{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T17:51:38Z","timestamp":1786557098647,"version":"3.56.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T00:00:00Z","timestamp":1587340800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T00:00:00Z","timestamp":1587340800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1007\/s42979-020-00146-7","type":"journal-article","created":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T16:04:18Z","timestamp":1587398658000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["Transfer Learning Applied to Reinforcement Learning-Based HVAC Control"],"prefix":"10.1007","volume":"1","author":[{"given":"Paulo","family":"Lissa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Schukat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enda","family":"Barrett","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,4,20]]},"reference":[{"key":"146_CR1","doi-asserted-by":"publisher","unstructured":"Barrett E, Linder SP. Autonomous HVAC control. A reinforcement learning approach. 2015. https:\/\/doi.org\/10.1007\/978-3-319-23461-8-1.","DOI":"10.1007\/978-3-319-23461-8-1"},{"key":"146_CR2","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1016\/j.conbuildmat.2017.09.110","volume":"157","author":"Kasthurirangan Gopalakrishnan","year":"2017","unstructured":"Gopalakrishnan Kasthurirangan, Khaitan Siddhartha K, Choudhary Alok, Agrawal Ankit. Deep Convolutional Neural Networks with transfer learning for computer vision-based data-driven pavement distress detection. Constr Build Mater. 2017;157:322\u201330.","journal-title":"Constr Build Mater"},{"key":"146_CR3","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","volume":"35","author":"Hoo-Chang Shin","year":"2016","unstructured":"Shin Hoo-Chang, Roth Holger, Gao Mingchen, Le Lu, Ziyue Xu, Nogues Isabella, Yao Jianhua, Mollura Daniel J, Summers Ronald M. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging. 2016;35:1285\u201398.","journal-title":"IEEE Trans Med Imaging"},{"key":"146_CR4","first-page":"2200","volume":"2013","author":"Mingsheng Long","year":"2013","unstructured":"Long Mingsheng, Wang Jianmin, Ding Guiguang, Sun Jia-Guang, Philip SYu. Transfer feature learning with joint distribution adaptation. IEEE Int Conf Comput Vis. 2013;2013:2200\u20137.","journal-title":"IEEE Int Conf Comput Vis"},{"key":"146_CR5","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.artint.2015.05.008","volume":"226","author":"Reinaldo AC Bianchi","year":"2015","unstructured":"Bianchi Reinaldo AC, Celiberto Luiz A, Santos Paulo E, Matsuura Jackson P, Lopez Ramon, de Mantaras Ramon Lopez. Transferring knowledge as heuristics in reinforcement learning: a case-based approach. Artif Intell. 2015;226:102\u201321.","journal-title":"Artif Intell"},{"key":"146_CR6","unstructured":"Chen Tessler, Shahar Givony, Tom Zahavy, Daniel J. Mankowitz, and Shie Mannor. A deep hierarchical approach to lifelong learning in minecraft. 2017. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI17). AAAI Press, 1553\u20131561."},{"key":"146_CR7","unstructured":"Chaplot, D. S., Lample, G., Sathyendra, K. M., & Salakhutdinov, R. Transfer deep reinforcement learning in 3d environments: An empirical study. 2016. In NIPS Deep Reinforcemente Leaning Workshop."},{"key":"146_CR8","unstructured":"Teh, Y., Bapst, V., Czarnecki, W. M., Quan, J., Kirkpatrick, J., Hadsell, R., Heess, N. & Pascanu, R. Distral: Robust multitask reinforcement learning. 2017. In Advances in Neural Information Processing Systems (pp. 4496-4506)."},{"key":"146_CR9","unstructured":"ASHRAE Handbook 2016: HVAC systems and equipment: SI Edition. ASHRAE, 2016."},{"key":"146_CR10","doi-asserted-by":"publisher","first-page":"1072","DOI":"10.1016\/j.apenergy.2018.11.002","volume":"235","author":"Jos\u00e9 R V\u00e1zquez-Canteli","year":"2019","unstructured":"V\u00e1zquez-Canteli Jos\u00e9 R, Nagy Zolt\u00e1n. Reinforcement learning for demand response: a review of algorithms and modeling techniques. Appl Energy. 2019;235:1072\u201389.","journal-title":"Appl Energy"},{"key":"146_CR11","doi-asserted-by":"crossref","unstructured":"Grzes M, Kudenko D. Learning shaping rewards in model-based reinforcement learning. In: Proceedings of AAMAS 2009 Workshop on Adaptive Learning Agents, vol. 115. 2009.","DOI":"10.1007\/978-3-642-03603-3_2"},{"key":"146_CR12","doi-asserted-by":"crossref","unstructured":"Wei T, Wang Y, Zhu Q. Deep reinforcement learning for building HVAC control. In: 2017 54th ACM\/EDAC\/IEEE Design Automation Conference (DAC). Austin; 2017. p. 1\u20136.","DOI":"10.1145\/3061639.3062224"},{"key":"146_CR13","unstructured":"Adam N, Hussain K, Farah C, Johan D. Deep reinforcement learning for optimal control of space heating. 2018. ArXiv e-prints (2018). arXiv:1805.03777 [stat.AP]"},{"key":"146_CR14","doi-asserted-by":"publisher","unstructured":"Wang Y, Velswamy K, Huang B. A long-short term memory recurrent neural network based reinforcement learning controller for office heating ventilation and air conditioning systems. Processes. 2017. https:\/\/doi.org\/10.3390\/pr5030046.","DOI":"10.3390\/pr5030046"},{"key":"146_CR15","unstructured":"Gao, Guanyu; LI, Jie; Wen, Yonggang. Energy-efficient thermal comfort control in smart buildings via deep reinforcement learning. 2019. arXiv preprint arXiv:1901.04693."},{"issue":"1","key":"146_CR16","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1191\/0143624403bt059oa","volume":"24","author":"A Shepherd","year":"2003","unstructured":"Shepherd A, Batty W. Fuzzy control strategies to provide cost and energy efficient high quality indoor environments in buildings with high occupant densities. Build Serv Eng Res Technol. 2003;24(1):35\u201345.","journal-title":"Build Serv Eng Res Technol"},{"issue":"2","key":"146_CR17","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.enbuild.2003.10.004","volume":"36","author":"F Calvino","year":"2004","unstructured":"Calvino F, La Gennusa M, Rizzo G, Scaccianoce G. The control of indoor thermal comfort conditions: introducing a fuzzy adaptive controller. Energy Build. 2004;36(2):97\u2013102.","journal-title":"Energy Build"},{"key":"146_CR18","volume-title":"Design and management for energy-efficient cyber-physical systems","author":"T Wei","year":"2018","unstructured":"Wei T. Design and management for energy-efficient cyber-physical systems. Riverside: UC; 2018."},{"key":"146_CR19","first-page":"1633","volume":"10","author":"Matthew E Taylor","year":"2009","unstructured":"Taylor Matthew E, Stone Peter. Transfer learning for reinforcement learning domains: a survey. J Mach Learn Res. 2009;10:1633\u201385.","journal-title":"J Mach Learn Res"},{"key":"146_CR20","unstructured":"Barreto A, Munos R, Schaul T, Silver D. Successor features for transfer in reinforcement learning. 2016. arXiv preprint arXiv:1606.05312."},{"key":"146_CR21","doi-asserted-by":"crossref","unstructured":"Killian, T., Konidaris, G., & Doshi-Velez, F. Transfer learning across patient variations with hidden parameter Markov decision processes. 2016. arXiv preprint arXiv:1612.00475.","DOI":"10.1609\/aaai.v31i1.11065"},{"key":"146_CR22","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1016\/j.enbuild.2016.01.030","volume":"116","author":"Elena Mocanu","year":"2016","unstructured":"Mocanu Elena, Nguyen Phuong, Wil L Kling, Gibescu Madeleine. Unsupervised energy prediction in a Smart Grid context using reinforcement cross-building transfer learning. Energy Build. 2016;116:646\u201355. https:\/\/doi.org\/10.1016\/j.enbuild.2016.01.030.","journal-title":"Energy Build"},{"key":"146_CR23","volume-title":"Automated planning: theory & practice","author":"D Nau","year":"2004","unstructured":"Nau D, Ghallab M, Traverso P. Automated planning: theory & practice. San Francisco: Morgan Kaufmann Publishers Inc; 2004."},{"key":"146_CR24","unstructured":"Watkins C. Learning from delayed rewards, Ph.D. dissertation, University of Cambridge, England. 1989."},{"key":"146_CR25","unstructured":"Strens, Malcolm. A Bayesian framework for reinforcement learning. 2000. ICML 2000. p. 943-950."},{"key":"146_CR26","unstructured":"ANSI\/ASHRAE Standard 55-2013: Thermal environmental conditions for human occupancy ASHRAE standard, ISSN 1041-2336."},{"key":"146_CR27","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/j.enbuild.2018.03.051","volume":"169","author":"Yujiao Chen","year":"2018","unstructured":"Chen Yujiao, Norford Leslie K, Samuelson Holly W, Malkawi Ali. Optimal control of HVAC and window systems for natural ventilation through reinforcement learning. Energy Build. 2018;169:195\u2013205 ISSN 0378-7788.","journal-title":"Energy Build"},{"key":"146_CR28","unstructured":"Weatherbit.io. https:\/\/www.weatherbit.io\/. Accessed 01 Nov 2019."}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-020-00146-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-020-00146-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-020-00146-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T20:46:55Z","timestamp":1666385215000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-020-00146-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,20]]},"references-count":28,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,5]]}},"alternative-id":["146"],"URL":"https:\/\/doi.org\/10.1007\/s42979-020-00146-7","relation":{},"ISSN":["2662-995X","2661-8907"],"issn-type":[{"value":"2662-995X","type":"print"},{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4,20]]},"assertion":[{"value":"31 January 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 April 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with Ethical Standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"127"}}