{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T11:53:20Z","timestamp":1781870000250,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":34,"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-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,22]]},"DOI":"10.1145\/3744256.3812588","type":"proceedings-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T11:01:41Z","timestamp":1781866901000},"page":"153-163","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["REAL: Real-world and Energy-efficient Adaptive Inverse Reinforcement Learning for Smart Buildings"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1893-5619","authenticated-orcid":false,"given":"Hamid","family":"Rajabi","sequence":"first","affiliation":[{"name":"Electrical Engineering and Computer Science, University of California, Merced, Merced, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4531-9704","authenticated-orcid":false,"given":"Alberto","family":"Cerpa","sequence":"additional","affiliation":[{"name":"Electrical Engineering and Computer Science, University of California, Merced, Merced, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"[n. d.]. EnergyPlus. https:\/\/energyplus.net\/."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Pieter Abbeel\u00a0et al. 2004. Apprenticeship learning via inverse reinforcement learning. ACM 21st International Conference on Machine Learning.","DOI":"10.1145\/1015330.1015430"},{"key":"e_1_3_3_2_4_2","volume-title":"2008 IEEE\/RSJ International Conference on Intelligent Robots and Systems","author":"al Pieter Abbeel\u00a0et","year":"2008","unstructured":"Pieter Abbeel\u00a0et al. 2008. Apprenticeship learning for motion planning with application to parking lot navigation. In 2008 IEEE\/RSJ International Conference on Intelligent Robots and Systems."},{"key":"e_1_3_3_2_5_2","unstructured":"ASHRAE. 2020. ANSI\/ASHRAE Standard 55-2020: Thermal Environmental Conditions for Human Occupancy."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360857"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3408308.3427986"},{"key":"e_1_3_3_2_8_2","unstructured":"Xianzhong Ding\u00a0et al. 2025. Multi-Zone HVAC Control With Model-Based Deep Reinforcement Learning. IEEE Transactions on Automation Science and Engineering (2025)."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Behrang\u00a0Alimohammadisagvand et al. 2018. Comparison of four rule-based demand response control algorithms in an electrically and heat pump-heated residential building. Applied Energy 209 (2018).","DOI":"10.1016\/j.apenergy.2017.10.088"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"C.\u00a0Eastman et al. 2009. Automatic rule-based checking of building designs. Automation in Construction 18 8 (2009).","DOI":"10.1016\/j.autcon.2009.07.002"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"G.T.\u00a0Costanzo et al. 2016. Experimental analysis of data-driven control for a building heating system. Sustainable Energy Grids and Networks 6 (2016).","DOI":"10.1016\/j.segan.2016.02.002"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Jyri\u00a0Salpakari et al. 2016. Optimal and rule-based control strategies for energy flexibility in buildings with PV. Applied Energy 161 (2016).","DOI":"10.1016\/j.apenergy.2015.10.036"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Kuldeep\u00a0Kurte et al. 2021. Comparative analysis of model-free and model-based HVAC control for residential demand response. ACM BuildSys 2021.","DOI":"10.1145\/3486611.3488727"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Sourav\u00a0Dey et al. 2023. Inverse reinforcement learning control for building energy management. Energy and Buildings 286 (2023).","DOI":"10.1016\/j.enbuild.2023.112941"},{"key":"e_1_3_3_2_15_2","unstructured":"Tuomas\u00a0Haarnoja et al. 2017. Reinforcement Learning with Deep Energy-Based Policies. arxiv:https:\/\/arXiv.org\/abs\/1702.08165"},{"key":"e_1_3_3_2_16_2","unstructured":"Tuomas\u00a0Haarnoja et al. 2018. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. arXiv:https:\/\/arXiv.org\/abs\/1801.01290"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Zhe\u00a0Wang et al. 2020. Reinforcement learning for building controls: The opportunities and challenges. Applied Energy 269 (2020).","DOI":"10.1016\/j.apenergy.2020.115036"},{"key":"e_1_3_3_2_18_2","unstructured":"Zhengbo\u00a0Zou et al. 2020. Towards optimal control of air handling units using deep reinforcement learning and recurrent neural network. Building and Environment (2020)."},{"key":"e_1_3_3_2_19_2","unstructured":"Povl\u00a0O. Fanger. 1970. Thermal comfort. Analysis and applications in environmental engineering. Copenhagen: Danish Technical Press. (1970)."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Alejandro Gonz\u00e1lez-Torres\u00a0et al. 2022. A review on buildings energy information: Trends end-uses fuels and drivers. Energy Reports 8 (2022) 12347\u201312361.","DOI":"10.1016\/j.egyr.2021.11.280"},{"key":"e_1_3_3_2_21_2","unstructured":"International Energy Agency. 2023. Buildings \u2013 Analysis and Data. https:\/\/www.iea.org\/energy-system\/buildings Accessed: 2025-09-19."},{"key":"e_1_3_3_2_22_2","unstructured":"Hsin-Yu Liu Bharathan Balaji Rajesh Gupta and Dezhi Hong. 2023. Rule-based Policy Regularization for Reinforcement Learning-based Building Control."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Hamid Rajabi. 2022. CRAWDAD ucmerced\/modes. 10.15783\/08kw-7n74","DOI":"10.15783\/08kw-7n74"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Hamid Rajabi. 2023. TODOS Dataset: Thermal Array-Based Occupancy Estimation for Intelligent Buildings. 10.21227\/y3dv-8b19","DOI":"10.21227\/y3dv-8b19"},{"key":"e_1_3_3_2_25_2","unstructured":"Hamid Rajabi\u00a0et al. 2022. MODES: Multi-sensor occupancy data-driven estimation system for smart buildings. ACM e-Energy 2022."},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Hamid Rajabi\u00a0et al. 2023. TODOS: Thermal sensOr Data-driven Occupancy Estimation System for Smart Buildings. ACM BuildSys 2023.","DOI":"10.1145\/3600100.3623753"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Nathan\u00a0D. Ratliff\u00a0et al. 2006. Maximum margin planning. 23rd ACM International Conference on Machine Learning.","DOI":"10.1145\/1143844.1143936"},{"key":"e_1_3_3_2_28_2","unstructured":"REN21. 2023. Buildings in Focus. Global Status Report for Buildings and Construction 2023."},{"key":"e_1_3_3_2_29_2","unstructured":"John Schulman\u00a0et al. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1707.06347 (2017)."},{"key":"e_1_3_3_2_30_2","volume-title":"2018 IEEE International Conference on Services Computing","author":"al Nouredine Tamani\u00a0et","year":"2018","unstructured":"Nouredine Tamani\u00a0et al. 2018. Rule-Based Model for Smart Building Supervision and Management. In 2018 IEEE International Conference on Services Computing."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Jos\u00e9 V\u00e1zquez-Canteli\u00a0et al. 2019. Reinforcement learning for demand response: A review of algorithms and modeling techniques. Applied energy 235 (2019).","DOI":"10.1016\/j.apenergy.2018.11.002"},{"key":"e_1_3_3_2_32_2","volume-title":"ACM 54th Annual Design Automation Conference 2017","author":"al Tianshu Wei\u00a0et","year":"2017","unstructured":"Tianshu Wei\u00a0et al. 2017. Deep Reinforcement Learning for Building HVAC Control. In ACM 54th Annual Design Automation Conference 2017."},{"key":"e_1_3_3_2_33_2","first-page":"265","volume-title":"19th ACM\/IEEE IPSN","author":"al Daniel\u00a0A Winkler\u00a0et","year":"2020","unstructured":"Daniel\u00a0A Winkler\u00a0et al. 2020. OFFICE: Optimization Framework For Improved Comfort & Efficiency. In 19th ACM\/IEEE IPSN. ACM, 265\u2013276."},{"key":"e_1_3_3_2_34_2","volume-title":"Building Performance Analysis Conference and SimBuild","author":"al Zhiang Zhang\u00a0et","year":"2018","unstructured":"Zhiang Zhang\u00a0et al. 2018. A deep reinforcement learning approach to using whole building energy model for hvac optimal control. In Building Performance Analysis Conference and SimBuild."},{"key":"e_1_3_3_2_35_2","first-page":"1433","volume-title":"Proc. AAAI","author":"Ziebart Brian\u00a0D.","year":"2008","unstructured":"Brian\u00a0D. Ziebart, Andrew Maas, J.\u00a0Andrew Bagnell, and Anind\u00a0K. Dey. 2008. Maximum Entropy Inverse Reinforcement Learning. In Proc. AAAI. 1433\u20131438."}],"event":{"name":"BuildSys '26: The 13th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","location":"Banff Canada","acronym":"BuildSys '26","sponsor":["SIGEnergy ACM Special Interest Group on Energy Systems and Informatics"]},"container-title":["Proceedings of the 13th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation"],"original-title":[],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T11:28:44Z","timestamp":1781868524000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3744256.3812588"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":34,"alternative-id":["10.1145\/3744256.3812588","10.1145\/3744256"],"URL":"https:\/\/doi.org\/10.1145\/3744256.3812588","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"}}]}}