{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T02:32:54Z","timestamp":1730341974953,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"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":[[2022,6,8]]},"DOI":"10.23919\/acc53348.2022.9867466","type":"proceedings-article","created":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T20:24:10Z","timestamp":1662409450000},"page":"2571-2577","source":"Crossref","is-referenced-by-count":1,"title":["Data-Driven Learning Control for Building Energy Management"],"prefix":"10.23919","author":[{"given":"Avisek","family":"Naug","sequence":"first","affiliation":[{"name":"Vanderbilt University,Nashville,Tennessee,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcos","family":"Quinones-Grueiro","sequence":"additional","affiliation":[{"name":"Vanderbilt University,Nashville,Tennessee,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gautam","family":"Biswas","sequence":"additional","affiliation":[{"name":"Vanderbilt University,Nashville,Tennessee,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref11","article-title":"Proximal Policy Optimization Algorithms","author":"schulman","year":"2017","journal-title":"ArXiv"},{"key":"ref12","article-title":"Algorithms for´ hyperparameter optimization","volume":"24","author":"bergstra","year":"2011","journal-title":"Advances in neural information processing systems"},{"year":"2021","key":"ref13","article-title":"Buildings.Examples.VAVReheat"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2018.8560520"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2021.111053"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.12.030"},{"key":"ref17","first-page":"1008","article-title":"Actor-citic agorithms","author":"konda","year":"1999","journal-title":"NIPS’99 Proceedings of the 12th International Conference on Neural Information Processing Systems"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref18"},{"article-title":"Deep online learning via meta-learning: Continual adaptation for model-based rl","year":"2018","author":"nagabandi","key":"ref19"},{"article-title":"Data-Driven Deep Reinforcement Learning","year":"2021","author":"seita","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360861"},{"key":"ref6","first-page":"7214","article-title":"Non-Stationary Markov Decision Processes a Worst-Case Approach using Model-Based Reinforcement Learning","author":"lecarpentier","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3459991"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0019241"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3408308.3427986"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360998"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"}],"event":{"name":"2022 American Control Conference (ACC)","start":{"date-parts":[[2022,6,8]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2022,6,10]]}},"container-title":["2022 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9866948\/9867142\/09867466.pdf?arnumber=9867466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T20:39:41Z","timestamp":1664829581000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9867466\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,8]]},"references-count":19,"URL":"https:\/\/doi.org\/10.23919\/acc53348.2022.9867466","relation":{},"subject":[],"published":{"date-parts":[[2022,6,8]]}}}