{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:12:18Z","timestamp":1784391138687,"version":"3.55.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2017,9,1]],"date-time":"2017-09-01T00:00:00Z","timestamp":1504224000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Flemish Institute for the Promotion of Scientific and Technological Research in Industry (IWT)"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Smart Grid"],"published-print":{"date-parts":[[2017,9]]},"DOI":"10.1109\/tsg.2016.2517211","type":"journal-article","created":{"date-parts":[[2016,2,8]],"date-time":"2016-02-08T19:11:16Z","timestamp":1454958676000},"page":"2149-2159","source":"Crossref","is-referenced-by-count":292,"title":["Residential Demand Response of Thermostatically Controlled Loads Using Batch Reinforcement Learning"],"prefix":"10.1109","volume":"8","author":[{"given":"Frederik","family":"Ruelens","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bert J.","family":"Claessens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stijn","family":"Vandael","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bart","family":"De Schutter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Babuska","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ronnie","family":"Belmans","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"521","article-title":"Exploiting policy knowledge in online least-squares policy iteration: An empirical study","volume":"19","author":"busoniu","year":"2010","journal-title":"Autom Comput Appl Math"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1002\/9781118029176","author":"powell","year":"2011","journal-title":"Approximate Dynamic Programming Solving the Curses of Dimensionality"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114724"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TDC.2008.4517260"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2012.2205591"},{"key":"ref30","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"ref37","first-page":"324","article-title":"Approximate dynamic programming","author":"bertsekas","year":"2011","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref36","author":"bellman","year":"2013","journal-title":"Dynamic Programming"},{"key":"ref35","year":"2015","journal-title":"Belpex—Belgian Power Exchange"},{"key":"ref34","first-page":"1","article-title":"Using PCA to efficiently represent state spaces","author":"curran","year":"2015","journal-title":"Proceedings of the 8th European Workshop on Reinforcement Learning (EWRL)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTGRID.2010.5622078"},{"key":"ref40","first-page":"317","article-title":"Neural fitted Q iteration—First experiences with a data efficient neural reinforcement learning method","volume":"3720","author":"riedmiller","year":"2005","journal-title":"Proc 16th Eur Conf Mach Learn (ECML)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2012.2213847"},{"key":"ref12","first-page":"1008","article-title":"Beyond theory: The challenge of implementing model predictive control in buildings","author":"cigler","year":"2013","journal-title":"Proc 11th REHVA World Congress (CLIMA)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HICSS.2012.545"},{"key":"ref14","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref15","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.2007630"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/10789669.2003.10391069"},{"key":"ref18","article-title":"An intelligent battery controller using bias-corrected Q-learning","author":"lee","year":"0","journal-title":"Association for the Advancement of Artificial Intelligence"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2013.2263201"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2396993"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SmartGridComm.2012.6485964"},{"key":"ref27","author":"rummery","year":"1994","journal-title":"On-line Q-learning using connectionist systems"},{"key":"ref3","first-page":"1","article-title":"Modeling and control of aggregated heterogeneous thermostatically controlled loads for ancillary services","author":"koch","year":"2011","journal-title":"Proc 17th Power Syst Comput Conf (PSCC)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2013.2277585"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2393059"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/PSCC.2014.7038106"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISGTEUROPE.2010.5638863"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/EEM.2009.5207145"},{"key":"ref2","article-title":"Annual energy outlook 2014 with projections to 2040","year":"2015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2010.2055904"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISGTEurope.2012.6465708"},{"key":"ref20","first-page":"2613","article-title":"Double Q-learning","author":"hasselt","year":"2010","journal-title":"Proc 24th Adv Neural Inf Process Syst (NIPS)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927534"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2106494"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-012-1248-5"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017928328829"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"hinton","year":"2006","journal-title":"Science"},{"key":"ref23","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref44","year":"2015","journal-title":"Gurobi Optimizer Reference Manual"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref43","article-title":"Realistic domestic hot-water profiles in different time scales: Report for the international energy agency, solar heating and cooling task (IEA-SHC)","author":"jordan","year":"2001"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"}],"container-title":["IEEE Transactions on Smart Grid"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165411\/8013887\/07401112.pdf?arnumber=7401112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:41:14Z","timestamp":1642005674000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7401112\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9]]},"references-count":45,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tsg.2016.2517211","relation":{},"ISSN":["1949-3053","1949-3061"],"issn-type":[{"value":"1949-3053","type":"print"},{"value":"1949-3061","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,9]]}}}