{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T12:32:47Z","timestamp":1762864367291,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","funder":[{"name":"Wilton E. Scott Institute for Energy Innovation"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,19]]},"DOI":"10.1145\/3736425.3770113","type":"proceedings-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T12:21:55Z","timestamp":1762863715000},"page":"192-202","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Ibex-RL: Interpretable and Scalable Control via Physics-Informed Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5302-0352","authenticated-orcid":false,"given":"Ozan Baris","family":"Mulayim","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2948-9236","authenticated-orcid":false,"given":"Mario","family":"Berg\u00e9s","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"2012 IEEE 51st IEEE conference on decision and control (CDC). IEEE, 6951\u20136956","author":"Agbi Clarence","year":"2012","unstructured":"Clarence Agbi, Zhen Song, and Bruce Krogh. 2012. Parameter identifiability for multi-zone building models. In 2012 IEEE 51st IEEE conference on decision and control (CDC). IEEE, 6951\u20136956."},{"key":"e_1_3_2_1_2_1","volume-title":"Differentiable mpc for end-to-end planning and control. Advances in neural information processing systems 31","author":"Amos Brandon","year":"2018","unstructured":"Brandon Amos, Ivan Jimenez, Jacob Sacks, Byron Boots, and J Zico Kolter. 2018. Differentiable mpc for end-to-end planning and control. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys '23)","author":"An Zhiyu","year":"2023","unstructured":"Zhiyu An, Xianzhong Ding, Arya Rathee, and Wan Du. 2023. CLUE: Safe ModelBased RL HVAC Control Using Epistemic Uncertainty Estimation. In Proceedings of the 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys '23). Association for Computing Machinery, New York, NY, USA, 149\u2013158."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of Building Simulation 2021: 17th Conference of IBPSA","volume":"17","author":"Arroyo Javier","year":"2022","unstructured":"Javier Arroyo, Carlo Manna, Fred Spiessens, Lieve Helsen, D Saelens, J Laverge, W Boydens, and L Helsen. 2022. An OpenAI-gym environment for the building optimization testing (BOPTEST) framework. In Proceedings of Building Simulation 2021: 17th Conference of IBPSA, Vol. 17. INT BUILDING PERFORMANCE SIMULATION ASSOC-IBPSA, 175\u2013182."},{"key":"e_1_3_2_1_5_1","volume-title":"Control-oriented thermal modeling of multizone buildings: Methods and issues: Intelligent control of a building system","author":"Atam Ercan","year":"2016","unstructured":"Ercan Atam and Lieve Helsen. 2016. Control-oriented thermal modeling of multizone buildings: Methods and issues: Intelligent control of a building system. IEEE Control systems magazine 36, 3 (2016), 86\u2013111."},{"key":"e_1_3_2_1_6_1","volume-title":"A survey on physics informed reinforcement learning: Review and open problems. Expert Systems with Applications","author":"Banerjee Chayan","year":"2025","unstructured":"Chayan Banerjee, Kien Nguyen, Clinton Fookes, and Maziar Raissi. 2025. A survey on physics informed reinforcement learning: Review and open problems. Expert Systems with Applications (2025), 128166."},{"key":"e_1_3_2_1_7_1","volume-title":"2016 American Control Conference (ACC). IEEE.","author":"Cai Jie","year":"2016","unstructured":"Jie Cai, Donghun Kim, James E Braun, and Jianghai Hu. 2016. Optimizing zone temperature setpoint excitation to minimize training data for data-driven dynamic building models. In 2016 American Control Conference (ACC). IEEE."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","author":"Chen Bingqing","year":"2019","unstructured":"Bingqing Chen, Zicheng Cai, and Mario Berg\u00e9s. 2019. Gnu-RL: A Precocial Reinforcement Learning Solution for Building HVAC Control Using a Differentiable MPC Policy. In Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (New York, NY, USA) (BuildSys '19). Association for Computing Machinery, New York, NY, USA, 10 pages."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","author":"Ding Xianzhong","unstructured":"Xianzhong Ding, Wan Du, and Alberto E. Cerpa. 2020. MB2C: Model-Based Deep Reinforcement Learning for Multi-zone Building Control. In Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (Virtual Event, Japan) (BuildSys '20). Association for Computing Machinery, New York, NY, USA, 50\u201359."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","first-page":"106852","DOI":"10.1016\/j.jobe.2023.106852","article-title":"Comparative study of model-based and model-free reinforcement learning control performance in HVAC systems","volume":"74","author":"Gao Cheng","year":"2023","unstructured":"Cheng Gao and Dan Wang. 2023. Comparative study of model-based and model-free reinforcement learning control performance in HVAC systems. Journal of Building Engineering 74 (2023), 106852.","journal-title":"Journal of Building Engineering"},{"key":"e_1_3_2_1_11_1","volume-title":"Experimental estimation of building energy performance by robust regression. Energy and buildings 38, 6","author":"Ghiaus Cristian","year":"2006","unstructured":"Cristian Ghiaus. 2006. Experimental estimation of building energy performance by robust regression. Energy and buildings 38, 6 (2006), 582\u2013587."},{"key":"e_1_3_2_1_12_1","unstructured":"Gargya Gokhale Bert Claessens and Chris Develder. 2022. PhysQ: a physics informed reinforcement learning framework for building control. arXiv:2211.11830"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 15th ACM International Conference on Future and Sustainable Energy Systems","author":"Gokhale Gargya","year":"2024","unstructured":"Gargya Gokhale, Seyed Soroush Karimi Madahi, Bert Claessens, and Chris Develder. 2024. Distill2Explain: Differentiable decision trees for explainable reinforcement learning in energy application controllers. In Proceedings of the 15th ACM International Conference on Future and Sustainable Energy Systems (Singapore, Singapore) (e-Energy '24). Association for Computing Machinery, New York, NY, USA, 55\u201364."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 11th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","author":"Goldfeder Judah","year":"2024","unstructured":"Judah Goldfeder and John Sipple. 2024. Reducing Carbon Emissions at Scale: Interpretable and Efficient to Implement Reinforcement Learning via Policy Extraction. In Proceedings of the 11th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (Hangzhou, China) (BuildSys '24). Association for Computing Machinery, New York, NY, USA, 403\u2013407."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","first-page":"6158","DOI":"10.1016\/j.egypro.2019.01.494","article-title":"Advanced building control via deep reinforcement learning","volume":"158","author":"Jia Ruoxi","year":"2019","unstructured":"Ruoxi Jia, Ming Jin, Kaiyu Sun, Tianzhen Hong, and Costas Spanos. 2019. Advanced building control via deep reinforcement learning. Energy Procedia 158 (2019), 6158\u20136163.","journal-title":"Energy Procedia"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 7th International Building Physics Conference","author":"John Camille","year":"2018","unstructured":"Camille John, Charalampos Vallianos, Jos\u00e9 Candanedo, and Andreas Athienitis. 2018. Estimating time constants for over 10,000 residential buildings in North America: Towards a statistical characterization of thermal dynamics. In Proceedings of the 7th International Building Physics Conference. Syracuse, NY, USA."},{"key":"e_1_3_2_1_17_1","volume-title":"The impact of intrinsic rewards on exploration in Reinforcement Learning. Neural Computing and Applications","author":"Kayal Aya","year":"2025","unstructured":"Aya Kayal, Eduardo Pignatelli, and Laura Toni. 2025. The impact of intrinsic rewards on exploration in Reinforcement Learning. Neural Computing and Applications (2025), 1\u201335."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","first-page":"126459","DOI":"10.1016\/j.apenergy.2025.126459","article-title":"Lessons learned from field demonstrations of model predictive control and reinforcement learning for residential and commercial HVAC: A review","volume":"399","author":"Khabbazi Arash J.","year":"2025","unstructured":"Arash J. Khabbazi, Elias N. Pergantis, Levi D. Reyes Premer, Panagiotis Papageorgiou, Alex H. Lee, James E. Braun, Gregor P. Henze, and Kevin J. Kircher. 2025. Lessons learned from field demonstrations of model predictive control and reinforcement learning for residential and commercial HVAC: A review. Applied Energy 399 (2025), 126459.","journal-title":"Applied Energy"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","first-page":"7727","DOI":"10.3390\/su12187727","article-title":"Evaluating the adaptability of reinforcement learning based HVAC control for residential houses","volume":"12","author":"Kurte Kuldeep","year":"2020","unstructured":"Kuldeep Kurte, Jeffrey Munk, Olivera Kotevska, Kadir Amasyali, Robert Smith, Evan McKee, Yan Du, Borui Cui, Teja Kuruganti, and Helia Zandi. 2020. Evaluating the adaptability of reinforcement learning based HVAC control for residential houses. Sustainability 12, 18 (2020), 7727.","journal-title":"Sustainability"},{"key":"e_1_3_2_1_20_1","volume-title":"2016 IEEE International Energy Conference (ENERGYCON). IEEE, 1\u20136.","author":"Leurs Tim","year":"2016","unstructured":"Tim Leurs, Bert J Claessens, Frederik Ruelens, Sam Weckx, and Geert Deconinck. 2016. Beyond theory: Experimental results of a self-learning air conditioning unit. In 2016 IEEE International Energy Conference (ENERGYCON). IEEE, 1\u20136."},{"key":"e_1_3_2_1_21_1","unstructured":"Sergey Levine Aviral Kumar George Tucker and Justin Fu. 2020. Offline Reinforcement Learning: Tutorial Review and Perspectives on Open Problems. arXiv:2005.01643 [cs.LG]"},{"key":"e_1_3_2_1_22_1","volume-title":"Transforming cooling optimization for green data center via deep reinforcement learning","author":"Li Yuanlong","year":"2019","unstructured":"Yuanlong Li, Yonggang Wen, Dacheng Tao, and Kyle Guan. 2019. Transforming cooling optimization for green data center via deep reinforcement learning. IEEE transactions on cybernetics 50, 5 (2019), 2002\u20132013."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1016\/j.enbuild.2015.04.029","article-title":"Field tests of an adaptive, model-predictive heating controller for residential buildings","volume":"99","author":"Lindel\u00f6f David","year":"2015","unstructured":"David Lindel\u00f6f, Hossein Afshari, Mohammad Alisafaee, Jayant Biswas, Miroslav Caban, Xavier Mocellin, and Jean Viaene. 2015. Field tests of an adaptive, model-predictive heating controller for residential buildings. Energy and Buildings 99 (2015), 292\u2013302.","journal-title":"Energy and Buildings"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 11th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","author":"Liu Hsin-Yu","year":"2024","unstructured":"Hsin-Yu Liu, Bharathan Balaji, Rajesh Gupta, and Dezhi Hong. 2024. Adaptive Policy Regularization for Offline-to-Online Reinforcement Learning in HVAC Control. In Proceedings of the 11th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (Hangzhou, China) (BuildSys '24). Association for Computing Machinery, New York, NY, USA, 1\u201310."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.enbuild.2005.06.001","article-title":"Experimental analysis of simulated reinforcement learning control for active and passive building thermal storage inventory","volume":"38","author":"Liu Simeng","year":"2006","unstructured":"Simeng Liu and Gregor P Henze. 2006. Experimental analysis of simulated reinforcement learning control for active and passive building thermal storage inventory: Part 2: Results and analysis. Energy and buildings 38, 2 (2006), 148\u2013161.","journal-title":"Energy and buildings"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","first-page":"109825","DOI":"10.1016\/j.enbuild.2020.109825","article-title":"Building temperature regulation in a multi-zone HVAC system using distributed adaptive control","volume":"215","author":"Lymperopoulos Georgios","year":"2020","unstructured":"Georgios Lymperopoulos and Petros Ioannou. 2020. Building temperature regulation in a multi-zone HVAC system using distributed adaptive control. Energy and Buildings 215 (2020), 109825.","journal-title":"Energy and Buildings"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","first-page":"125770","DOI":"10.1016\/j.apenergy.2025.125770","article-title":"Fully data-driven and modular building thermal control with physically consistent modeling","volume":"390","author":"Montazeri Mina","year":"2025","unstructured":"Mina Montazeri, Carl Remlinger, Benjamin Bejar Haro, and Philipp Heer. 2025. Fully data-driven and modular building thermal control with physically consistent modeling. Applied Energy 390 (2025), 125770.","journal-title":"Applied Energy"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems (E-Energy '25)","author":"Mulayim Ozan Baris","year":"2025","unstructured":"Ozan Baris Mulayim and Mario Berg\u00e9s. 2025. On the Impact of Simulated Occupancy Behavior Assumptions on Reinforcement Learning for HVAC Controls. In Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems (E-Energy '25). Association for Computing Machinery, New York, NY, USA, 317\u2013321."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Ozan Baris Mulayim and Mario Berg\u00e9s. 2024. Leveraging Grey Box Models for Enhanced Energy Flexibility in Centralized and Decentralized Single-Zone Multi-Node Systems. In 2024 IEEE International Conference on Communications Control and Computing Technologies for Smart Grids (SmartGridComm). 264\u2013270.","DOI":"10.1109\/SmartGridComm60555.2024.10738056"},{"key":"e_1_3_2_1_30_1","unstructured":"Ozan Baris Mulayim Elias N. Pergantis Levi D. Reyes Premer Bingqing Chen Guannan Qu Kevin J. Kircher and Mario Berg\u00e9s. 2025. Comparative Field Deployment of Reinforcement Learning and Model Predictive Control for Residential HVAC. arXiv:2510.01475 [eess.SY]"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","first-page":"110435","DOI":"10.1016\/j.buildenv.2023.110435","article-title":"Ten questions concerning reinforcement learning for building energy management","volume":"241","author":"Nagy Zoltan","year":"2023","unstructured":"Zoltan Nagy, Gregor Henze, Sourav Dey, Javier Arroyo, Lieve Helsen, Xiangyu Zhang, Bingqing Chen, Kadir Amasyali, Kuldeep Kurte, Ahmed Zamzam, et al. 2023. Ten questions concerning reinforcement learning for building energy management. Building and Environment 241 (2023), 110435.","journal-title":"Building and Environment"},{"key":"e_1_3_2_1_32_1","volume-title":"2022 IEEE conference on control technology and applications (CCTA). IEEE, 1172\u20131177","author":"Naug Avisek","year":"2022","unstructured":"Avisek Naug, Marcos Quinones-Grueiro, and Gautam Biswas. 2022. Reinforcement learning-based HVAC supervisory control of a multi-zone building-A real case study. In 2022 IEEE conference on control technology and applications (CCTA). IEEE, 1172\u20131177."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","first-page":"123447","DOI":"10.1016\/j.apenergy.2024.123447","article-title":"Real building implementation of a deep reinforcement learning controller to enhance energy efficiency and indoor temperature control","volume":"368","author":"Silvestri Alberto","year":"2024","unstructured":"Alberto Silvestri, Davide Coraci, Silvio Brandi, Alfonso Capozzoli, Esther Borkowski, Johannes K\u00f6hler, Duan Wu, Melanie N Zeilinger, and Arno Schlueter. 2024. Real building implementation of a deep reinforcement learning controller to enhance energy efficiency and indoor temperature control. Applied Energy 368 (2024), 123447.","journal-title":"Applied Energy"},{"key":"e_1_3_2_1_34_1","unstructured":"Richard S Sutton Andrew G Barto et al. 1998. Reinforcement learning: An introduction. Vol. 1. MIT press Cambridge."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","first-page":"118127","DOI":"10.1016\/j.apenergy.2021.118127","article-title":"Data-driven control of room temperature and bidirectional EV charging using deep reinforcement learning: Simulations and experiments","volume":"307","author":"Svetozarevic Bratislav","year":"2022","unstructured":"Bratislav Svetozarevic, Christian Baumann, Simon Muntwiler, Loris Di Natale, Melanie N Zeilinger, and Philipp Heer. 2022. Data-driven control of room temperature and bidirectional EV charging using deep reinforcement learning: Simulations and experiments. Applied Energy 307 (2022), 118127.","journal-title":"Applied Energy"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","first-page":"7294","DOI":"10.1109\/LRA.2024.3422836","article-title":"DiffTune-MPC: Closed-loop learning for model predictive control","volume":"9","author":"Tao Ran","year":"2024","unstructured":"Ran Tao, Sheng Cheng, Xiaofeng Wang, Shenlong Wang, and Naira Hovakimyan. 2024. DiffTune-MPC: Closed-loop learning for model predictive control. IEEE Robotics and Automation Letters 9, 8 (2024), 7294\u20137301.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"e_1_3_2_1_37_1","volume-title":"2014 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 1168\u20131175","author":"Tassa Yuval","year":"2014","unstructured":"Yuval Tassa, Nicolas Mansard, and Emo Todorov. 2014. Control-limited differential dynamic programming. In 2014 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 1168\u20131175. 10.1109\/ICRA.2014.6907001"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","first-page":"117733","DOI":"10.1016\/j.apenergy.2021.117733","article-title":"Controlling distributed energy resources via deep reinforcement learning for load flexibility and energy efficiency","volume":"304","author":"Touzani Samir","year":"2021","unstructured":"Samir Touzani, Anand Krishnan Prakash, Zhe Wang, Shreya Agarwal, Marco Pritoni, Mariam Kiran, Richard Brown, and Jessica Granderson. 2021. Controlling distributed energy resources via deep reinforcement learning for load flexibility and energy efficiency. Applied Energy 304 (2021), 117733.","journal-title":"Applied Energy"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","first-page":"123706","DOI":"10.1016\/j.apenergy.2024.123706","article-title":"Long-term experimental evaluation and comparison of advanced controls for HVAC systems","volume":"371","author":"Wang Xuezheng","year":"2024","unstructured":"Xuezheng Wang and Bing Dong. 2024. Long-term experimental evaluation and comparison of advanced controls for HVAC systems. Applied Energy 371 (2024), 123706.","journal-title":"Applied Energy"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1109\/TSUSC.2022.3164084","article-title":"Safe building HVAC control via batch reinforcement learning","volume":"7","author":"Zhang Chi","year":"2022","unstructured":"Chi Zhang, Sanmukh Rao Kuppannagari, and Viktor K Prasanna. 2022. Safe building HVAC control via batch reinforcement learning. IEEE Transactions on Sustainable Computing 7, 4 (2022), 923\u2013934.","journal-title":"IEEE Transactions on Sustainable Computing"}],"event":{"name":"BUILDSYS '25: 12th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","location":"Colorado School of Mines Golden CO USA","acronym":"BUILDSYS '25","sponsor":["SIGEnergy ACM Special Interest Group on Energy Systems and Informatics"]},"container-title":["Proceedings of the 12th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3736425.3770113","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T12:25:01Z","timestamp":1762863901000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3736425.3770113"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"references-count":40,"alternative-id":["10.1145\/3736425.3770113","10.1145\/3736425"],"URL":"https:\/\/doi.org\/10.1145\/3736425.3770113","relation":{},"subject":[],"published":{"date-parts":[[2025,11,11]]},"assertion":[{"value":"2025-11-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}