{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:08:21Z","timestamp":1778342901939,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,11,7]],"date-time":"2018-11-07T00:00:00Z","timestamp":1541548800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,11,7]]},"DOI":"10.1145\/3276774.3276775","type":"proceedings-article","created":{"date-parts":[[2018,11,28]],"date-time":"2018-11-28T19:16:10Z","timestamp":1543432570000},"page":"148-157","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":84,"title":["Practical implementation and evaluation of deep reinforcement learning control for a radiant heating system"],"prefix":"10.1145","author":[{"given":"Zhiang","family":"Zhang","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Khee Poh","family":"Lam","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]}],"member":"320","published-online":{"date-parts":[[2018,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Refrigerating and Air-Conditioning Engineers","author":"American Society of Heating","year":"2002","unstructured":"American Society of Heating , Refrigerating and Air-Conditioning Engineers 2002 . Guideline 14, Measurement of Energy and Demand Savings. Guideline . American Society of Heating, Refrigerating and Air-Conditioning Engineers 2002. Guideline 14, Measurement of Energy and Demand Savings. Guideline."},{"key":"e_1_3_2_1_2_1","volume-title":"Refrigerating and Air-Conditioning Engineers","author":"American Society of Heating","year":"2017","unstructured":"American Society of Heating , Refrigerating and Air-Conditioning Engineers 2017 . Standard 55, Thermal Environmental Conditions for Human Occupancy. Standard . American Society of Heating, Refrigerating and Air-Conditioning Engineers 2017. Standard 55, Thermal Environmental Conditions for Human Occupancy. Standard."},{"key":"e_1_3_2_1_3_1","volume-title":"CoRR abs\/1606.01540","author":"Brockman Greg","year":"2016","unstructured":"Greg Brockman , Vicki Cheung , Ludwig Pettersson , Jonas Schneider , John Schulman , Jie Tang , and Wojciech Zaremba . 2016. Open AI Gym . CoRR abs\/1606.01540 ( 2016 ). arXiv:1606.01540 Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. 2016. OpenAI Gym. CoRR abs\/1606.01540 (2016). arXiv:1606.01540"},{"key":"e_1_3_2_1_4_1","volume-title":"Retrieved","author":"Inc.","year":"2018","unstructured":"BuildSimHub, Inc. 2018 . BuildSimHub . Retrieved January 18, 2018 from https:\/\/www.buildsim.io\/ BuildSimHub, Inc. 2018. BuildSimHub. Retrieved January 18, 2018 from https:\/\/www.buildsim.io\/"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1137\/0916069"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2012.07.003"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2017.08.069"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2015.11.014"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.segan.2016.02.002"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2006.07.010"},{"key":"e_1_3_2_1_11_1","volume-title":"STAR","author":"ENERGY","year":"2017","unstructured":"ENERGY STAR 2017 . Portfolio Manager Technical Reference : Climate and Weather. Technical Reference. Retrieved August 27, 2018 from https:\/\/www.energystar.gov\/buildings\/tools-and-resources\/portfolio-manager-technical-reference-climate-and-weather ENERGY STAR 2017. Portfolio Manager Technical Reference: Climate and Weather. Technical Reference. Retrieved August 27, 2018 from https:\/\/www.energystar.gov\/buildings\/tools-and-resources\/portfolio-manager-technical-reference-climate-and-weather"},{"key":"e_1_3_2_1_12_1","volume-title":"Thermal comfort: analysis and applications in environmental engineering","author":"Fanger Povl Ole","unstructured":"Povl Ole Fanger . 1970. Thermal comfort: analysis and applications in environmental engineering . Danish Technical Press , Copenhagen, Denmark . Povl Ole Fanger. 1970. Thermal comfort: analysis and applications in environmental engineering. Danish Technical Press, Copenhagen, Denmark."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/2693820.2693826"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2528282.2528297"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2015.01.037"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2017.12.019"},{"key":"e_1_3_2_1_17_1","volume-title":"Retrieved","author":"Lawrence Berkeley National Laboratory.","year":"2016","unstructured":"Lawrence Berkeley National Laboratory. 2016 . Building Controls Virtual Test Bed . Retrieved September 25, 2018 from https:\/\/simulationresearch.lbl.gov\/bcvtb Lawrence Berkeley National Laboratory. 2016. Building Controls Virtual Test Bed. Retrieved September 25, 2018 from https:\/\/simulationresearch.lbl.gov\/bcvtb"},{"key":"e_1_3_2_1_18_1","volume-title":"Transforming Cooling Optimization for Green Data Center via Deep Reinforcement Learning. ArXiv e-prints (Sept","author":"Li Yuanlong","year":"2017","unstructured":"Yuanlong Li , Yonggang Wen , Kyle Guan , and Dacheng Tao . 2017. Transforming Cooling Optimization for Green Data Center via Deep Reinforcement Learning. ArXiv e-prints (Sept . 2017 ). arXiv:cs.AI\/1709.05077 Yuanlong Li, Yonggang Wen, Kyle Guan, and Dacheng Tao. 2017. Transforming Cooling Optimization for Green Data Center via Deep Reinforcement Learning. ArXiv e-prints (Sept. 2017). arXiv:cs.AI\/1709.05077"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2015.04.033"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2005.06.001"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1115\/1.2710491"},{"key":"e_1_3_2_1_22_1","volume-title":"Mehdi Mirza, Alex Graves, Timothy P Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu.","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih , Adri\u00e0 Puigdom\u00e8nech Badia , Mehdi Mirza, Alex Graves, Timothy P Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016 . Asynchronous Methods for Deep Reinforcement Learning. ArXiv e-prints (Feb. 2016). arXiv:1602.01783 Volodymyr Mnih, Adri\u00e0 Puigdom\u00e8nech Badia, Mehdi Mirza, Alex Graves, Timothy P Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous Methods for Deep Reinforcement Learning. ArXiv e-prints (Feb. 2016). arXiv:1602.01783"},{"key":"e_1_3_2_1_23_1","volume-title":"Playing Atari with Deep Reinforcement Learning. ArXiv e-prints (Dec","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih , Koray Kavukcuoglu , David Silver , Alex Graves , Ioannis Antonoglou , Daan Wierstra , and Martin Riedmiller . 2013. Playing Atari with Deep Reinforcement Learning. ArXiv e-prints (Dec . 2013 ). arXiv:1312.5602 Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. ArXiv e-prints (Dec. 2013). arXiv:1312.5602"},{"key":"e_1_3_2_1_24_1","volume-title":"Deep Reinforcement Learning for Optimal Control of Space Heating. ArXiv e-prints (May","author":"Nagy Adam","year":"2018","unstructured":"Adam Nagy , Hussain Kazmi , Farah Cheaib , and Johan Driesen . 2018. Deep Reinforcement Learning for Optimal Control of Space Heating. ArXiv e-prints (May 2018 ). arXiv:stat.AP\/1805.03777 Adam Nagy, Hussain Kazmi, Farah Cheaib, and Johan Driesen. 2018. Deep Reinforcement Learning for Optimal Control of Space Heating. ArXiv e-prints (May 2018). arXiv:stat.AP\/1805.03777"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2017.03.018"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2017.09.102"},{"key":"e_1_3_2_1_27_1","volume-title":"Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res. 12 (Nov.","author":"Pedregosa Fabian","year":"2011","unstructured":"Fabian Pedregosa , Ga\u00ebl Varoquaux , Alexandre Gramfort , Vincent Michel , Bertrand Thirion , Olivier Grisel , Mathieu Blondel , Peter Prettenhofer , Ron Weiss , Vincent Dubourg , Jake Vanderplas , Alexandre Passos , David Cournapeau , Matthieu Brucher , Matthieu Perrot , and \u00c9douard Duchesnay . 2011 . Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res. 12 (Nov. 2011), 2825--2830. http:\/\/dl.acm.org\/citation.cfm?id=1953048.2078195 Fabian Pedregosa, Ga\u00ebl Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, and \u00c9douard Duchesnay. 2011. Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res. 12 (Nov. 2011), 2825--2830. http:\/\/dl.acm.org\/citation.cfm?id=1953048.2078195"},{"key":"e_1_3_2_1_28_1","volume-title":"IEEE International Conference on Automatic Computing: Feedback Computing","volume":"16","author":"Peng Kuo Shiuan","unstructured":"Kuo Shiuan Peng and Clayton T. Morrison . 2016. Model Predictive Prior Reinforcement Learning for a Heat Pump Thermostat . In IEEE International Conference on Automatic Computing: Feedback Computing , Vol. 16 . Kuo Shiuan Peng and Clayton T. Morrison. 2016. Model Predictive Prior Reinforcement Learning for a Heat Pump Thermostat. In IEEE International Conference on Automatic Computing: Feedback Computing, Vol. 16."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2971648.2971659"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2015.07.051"},{"key":"e_1_3_2_1_31_1","volume-title":"Barto","author":"Sutton Richard S.","year":"2017","unstructured":"Richard S. Sutton and Andrew G . Barto . 2017 . Reinforcement Learning : An Introduction (second edi ed.). MIT Press , Cambridge, MA, USA. Richard S. Sutton and Andrew G. Barto. 2017. Reinforcement Learning: An Introduction (second edi ed.). MIT Press, Cambridge, MA, USA."},{"key":"e_1_3_2_1_32_1","volume-title":"Retrieved","author":"Foundation The","year":"2018","unstructured":"The openHAB Foundation . 2018 . openHAB . Retrieved May 22, 2018 from https:\/\/www.openhab.org\/ The openHAB Foundation. 2018. openHAB. Retrieved May 22, 2018 from https:\/\/www.openhab.org\/"},{"key":"e_1_3_2_1_33_1","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the Gradient by a Running Average of Its Recent Magnitude","volume":"4","author":"Tieleman Tijmen","year":"2012","unstructured":"Tijmen Tieleman and Geoffrey Hinton . 2012 . Lecture 6.5-rmsprop: Divide the Gradient by a Running Average of Its Recent Magnitude . COURSERA: Neural Networks for Machine Learning 4 (2012), 26 -- 31 . Tijmen Tieleman and Geoffrey Hinton. 2012. Lecture 6.5-rmsprop: Divide the Gradient by a Running Average of Its Recent Magnitude. COURSERA: Neural Networks for Machine Learning 4 (2012), 26--31.","journal-title":"COURSERA: Neural Networks for Machine Learning"},{"key":"e_1_3_2_1_34_1","volume-title":"Retrieved","author":"U.S. Department of Energy.","year":"2015","unstructured":"U.S. Department of Energy. 2015 . EnergyPlus 8.3.0 . Retrieved January 18, 2018 from https:\/\/energyplus.net\/ U.S. Department of Energy. 2015. EnergyPlus 8.3.0. Retrieved January 18, 2018 from https:\/\/energyplus.net\/"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2014.01.016"},{"key":"e_1_3_2_1_36_1","volume-title":"A Long-Short Term Memory Recurrent Neural Network Based Reinforcement Learning Controller for Office Heating Ventilation and Air Conditioning Systems. Processes 5, 46","author":"Wang Yuan","year":"2017","unstructured":"Yuan Wang , Kirubakaran Velswamy , and Biao Huang . 2017. A Long-Short Term Memory Recurrent Neural Network Based Reinforcement Learning Controller for Office Heating Ventilation and Air Conditioning Systems. Processes 5, 46 ( 2017 ). Yuan Wang, Kirubakaran Velswamy, and Biao Huang. 2017. A Long-Short Term Memory Recurrent Neural Network Based Reinforcement Learning Controller for Office Heating Ventilation and Air Conditioning Systems. Processes 5, 46 (2017)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062224"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2015.07.050"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272036.3272037"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1080\/19401493.2014.891656"}],"event":{"name":"BuildSys '18: The 5th ACM International Conference on Systems for Built Environments","location":"Shenzen China","acronym":"BuildSys '18","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGCOMM ACM Special Interest Group on Data Communication","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGOPS ACM Special Interest Group on Operating Systems","SIGBED ACM Special Interest Group on Embedded Systems","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 5th Conference on Systems for Built Environments"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3276774.3276775","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3276774.3276775","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T19:03:40Z","timestamp":1750273420000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3276774.3276775"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,7]]},"references-count":40,"alternative-id":["10.1145\/3276774.3276775","10.1145\/3276774"],"URL":"https:\/\/doi.org\/10.1145\/3276774.3276775","relation":{},"subject":[],"published":{"date-parts":[[2018,11,7]]},"assertion":[{"value":"2018-11-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}