-title":"United Nations Environment Programme"},{"key":"ref4","volume-title":"Heating, IEA, Paris","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.applthermaleng.2014.03.055"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-7788(00)00114-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/0960-1481(94)90420-0"},{"key":"ref8","volume-title":"IES virtual enviroment (IESVE)","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2017.06.011"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2019.106535"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/en15228663"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jobe.2022.104165"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.115036"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.7250\/itms-2018-0004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13932-1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117733"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref22","article-title":"Mastering chess and shogi by selfplay with a general reinforcement learning algorithm","author":"Silver","year":"2017","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Imagination-augmented agents for deep reinforcement learning","author":"Weber","year":"2017","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Model-based value estimation for efficient model-free reinforcement learning","author":"Feinberg","year":"2018","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2019.07.019"},{"key":"ref27","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Mnih","year":"2016"},{"key":"ref28","article-title":"OpenAI Pieter Abbeel, and Wojciech Zaremba. Hindsight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref29","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto","year":"2018"},{"key":"ref32","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja","year":"2018"},{"key":"ref33","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"International conference on machine learning","author":"Bellemare","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/en15062112"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/s20174918"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.114943"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SIU.2018.8404287"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2020.110225"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyai.2020.100043"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2021.108680"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.116117"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117642"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2022.2120598"},{"key":"ref45","volume-title":"Reinforcement learning in non-stationary environments","author":"Lecarpentier","year":"2020"},{"key":"ref46","article-title":"A survey of meta-reinforcement learning","author":"Beck","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society","location":"Singapore, Singapore","start":{"date-parts":[[2023,10,16]]},"end":{"date-parts":[[2023,10,19]]}},"container-title":["IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10311571\/10311610\/10312131.pdf?arnumber=10312131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T20:15:59Z","timestamp":1710360959000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10312131\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,16]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iecon51785.2023.10312131","relation":{},"subject":[],"published":{"date-parts":[[2023,10,16]]}}}