{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T11:52:36Z","timestamp":1781610756882,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100009318","name":"Helmholtz Association","doi-asserted-by":"publisher","award":["VH-NG-1727"],"award-info":[{"award-number":["VH-NG-1727"]}],"id":[{"id":"10.13039\/501100009318","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009318","name":"Program-Oriented Funding POF IV in the program Energy Systems Design","doi-asserted-by":"publisher","award":["Project number 37.12.01"],"award-info":[{"award-number":["Project number 37.12.01"]}],"id":[{"id":"10.13039\/501100009318","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009318","name":"Ministry of Science, Research and the Arts Baden-W\u00fcrttemberg (MWK)","doi-asserted-by":"publisher","award":["bwHPC (bwUniCluster 3.0)"],"award-info":[{"award-number":["bwHPC (bwUniCluster 3.0)"]}],"id":[{"id":"10.13039\/501100009318","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,22]]},"DOI":"10.1145\/3744255.3811723","type":"proceedings-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T10:13:49Z","timestamp":1781604829000},"page":"42-54","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Trans-SAC: Robust and Transferable Maximum Entropy Reinforcement Learning for Heat Pump Control"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1958-6094","authenticated-orcid":false,"given":"Qiong","family":"Huang","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology, Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7402-0770","authenticated-orcid":false,"given":"Adrian Till","family":"Assmuth","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology, Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3473-5545","authenticated-orcid":false,"given":"Felix","family":"Langner","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology, Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3572-9083","authenticated-orcid":false,"given":"Veit","family":"Hagenmeyer","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology, Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1607-9748","authenticated-orcid":false,"given":"Benjamin","family":"Sch\u00e4fer","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology, Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","unstructured":"Hylke\u00a0E Beck Niklaus\u00a0E Zimmermann Tim\u00a0R McVicar Noemi Vergopolan Alexis Berg and Eric\u00a0F Wood. 2018. Present and future K\u00f6ppen-Geiger climate classification maps at 1-km resolution. Scientific data 5 1 (2018) 1\u201312. 10.1038\/sdata.2018.214","DOI":"10.1038\/sdata.2018.214"},{"key":"e_1_3_3_2_3_2","unstructured":"Bundesnetzagentur. 2025. SMARD. https:\/\/www.smard.de\/home\/downloadcenter\/download-marktdaten\/."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Davide Coraci Silvio Brandi Tianzhen Hong and Alfonso Capozzoli. 2023. Online transfer learning strategy for enhancing the scalability and deployment of deep reinforcement learning control in smart buildings. Applied Energy 333 (2023) 120598. 10.1016\/j.apenergy.2022.120598","DOI":"10.1016\/j.apenergy.2022.120598"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISGTEurope64741.2025.11305332"},{"key":"e_1_3_3_2_6_2","unstructured":"Joint Research\u00a0Centre European\u00a0Commission. 2025. Photovolatic Geographical Information System. https:\/\/re.jrc.ec.europa.eu\/pvg_tools\/de\/tools.html."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"David Fischer and Hatef Madani. 2017. On heat pumps in smart grids: A review. Renewable and Sustainable Energy Reviews 70 (2017) 342\u2013357. 10.1016\/j.rser.2016.11.182","DOI":"10.1016\/j.rser.2016.11.182"},{"key":"e_1_3_3_2_8_2","first-page":"1861","volume-title":"International conference on machine learning","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning. PMLR, Stockholm, Sweden, 1861\u20131870."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","unstructured":"Qiong Huang Adrian\u00a0Till Assmuth Felix Langner Benjamin Sch\u00e4fer and Veit Hagenmeyer. 2026. Deep Reinforcement Learning for Price-Aware Building Heating Control. KI - K\u00fcnstliche Intelligenz (2026) 1\u20139. 10.1007\/s13218-026-00908-0","DOI":"10.1007\/s13218-026-00908-0"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Kevlyn Kadamala Des Chambers and Enda Barrett. 2024. Enhancing HVAC control systems through transfer learning with deep reinforcement learning agents. Smart Energy 13 (2024) 100131. 10.1016\/j.segy.2024.100131","DOI":"10.1016\/j.segy.2024.100131"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Michaela Killian and Martin Kozek. 2016. Ten questions concerning model predictive control for energy efficient buildings. Building and Environment 105 (2016) 403\u2013412. 10.1016\/j.buildenv.2016.05.034","DOI":"10.1016\/j.buildenv.2016.05.034"},{"key":"e_1_3_3_2_12_2","volume-title":"4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings","author":"Lillicrap Timothy\u00a0P","year":"2016","unstructured":"Timothy\u00a0P Lillicrap, Jonathan\u00a0J Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. 2016. Continuous control with deep reinforcement learning. In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). Open-access, Puerto Rico. http:\/\/arxiv.org\/abs\/1509.02971"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"Paulo Lissa Michael Schukat Marcus Keane and Enda Barrett. 2021. Transfer learning applied to DRL-Based heat pump control to leverage microgrid energy efficiency. Smart Energy 3 (2021) 100044. 10.1016\/j.segy.2021.100044","DOI":"10.1016\/j.segy.2021.100044"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei\u00a0A Rusu Joel Veness Marc\u00a0G Bellemare Alex Graves Martin Riedmiller Andreas\u00a0K Fidjeland Georg Ostrovski et\u00a0al. 2015. Human-level control through deep reinforcement learning. nature 518 7540 (2015) 529\u2013533. 10.1038\/nature14236","DOI":"10.1038\/nature14236"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Zoltan Nagy Gregor Henze Sourav Dey Javier Arroyo Lieve Helsen Xiangyu Zhang Bingqing Chen Kadir Amasyali Kuldeep Kurte Ahmed Zamzam et\u00a0al. 2023. Ten questions concerning reinforcement learning for building energy management. Building and Environment 241 (2023) 110435. 10.1016\/j.buildenv.2023.110435","DOI":"10.1016\/j.buildenv.2023.110435"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Frauke Oldewurtel Alessandra Parisio Colin\u00a0N Jones Dimitrios Gyalistras Markus Gwerder Vanessa Stauch Beat Lehmann and Manfred Morari. 2012. Use of model predictive control and weather forecasts for energy efficient building climate control. Energy and buildings 45 (2012) 15\u201327. 10.1016\/j.enbuild.2011.09.022","DOI":"10.1016\/j.enbuild.2011.09.022"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ENERGYCON.2018.8398832"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"Giuseppe Pinto Zhe Wang Abhishek Roy Tianzhen Hong and Alfonso Capozzoli. 2022. Transfer learning for smart buildings: A critical review of algorithms applications and future perspectives. Advances in Applied Energy 5 (2022) 100084. 10.1016\/j.adapen.2022.100084","DOI":"10.1016\/j.adapen.2022.100084"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3679240.3734589"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-37717-4_29"},{"key":"e_1_3_3_2_21_2","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1707.06347 (2017)."},{"key":"e_1_3_3_2_22_2","unstructured":"Matthew\u00a0E. Taylor and Peter Stone. 2009. Transfer Learning for Reinforcement Learning Domains: A Survey. J. Mach. Learn. Res. 10 (Dec. 2009) 1633\u20131685."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Tsuyoshi Ueno and Alan Meier. 2020. A method to generate heating and cooling schedules based on data from connected thermostats. Energy and Buildings 228 (2020) 110423. 10.1016\/j.enbuild.2020.110423","DOI":"10.1016\/j.enbuild.2020.110423"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Charalampos Vallianos Jos\u00e9 Candanedo and Andreas Athienitis. 2024. Thermal modeling for control applications of 60 000 homes in North America using smart thermostat data. Energy and Buildings 303 (2024) 113811. 10.1016\/j.enbuild.2023.113811","DOI":"10.1016\/j.enbuild.2023.113811"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","unstructured":"Jos\u00e9\u00a0R V\u00e1zquez-Canteli and Zolt\u00e1n Nagy. 2019. Reinforcement learning for demand response: A review of algorithms and modeling techniques. Applied energy 235 (2019) 1072\u20131089. 10.1016\/j.apenergy.2018.11.002","DOI":"10.1016\/j.apenergy.2018.11.002"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","unstructured":"Zhe Wang and Tianzhen Hong. 2020. Reinforcement learning for building controls: The opportunities and challenges. Applied Energy 269 (2020) 115036. 10.1016\/j.apenergy.2020.115036","DOI":"10.1016\/j.apenergy.2020.115036"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3408308.3427617"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969197"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","unstructured":"Liang Yu Shuqi Qin Meng Zhang Chao Shen Tao Jiang and Xiaohong Guan. 2021. A review of deep reinforcement learning for smart building energy management. IEEE Internet of Things Journal 8 15 (2021) 12046\u201312063. 10.1109\/JIOT.2021.3078462","DOI":"10.1109\/JIOT.2021.3078462"}],"event":{"name":"E-Energy '26: The 17th ACM International Conference on Future and Sustainable Energy Systems","location":"Banff , Alberta , Canada","acronym":"E-Energy '26","sponsor":["SIGENERGY ACM Special Interest Group on Energy Systems and Informatics"]},"container-title":["Proceedings of the 17th ACM International Conference on Future and Sustainable Energy Systems"],"original-title":[],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T11:07:41Z","timestamp":1781608061000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3744255.3811723"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":28,"alternative-id":["10.1145\/3744255.3811723","10.1145\/3744255"],"URL":"https:\/\/doi.org\/10.1145\/3744255.3811723","relation":{},"subject":[],"published":{"date-parts":[[2026,6,22]]},"assertion":[{"value":"2026-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}