{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T22:53:12Z","timestamp":1781650392295,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T00:00:00Z","timestamp":1605657600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Department of Energy, US","award":["DE-EE0009150"],"award-info":[{"award-number":["DE-EE0009150"]}]},{"DOI":"10.13039\/501100004801","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1834701"],"award-info":[{"award-number":["1834701"]}],"id":[{"id":"10.13039\/501100004801","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,11,18]]},"DOI":"10.1145\/3408308.3427617","type":"proceedings-article","created":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T03:20:52Z","timestamp":1606101652000},"page":"230-239","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":47,"title":["One for Many"],"prefix":"10.1145","author":[{"given":"Shichao","family":"Xu","sequence":"first","affiliation":[{"name":"Northwestern University, Evanston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"O'Neill","sequence":"additional","affiliation":[{"name":"Texas A&M University College Station, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,11,18]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Ilge Akkaya Marcin Andrychowicz Maciek Chociej Mateusz Litwin Bob McGrew Arthur Petron Alex Paino Matthias Plappert Glenn Powell Raphael Ribas etal 2019. Solving rubik's cube with a robot hand. arXiv:1910.07113 (2019).  Ilge Akkaya Marcin Andrychowicz Maciek Chociej Mateusz Litwin Bob McGrew Arthur Petron Alex Paino Matthias Plappert Glenn Powell Raphael Ribas et al. 2019. Solving rubik's cube with a robot hand. arXiv:1910.07113 (2019)."},{"key":"e_1_3_2_1_2_1","volume-title":"A Reinforcement Learning Approach","author":"Barrett Enda","unstructured":"Enda Barrett and Stephen Linder . 2015. Autonomous HVAC Control , A Reinforcement Learning Approach . Springer . Enda Barrett and Stephen Linder. 2015. Autonomous HVAC Control, A Reinforcement Learning Approach. Springer."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2019.119866"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.segan.2016.02.002"},{"key":"e_1_3_2_1_5_1","volume-title":"Winkelmann","author":"Crawley Drury B.","year":"2000","unstructured":"Drury B. Crawley , Curtis O. Pedersen , Linda K. Lawrie , and Frederick C . Winkelmann . 2000 . EnergyPlus: Energy Simulation Program. ASHRAE 42 (2000). Drury B. Crawley, Curtis O. Pedersen, Linda K. Lawrie, and Frederick C. Winkelmann. 2000. EnergyPlus: Energy Simulation Program. ASHRAE 42 (2000)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"e_1_3_2_1_7_1","volume-title":"Using reinforcement learning to optimize occupant comfort and energy usage in HVAC systems. JAISE","author":"Fazenda Pedro","year":"2014","unstructured":"Pedro Fazenda , Kalyan Veeramachaneni , Pedro Lima , and Una-May O'Reilly . 2014. Using reinforcement learning to optimize occupant comfort and energy usage in HVAC systems. JAISE ( 2014 ), 675--690. Pedro Fazenda, Kalyan Veeramachaneni, Pedro Lima, and Una-May O'Reilly. 2014. Using reinforcement learning to optimize occupant comfort and energy usage in HVAC systems. JAISE (2014), 675--690."},{"key":"e_1_3_2_1_8_1","volume-title":"Energy-efficient thermal comfort control in smart buildings via deep reinforcement learning. arXiv preprint arXiv:1901.04693","author":"Gao Guanyu","year":"2019","unstructured":"Guanyu Gao , Jie Li , and Yonggang Wen . 2019. Energy-efficient thermal comfort control in smart buildings via deep reinforcement learning. arXiv preprint arXiv:1901.04693 ( 2019 ). Guanyu Gao, Jie Li, and Yonggang Wen. 2019. Energy-efficient thermal comfort control in smart buildings via deep reinforcement learning. arXiv preprint arXiv:1901.04693 (2019)."},{"key":"e_1_3_2_1_9_1","volume-title":"DeepComfort: Energy-Efficient Thermal Comfort Control in Buildings via Reinforcement Learning","author":"Gao Guanyu","year":"2020","unstructured":"Guanyu Gao , Jie Li , and Yonggang Wen . 2020. DeepComfort: Energy-Efficient Thermal Comfort Control in Buildings via Reinforcement Learning . IEEE Internet of Things Journal ( 2020 ). Guanyu Gao, Jie Li, and Yonggang Wen. 2020. DeepComfort: Energy-Efficient Thermal Comfort Control in Buildings via Reinforcement Learning. IEEE Internet of Things Journal (2020)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/3086952"},{"key":"e_1_3_2_1_11_1","volume-title":"Learning invariant feature spaces to transfer skills with reinforcement learning. ICLR","author":"Gupta Abhishek","year":"2017","unstructured":"Abhishek Gupta , Coline Devin , YuXuan Liu , Pieter Abbeel , and Sergey Levine . 2017. Learning invariant feature spaces to transfer skills with reinforcement learning. ICLR ( 2017 ). Abhishek Gupta, Coline Devin, YuXuan Liu, Pieter Abbeel, and Sergey Levine. 2017. Learning invariant feature spaces to transfer skills with reinforcement learning. ICLR (2017)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Todd Hester Matej Vecerik Olivier Pietquin Marc Lanctot Tom Schaul Bilal Piot Dan Horgan John Quan Andrew Sendonaris Ian Osband etal 2018. Deep q-learning from demonstrations. In AAAI.  Todd Hester Matej Vecerik Olivier Pietquin Marc Lanctot Tom Schaul Bilal Piot Dan Horgan John Quan Andrew Sendonaris Ian Osband et al. 2018. Deep q-learning from demonstrations. In AAAI.","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"e_1_3_2_1_14_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/sj.jea.7500165"},{"key":"e_1_3_2_1_16_1","volume-title":"IEEE International Conference on Automation Science and Engineering(CASE), 444--449","author":"Li B.","unstructured":"B. Li and L. Xia . 2015. A multi-grid reinforcement learning method for energy conservation and comfort of HVAC in buildings . IEEE International Conference on Automation Science and Engineering(CASE), 444--449 . B. Li and L. Xia. 2015. A multi-grid reinforcement learning method for energy conservation and comfort of HVAC in buildings. IEEE International Conference on Automation Science and Engineering(CASE), 444--449."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2927410"},{"key":"e_1_3_2_1_18_1","volume-title":"Transfer Learning Applied to Reinforcement Learning-Based HVAC Control. SN Computer Science 1","author":"Lissa Paulo","year":"2020","unstructured":"Paulo Lissa , Michael Schukat , and Enda Barrett . 2020. Transfer Learning Applied to Reinforcement Learning-Based HVAC Control. SN Computer Science 1 ( 2020 ). Paulo Lissa, Michael Schukat, and Enda Barrett. 2020. Transfer Learning Applied to Reinforcement Learning-Based HVAC Control. SN Computer Science 1 (2020)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2011.2124461"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1115\/DSCC2011-6078"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2014.03.057"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2014.6858875"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei A Rusu Joel Veness Marc G Bellemare Alex Graves Martin Riedmiller Andreas K Fidjeland Georg Ostrovski etal 2015. Human-level control through deep reinforcement learning. nature 518 7540 (2015) 529--533.  Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei A Rusu Joel Veness Marc G Bellemare Alex Graves Martin Riedmiller Andreas K Fidjeland Georg Ostrovski et al. 2015. Human-level control through deep reinforcement learning. nature 518 7540 (2015) 529--533.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP.2019.00060"},{"key":"e_1_3_2_1_25_1","volume-title":"REHVA World Congress CLIMA.","author":"Nikovski D","year":"2013","unstructured":"D Nikovski , J Xu , and M Nonaka . 2013 . A method for computing optimal set-point schedules for HVAC systems . In REHVA World Congress CLIMA. D Nikovski, J Xu, and M Nonaka. 2013. A method for computing optimal set-point schedules for HVAC systems. In REHVA World Congress CLIMA."},{"key":"e_1_3_2_1_26_1","unstructured":"U.S. Department of Energy. 2011. Buildings energy data book.  U.S. Department of Energy. 2011. Buildings energy data book."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2016.09.044"},{"key":"e_1_3_2_1_28_1","unstructured":"T. Wei S. Ren and Q. Zhu. 2019. Deep Reinforcement Learning for Joint Datacenter and HVAC Load Control in Distributed Mixed-Use Buildings. IEEE Transactions on Sustainable Computing (2019) 1--1.  T. Wei S. Ren and Q. Zhu. 2019. Deep Reinforcement Learning for Joint Datacenter and HVAC Load Control in Distributed Mixed-Use Buildings. IEEE Transactions on Sustainable Computing (2019) 1--1."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062224"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2015.2495244"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1080\/19401493.2010.518631"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Stephen Wilcox and William Marion. 2008. Users manual for TMY3 data sets. (2008).  Stephen Wilcox and William Marion. 2008. Users manual for TMY3 data sets. (2008).","DOI":"10.2172\/928611"},{"key":"e_1_3_2_1_33_1","volume-title":"Distributed Control of Multi-zone HVAC Systems Considering Indoor Air Quality. arXiv preprint arXiv:2003.08208","author":"Yang Yu","year":"2020","unstructured":"Yu Yang , Seshadhri Srinivasan , Guoqiang Hu , and Costas J Spanos . 2020. Distributed Control of Multi-zone HVAC Systems Considering Indoor Air Quality. arXiv preprint arXiv:2003.08208 ( 2020 ). Yu Yang, Seshadhri Srinivasan, Guoqiang Hu, and Costas J Spanos. 2020. Distributed Control of Multi-zone HVAC Systems Considering Indoor Air Quality. arXiv preprint arXiv:2003.08208 (2020)."},{"key":"e_1_3_2_1_34_1","volume-title":"Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildings","author":"Yu Liang","year":"2020","unstructured":"Liang Yu , Yi Sun , Zhanbo Xu , Chao Shen , Dong Yue , Tao Jiang , and Xiaohong Guan . 2020. Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildings . IEEE Transactions on Smart Grid ( 2020 ). Liang Yu, Yi Sun, Zhanbo Xu, Chao Shen, Dong Yue, Tao Jiang, and Xiaohong Guan. 2020. Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildings. IEEE Transactions on Smart Grid (2020)."},{"key":"e_1_3_2_1_35_1","volume-title":"2015 AAAI Fall Symposium Series.","author":"Zhan Yusen","year":"2015","unstructured":"Yusen Zhan and Mattew E Taylor . 2015 . Online transfer learning in reinforcement learning domains . In 2015 AAAI Fall Symposium Series. Yusen Zhan and Mattew E Taylor. 2015. Online transfer learning in reinforcement learning domains. In 2015 AAAI Fall Symposium Series."},{"key":"e_1_3_2_1_36_1","first-page":"22","article-title":"A deep reinforcement learning approach to using whole building energy model for hvac optimal control","volume":"3","author":"Zhang Zhiang","year":"2018","unstructured":"Zhiang Zhang , Adrian Chong , Yuqi Pan , Chenlu Zhang , Siliang Lu , and Khee Poh Lam . 2018 . A deep reinforcement learning approach to using whole building energy model for hvac optimal control . In BPAC and SimBuild , Vol. 3. 22 -- 23 . Zhiang Zhang, Adrian Chong, Yuqi Pan, Chenlu Zhang, Siliang Lu, and Khee Poh Lam. 2018. A deep reinforcement learning approach to using whole building energy model for hvac optimal control. In BPAC and SimBuild, Vol. 3. 22--23.","journal-title":"BPAC and SimBuild"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3276774.3276775"}],"event":{"name":"BuildSys '20: The 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","location":"Virtual Event Japan","acronym":"BuildSys '20","sponsor":["SIGEnergy ACM Special Interest Group on Energy Systems and Informatics"]},"container-title":["Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3408308.3427617","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3408308.3427617","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:39:02Z","timestamp":1750199942000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3408308.3427617"}},"subtitle":["Transfer Learning for Building HVAC Control"],"short-title":[],"issued":{"date-parts":[[2020,11,18]]},"references-count":37,"alternative-id":["10.1145\/3408308.3427617","10.1145\/3408308"],"URL":"https:\/\/doi.org\/10.1145\/3408308.3427617","relation":{},"subject":[],"published":{"date-parts":[[2020,11,18]]},"assertion":[{"value":"2020-11-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}