Analysis of Model-Agnostic Meta-Reinforcement Learning on Automated HVAC Control
2025 33rd Signal Processing and Communications Applications Conference (SIU)
Abstract
This paper introduces a Model-Agnostic Meta-Reinforcement Learning framework for HVAC automation, integrating Model Agnostic Meta-Learning with Double Deep Q-Networks to improve adaptability across varying environmental conditions. The proposed approach is evaluated using Sinergym, an EnergyPlus-integrated RL Simulation framework, and benchmarked against conventional RL-based HVAC controllers. Results demonstrate that Model-Agnostic Meta-Learning integrated Double Deep Q-Network achieves a 7% reduction in overall power consumption while dynamically adapting to climate variations. These findings highlight the potential of Model Agnostic Meta-Learning in optimizing HVAC control strategies.
Selected figures
Cite this work
U. Filiz, M. B. Hekimoğlu, S. Baghaee and I. Ulusoy, "Analysis of Model-Agnostic Meta-Reinforcement Learning on Automated HVAC Control," in 2025 33rd Signal Processing and Communications Applications Conference (SIU), pp. 1-4, 2025. doi: 10.1109/SIU66497.2025.11112293.
@inproceedings{filiz2025analysis,
author = {Filiz, Ulaş and Hekimoğlu, Mehmet Burak and Baghaee, Sajjad and Ulusoy, Ilkay},
title = {Analysis of Model-Agnostic Meta-Reinforcement Learning on Automated HVAC Control},
booktitle = {2025 33rd Signal Processing and Communications Applications Conference (SIU)},
pages = {1-4},
publisher = {IEEE},
year = {2025},
doi = {10.1109/SIU66497.2025.11112293},
url = {https://ieeexplore.ieee.org/abstract/document/11112293}
}