{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T11:00:52Z","timestamp":1756810852726,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T00:00:00Z","timestamp":1679443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T00:00:00Z","timestamp":1679443200000},"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":[[2023,3,22]]},"DOI":"10.1109\/ciss56502.2023.10089681","type":"proceedings-article","created":{"date-parts":[[2023,4,10]],"date-time":"2023-04-10T18:58:36Z","timestamp":1681153116000},"page":"1-6","source":"Crossref","is-referenced-by-count":4,"title":["Offline Reinforcement Learning for Price-Based Demand Response Program Design"],"prefix":"10.1109","author":[{"given":"Ce","family":"Xu","sequence":"first","affiliation":[{"name":"Stony Brook University Stony Brook,Department of Electrical and Computer Engineering,NY,USA,11794"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"Amazon,Seattle,WA,USA,98109"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Zhao","sequence":"additional","affiliation":[{"name":"Stony Brook University Stony Brook,Department of Electrical and Computer Engineering,NY,USA,11794"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2957705"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2396993"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.114945"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/NAPS50074.2021.9449714"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2172\/836966"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2495145"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2018.03.072"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2018.8403783"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2017.03.102"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.119082"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2640184"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3486611.3486668"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"journal-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"ref17","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Intl Conf. on machine learning","author":"Wang","year":"2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2871361"},{"key":"ref19","first-page":"4195","article-title":"Proximal gradient temporal difference learning algorithms","volume-title":"International Joint Conference of Artificial Intelligence (IJCAI)","author":"Liu","year":"2016"},{"key":"ref20","first-page":"3703","article-title":"Batch policy learning under con-straints","volume-title":"Intl Conf. on Machine Learning","author":"Le","year":"2019"},{"issue":"2015","key":"ref21","first-page":"7857","article-title":"Low carbon london project: Data from the dynamic time-of-use electricity pricing trial, 2013","volume":"7857","author":"Schofield","year":"2015","journal-title":"UK Data Service, SN"},{"journal-title":"Centre for Environmental Data Analysis","article-title":"Met office MIDAS open: UK land surface stations data (1853-current)","year":"2019","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1088\/1755-1315\/121\/5\/052081"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref24"}],"event":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","start":{"date-parts":[[2023,3,22]]},"location":"Baltimore, MD, USA","end":{"date-parts":[[2023,3,24]]}},"container-title":["2023 57th Annual Conference on Information Sciences and Systems (CISS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10089615\/10089616\/10089681.pdf?arnumber=10089681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T11:10:28Z","timestamp":1709464228000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10089681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,22]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ciss56502.2023.10089681","relation":{},"subject":[],"published":{"date-parts":[[2023,3,22]]}}}