{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T11:00:42Z","timestamp":1776078042542,"version":"3.50.1"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["2239458"],"award-info":[{"award-number":["2239458"]}]},{"DOI":"10.13039\/100005595","name":"University of California (UC) National Laboratory Fees Research Program","doi-asserted-by":"publisher","award":["69763"],"award-info":[{"award-number":["69763"]}],"id":[{"id":"10.13039\/100005595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2024.3410951","type":"journal-article","created":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T17:46:49Z","timestamp":1718387209000},"page":"4408-4426","source":"Crossref","is-referenced-by-count":18,"title":["Multi-Zone HVAC Control With Model-Based Deep Reinforcement Learning"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6114-2801","authenticated-orcid":false,"given":"Xianzhong","family":"Ding","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, University of California at Merced, Merced, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4531-9704","authenticated-orcid":false,"given":"Alberto","family":"Cerpa","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of California at Merced, Merced, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2732-6954","authenticated-orcid":false,"given":"Wan","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of California at Merced, Merced, CA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3408308.3427986"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/sj.jea.7500165"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2306964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2361122"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3643832.3661876"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3583120.3586969"},{"key":"ref7","first-page":"979","article-title":"Model predictive control for mid-size commercial building HVAC: Implementation, results and energy savings","volume-title":"Proc. 2nd Int. Conf. Building Energy Environ.","author":"Bengea"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2172\/1419622"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2647881"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2975847"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2015.10.036"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2674061.2674072"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN48710.2020.00030"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-1514(199601\/03)17:1<71::AID-OCA561>3.0.CO;2-E"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2014.12.019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3389\/fbuil.2020.562239"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360857"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3656043"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3276774.3276775"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3396851.3402364"},{"key":"ref21","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3600100.3623742"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3656234"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360861"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2011.12.005"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref28","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref29","article-title":"Thermal comfort. analysis and applications in environmental engineering","author":"Fanger","year":"1970","journal-title":"Thermal Comfort. Anal. Appl. Environ. Eng."},{"key":"ref30","first-page":"1","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lakshminarayanan"},{"key":"ref31","first-page":"1","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Chua"},{"key":"ref32","volume-title":"Model-based Reinforcement Learning","author":"Levine","year":"2020"},{"key":"ref33","first-page":"1101","article-title":"Deep dynamics models for learning dexterous manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Nagabandi"},{"key":"ref34","volume-title":"Thermal Environmental Conditions for Human Occupancy","year":"2004"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2013.01.008"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1080\/19401493.2010.518631"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2014.2313736"},{"key":"ref39","first-page":"1","article-title":"A natural policy gradient","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"14","author":"Kakade"},{"key":"ref40","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Schulman"},{"key":"ref41","article-title":"The cross-entropy method for optimization","volume-title":"Handbook of Statistics","author":"Botev","year":"2013"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3279278"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2012.2205567"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2015.2455419"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2992117"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3315549"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3011739"},{"key":"ref48","first-page":"22069","article-title":"Learning individually inferred communication for multi-agent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ding"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3396851.3397694"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3404191"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00085"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2712560"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3299275"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3183610"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3356250.3360038"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.119742"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3439332"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3408308.3427604"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3164023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2015.06.033"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2015.05.081"},{"key":"ref62","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn","volume":"97","author":"Iqbal"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2023.113770"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3600100.3623753"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3538637.3538852"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/10557792.pdf?arnumber=10557792","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T05:52:52Z","timestamp":1740203572000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10557792\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tase.2024.3410951","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}