{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:39:31Z","timestamp":1780501171008,"version":"3.54.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2238381"],"award-info":[{"award-number":["2238381"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.23919\/acc60939.2024.10644697","type":"proceedings-article","created":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:56:19Z","timestamp":1725558979000},"page":"4813-4818","source":"Crossref","is-referenced-by-count":1,"title":["Constrained Reinforcement Learning for Building Demand Response"],"prefix":"10.23919","author":[{"given":"Jerson","family":"Sanchez","sequence":"first","affiliation":[{"name":"School of Aerospace and Mechanical Engineering, University of Oklahoma,Norman,OK,73072"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Aerospace and Mechanical Engineering, University of Oklahoma,Norman,OK,73072"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Benefits of demand response in electricity markets and recommendations for achieving them","volume-title":"US Department of Energy","year":"2006"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/10789669.2003.10391069"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2021.110833"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.116117"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2957289"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/su12187727"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3014055"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/acc50511.2021.9482917"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyai.2020.100020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1287\/opre.21.5.1071"},{"key":"ref11","article-title":"Trust region policy optimization","volume":"ab\/1502.05477","author":"Schulman","year":"2015","journal-title":"CoRR"},{"key":"ref12","author":"Schulman","year":"2018","journal-title":"High-dimensional continuous control using generalized advantage estimation"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icsmc.2004.1398296"},{"key":"ref15","article-title":"Constrained policy optimization","volume":"abs\/1705.1 0528","author":"Achiam","year":"2017","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/19401493.2015.1108999"},{"key":"ref17","volume-title":"Small general service rate","year":"2021"},{"key":"ref18","volume-title":"CVX: Matlab software for disci-plined convex programming, version 2.1","author":"Grant","year":"2014"},{"key":"ref19","volume-title":"Gurobi solver"},{"issue":"268","key":"ref20","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2024 American Control Conference (ACC)","location":"Toronto, ON, Canada","start":{"date-parts":[[2024,7,10]]},"end":{"date-parts":[[2024,7,12]]}},"container-title":["2024 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10644130\/10644150\/10644697.pdf?arnumber=10644697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T07:15:24Z","timestamp":1725693324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10644697\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":20,"URL":"https:\/\/doi.org\/10.23919\/acc60939.2024.10644697","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]}}}