{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T13:38:25Z","timestamp":1778333905418,"version":"3.51.4"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2022.3227450","type":"journal-article","created":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T20:40:45Z","timestamp":1670445645000},"page":"7574-7587","source":"Crossref","is-referenced-by-count":13,"title":["Multi-Agent Reinforcement Learning Based Actuator Control for EV HVAC Systems"],"prefix":"10.1109","volume":"11","author":[{"given":"Sungho","family":"Joo","sequence":"first","affiliation":[{"name":"MakinaRocks, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongmin","family":"Lee","sequence":"additional","affiliation":[{"name":"MakinaRocks, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minseop","family":"Kim","sequence":"additional","affiliation":[{"name":"MakinaRocks, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1288-5104","authenticated-orcid":false,"given":"Taeho","family":"Lee","sequence":"additional","affiliation":[{"name":"MakinaRocks, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanghyeok","family":"Choi","sequence":"additional","affiliation":[{"name":"MakinaRocks, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seungju","family":"Kim","sequence":"additional","affiliation":[{"name":"MakinaRocks, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeyeol","family":"Lee","sequence":"additional","affiliation":[{"name":"MakinaRocks, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9028-8199","authenticated-orcid":false,"given":"Joongjae","family":"Kim","sequence":"additional","affiliation":[{"name":"Hanon Systems, Deajeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongsub","family":"Lim","sequence":"additional","affiliation":[{"name":"MakinaRocks, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5059-1684","authenticated-orcid":false,"given":"Jeonghoon","family":"Lee","sequence":"additional","affiliation":[{"name":"Hanon Systems, Deajeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CODES-ISSS.2013.6659013"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2016.08.008"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2744804"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.applthermaleng.2015.02.001"},{"key":"ref5","first-page":"1","article-title":"Energy consumption, driving range and cabin temperature performances at different ambient conditions in support to the design of a user-centric efficient electric vehicle: The quiet project","volume-title":"Proc. 14th SDEWES Conf.","author":"Paffumi"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10098-006-0040-0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.4028\/www.scientific.net\/AMR.129-131.17"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISCI.2013.6612382"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrefrig.2014.11.003"},{"key":"ref10","article-title":"Potential of controlling subcooling in residential A\/C system","author":"Xu","year":"2014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2006.1689675"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2017.04.010"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062224"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/pr5030046"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2725899"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2018.03.051"},{"key":"ref18","first-page":"22","article-title":"A deep reinforcement learning approach to using whole building energy model for HVAC optimal control","volume-title":"Proc. Building Perform. Anal. Conf.","volume":"3","author":"Zhang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2992117"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3011739"},{"key":"ref21","volume-title":"GT-SUITE\u00ae","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IECON43393.2020.9255028"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrefrig.2018.02.003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrefrig.2017.03.015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","volume-title":"arXiv:1509.02971","author":"Lillicrap","year":"2015"},{"key":"ref28","article-title":"Proximal policy optimization algorithms","volume-title":"arXiv:1707.06347","author":"Schulman","year":"2017"},{"key":"ref29","article-title":"Soft actor-critic algorithms and applications","volume-title":"arXiv:1812.05905","author":"Haarnoja","year":"2018"},{"key":"ref30","volume-title":"Modeling Purposeful Adaptive Behavior With the Principle of Maximum Causal Entropy","author":"Ziebart","year":"2010"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref35","article-title":"Emergent tool use from multi-agent autocurricula","volume-title":"arXiv:1909.07528","author":"Baker","year":"2019"},{"key":"ref36","article-title":"Dota 2 with large scale deep reinforcement learning","volume-title":"arXiv:1912.06680","author":"Berner","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2015.2418322"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.applthermaleng.2020.116084"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","volume-title":"arXiv:1412.6980","author":"Kingma","year":"2014"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/09973292.pdf?arnumber=9973292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:53:14Z","timestamp":1706763194000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9973292\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3227450","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}