{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T20:15:03Z","timestamp":1777407303639,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,6,18]],"date-time":"2017-06-18T00:00:00Z","timestamp":1497744000000},"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":[[2017,6,18]]},"DOI":"10.1145\/3061639.3062224","type":"proceedings-article","created":{"date-parts":[[2017,6,13]],"date-time":"2017-06-13T12:18:42Z","timestamp":1497356322000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":328,"title":["Deep Reinforcement Learning for Building HVAC Control"],"prefix":"10.1145","author":[{"given":"Tianshu","family":"Wei","sequence":"first","affiliation":[{"name":"University of California, Riverside"}]},{"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Syracuse University"}]},{"given":"Qi","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of California, Riverside"}]}],"member":"320","published-online":{"date-parts":[[2017,6,18]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23461-8_1"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"e_1_3_2_1_3_1","volume-title":"Experimental analysis of data-driven control for a building heating system. CoRR, abs\/1507.03638","author":"Costanzo G. T.","year":"2015","unstructured":"G. T. Costanzo and Experimental analysis of data-driven control for a building heating system. CoRR, abs\/1507.03638 , 2015 . G. T. Costanzo and et al. Experimental analysis of data-driven control for a building heating system. CoRR, abs\/1507.03638, 2015."},{"key":"e_1_3_2_1_4_1","unstructured":"EnergyPlus. https:\/\/energyplus.net\/.  EnergyPlus. https:\/\/energyplus.net\/."},{"key":"e_1_3_2_1_5_1","volume-title":"Journal of Machine Learning Research","author":"Ernst D.","year":"2005","unstructured":"D. Ernst and et al. Tree-based batch mode reinforcement learning . Journal of Machine Learning Research , 2005 . D. Ernst and et al. Tree-based batch mode reinforcement learning. Journal of Machine Learning Research, 2005."},{"key":"e_1_3_2_1_6_1","first-page":"675","volume-title":"Journal of Ambient Intelligence and Smart Environments","author":"Fazenda P.","year":"2014","unstructured":"P. Fazenda and et al. Using reinforcement learning to optimize occupant comfort and energy usage in hvac systems . Journal of Ambient Intelligence and Smart Environments , pages 675 -- 690 , 2014 . P. Fazenda and et al. Using reinforcement learning to optimize occupant comfort and energy usage in hvac systems. Journal of Ambient Intelligence and Smart Environments, pages 675--690, 2014."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_1_8_1","unstructured":"G. Hinton N. Srivastava and K. Swersky. Lecture 6a overview of mini---batch gradient descent. http:\/\/www.es.toronto.edu\/~tijmen\/csc321\/slides\/lecture_slides_lec6.pdf.  G. Hinton N. Srivastava and K. Swersky. Lecture 6a overview of mini---batch gradient descent. http:\/\/www.es.toronto.edu\/~tijmen\/csc321\/slides\/lecture_slides_lec6.pdf."},{"key":"e_1_3_2_1_9_1","first-page":"444","volume-title":"A multi-grid reinforcement learning method for energy conservation and comfort of HVAC in buildings","author":"Li B.","year":"2015","unstructured":"B. Li and L. Xia . A multi-grid reinforcement learning method for energy conservation and comfort of HVAC in buildings . pages 444 -- 449 , 2015 . B. Li and L. Xia. A multi-grid reinforcement learning method for energy conservation and comfort of HVAC in buildings. pages 444--449, 2015."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2011.2124461"},{"key":"e_1_3_2_1_11_1","volume-title":"DSCC","author":"Maasoumy M.","year":"2011","unstructured":"M. Maasoumy and et al. Model-based hierarchical optimal control design for HVAC systems . DSCC , 2011 . M. Maasoumy and et al. Model-based hierarchical optimal control design for HVAC systems. DSCC, 2011."},{"key":"e_1_3_2_1_12_1","volume-title":"Human-level control through deep reinforcement learning. Nature 518.7540","author":"Mnih V.","year":"2015","unstructured":"V. Mnih and Human-level control through deep reinforcement learning. Nature 518.7540 , 2015 . V. Mnih and et al. Human-level control through deep reinforcement learning. Nature 518.7540, 2015."},{"key":"e_1_3_2_1_13_1","unstructured":"National Solar Radiation Data Base. http:\/\/rredc.nrel.gov.  National Solar Radiation Data Base. http:\/\/rredc.nrel.gov."},{"key":"e_1_3_2_1_14_1","volume-title":"REHVA World Congress CLIMA","author":"Nikovski D.","year":"2013","unstructured":"D. Nikovski , J. Xu , and M. Nonaka . A method for computing optimal set-point schedules for HVAC systems . REHVA World Congress CLIMA , 2013 . D. Nikovski, J. Xu, and M. Nonaka. A method for computing optimal set-point schedules for HVAC systems. REHVA World Congress CLIMA, 2013."},{"key":"e_1_3_2_1_15_1","volume-title":"ACC","author":"Oldewurtel F.","year":"2010","unstructured":"F. Oldewurtel and et al. Energy efficient building climate control using stochastic model predictive control and weather predictions . ACC , 2010 . F. Oldewurtel and et al. Energy efficient building climate control using stochastic model predictive control and weather predictions. ACC, 2010."},{"key":"e_1_3_2_1_16_1","volume-title":"Journal of Building Performance Simulation","author":"Olivieri S. J.","year":"2014","unstructured":"S. J. Olivieri and et al. Evaluation of commercial building demand response potential using optimal short-term curtailment of heating, ventilation, and air-conditioning loads . Journal of Building Performance Simulation , 2014 . S. J. Olivieri and et al. Evaluation of commercial building demand response potential using optimal short-term curtailment of heating, ventilation, and air-conditioning loads. Journal of Building Performance Simulation, 2014."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017928328829"},{"key":"e_1_3_2_1_18_1","volume-title":"Neural Fitted Q Iteration -- First Experiences with a Data Efficient Neural Reinforcement Learning Method","author":"Riedmiller M.","year":"2005","unstructured":"M. Riedmiller . Neural Fitted Q Iteration -- First Experiences with a Data Efficient Neural Reinforcement Learning Method . Springer , 2005 . M. Riedmiller. Neural Fitted Q Iteration -- First Experiences with a Data Efficient Neural Reinforcement Learning Method. Springer, 2005."},{"key":"e_1_3_2_1_19_1","volume-title":"Mastering the game of go with deep neural networks and tree search. Nature, 529(7587)","author":"Silver D.","year":"2016","unstructured":"D. Silver and Mastering the game of go with deep neural networks and tree search. Nature, 529(7587) , 2016 . D. Silver and et al. Mastering the game of go with deep neural networks and tree search. Nature, 529(7587), 2016."},{"key":"e_1_3_2_1_20_1","unstructured":"SCE. https:\/\/www.sce.com\/NR\/sc3\/tm2\/pdf\/CE281.pdf.  SCE. https:\/\/www.sce.com\/NR\/sc3\/tm2\/pdf\/CE281.pdf."},{"key":"e_1_3_2_1_21_1","volume-title":"Standard 55-2004-thermal environmental conditions for human occupancy","author":"Standard A.","year":"2004","unstructured":"A. Standard . Standard 55-2004-thermal environmental conditions for human occupancy . ASHRAE Inc ., 2004 . A. Standard. Standard 55-2004-thermal environmental conditions for human occupancy. ASHRAE Inc., 2004."},{"key":"e_1_3_2_1_22_1","volume-title":"AAMAS","author":"Urieli D.","year":"2013","unstructured":"D. Urieli and P. Stone . A learning agent for heat-pump thermostat control . AAMAS , 2013 . D. Urieli and P. Stone. A learning agent for heat-pump thermostat control. AAMAS, 2013."},{"key":"e_1_3_2_1_23_1","unstructured":"U.S. DoE. Buildings energy data book.  U.S. DoE. Buildings energy data book."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/2691365.2691405"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1080\/19401493.2010.518631"},{"key":"e_1_3_2_1_27_1","volume-title":"Applied Energy","author":"Yang L.","year":"2015","unstructured":"L. Yang and et al. Reinforcement learning for optimal control of low exergy buildings . Applied Energy , 2015 . L. Yang and et al. Reinforcement learning for optimal control of low exergy buildings. Applied Energy, 2015."}],"event":{"name":"DAC '17: The 54th Annual Design Automation Conference 2017","location":"Austin TX USA","acronym":"DAC '17","sponsor":["EDAC Electronic Design Automation Consortium","SIGDA ACM Special Interest Group on Design Automation","IEEE-CEDA","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 54th Annual Design Automation Conference 2017"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3061639.3062224","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3061639.3062224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:36:34Z","timestamp":1750217794000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3061639.3062224"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6,18]]},"references-count":27,"alternative-id":["10.1145\/3061639.3062224","10.1145\/3061639"],"URL":"https:\/\/doi.org\/10.1145\/3061639.3062224","relation":{},"subject":[],"published":{"date-parts":[[2017,6,18]]},"assertion":[{"value":"2017-06-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}