{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T22:16:51Z","timestamp":1785017811367,"version":"3.55.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFF0619300"],"award-info":[{"award-number":["2024YFF0619300"]}]},{"name":"Natural Science Fund of Shandong Province","award":["ZR2023QF048"],"award-info":[{"award-number":["ZR2023QF048"]}]},{"name":"Natural Science Fund of Shandong Province","award":["2023HWYQ-003"],"award-info":[{"award-number":["2023HWYQ-003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Smart Grid"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tsg.2026.3665037","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T21:07:28Z","timestamp":1771276048000},"page":"3112-3125","source":"Crossref","is-referenced-by-count":1,"title":["HVAC Control With Optimization-Guided Behavior Cloning and Restricted Residual Policy Learning"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3208-9620","authenticated-orcid":false,"given":"Shuhua","family":"Gao","sequence":"first","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3392-3234","authenticated-orcid":false,"given":"Hailong","family":"Wen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Wang","sequence":"additional","affiliation":[{"name":"State Grid Shandong Electric Power Company Electric Power Research Institute, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunmeng","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1229-6860","authenticated-orcid":false,"given":"Cheng","family":"Xiang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3151748"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.scs.2020.102480"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/UKSim.2016.13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICSTCC.2015.7321372"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2016.11.041"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117005"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2983486"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CEC45853.2021.9504800"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2021.108681"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2021.3057630"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPEL.2025.3581978"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.118346"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2023.3324795"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3357109"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSUSC.2022.3164084"},{"key":"ref16","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref17","first-page":"1","article-title":"Offline reinforcement learning with implicit Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kostrikov"},{"key":"ref18","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fujimoto"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSUSC.2023.3251302"},{"key":"ref20","first-page":"470","article-title":"A dataset perspective on offline reinforcement learning","volume-title":"Proc. Conf. Lifelong Learn. Agents","author":"Schweighofer"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3111454"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2024.123753"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyai.2023.100255"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2019.106326"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.01.030"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3273590"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360849"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2024.114879"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.128166"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040202"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3101357"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1080\/19401493.2024.2418813"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-017-0130-5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2022.100258"},{"key":"ref37","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref38","first-page":"1","article-title":"A simple weight decay can improve generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"4","author":"Krogh"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3250241"},{"key":"ref40","first-page":"1","article-title":"Behavioral cloning from noisy demonstrations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sasaki"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref43","first-page":"40587","article-title":"Supported value regularization for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Chen"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117642"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.2172\/1854582","article-title":"End-use load profiles for the U.S. Building stock: Methodology and results of model calibration, validation, and uncertainty quantification","author":"Wilson","year":"2022"},{"key":"ref46","article-title":"The citylearn challenge 2023 dataset","author":"Nweye","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2025.3547260"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57077-4_10"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3122570"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3106662"}],"container-title":["IEEE Transactions on Smart Grid"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165411\/11575304\/11397099.pdf?arnumber=11397099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T06:03:27Z","timestamp":1782281007000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11397099\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":50,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tsg.2026.3665037","relation":{},"ISSN":["1949-3053","1949-3061"],"issn-type":[{"value":"1949-3053","type":"print"},{"value":"1949-3061","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}