Online transfer learning strategy for enhancing the scalability and deployment of deep reinforcement learning control in smart buildings

D Coraci, S Brandi, T Hong, A Capozzoli - Applied Energy, 2023 - Elsevier
… This study is the only one in which the use of heterogeneouslearning process, to accelerate
the convergence process of … to imitation learning, but in this case the expert controller could …

[HTML][HTML] Gnu-rl: A practical and scalable reinforcement learning solution for building hvac control using a differentiable mpc policy

B Chen, Z Cai, M Bergés - Frontiers in Built Environment, 2020 - frontiersin.org
HVAC control literature. We hypothesized that encoding such knowledge in the policy would
expedite the learning … domain knowledge on HVAC control and expert demonstration from …

Reinforcement learning for building controls: The opportunities and challenges

Z Wang, T Hong - Applied Energy, 2020 - Elsevier
… , addressing current RL challenges, such as accelerating training and enhancing control
robustness, as … is a time-consuming process and requires expertise. Rather than training the RL …

A practical deep reinforcement learning framework for multivariate occupant-centric control in buildings

Y Lei, S Zhan, E Ono, Y Peng, Z Zhang, T Hasama… - Applied Energy, 2022 - Elsevier
… due to the need for many heterogeneous agents [28]. Hence, a … with expert manual control
in a real central chiller plant. … during the exploration and accelerating the training process. In …

Ten questions concerning reinforcement learning for building energy management

Z Nagy, G Henze, S Dey, J Arroyo, L Helsen… - Building and …, 2023 - Elsevier
… to expedite the adoption of RL for building energy management. … expert experience, and
are unable to adapt to changing objectives. Despite being developed by building control experts

On-policy learning-based deep reinforcement learning assessment for building control efficiency and stability

JY Lee, A Rahman, S Huang, AD Smith… - … and Technology for …, 2022 - Taylor & Francis
… of overall building thermal dynamics and heterogeneous environmental conditions in
real … industry experts. They are widely used in assessments on how different designs and …

Applications of reinforcement learning for building energy efficiency control: A review

Q Fu, Z Han, J Chen, Y Lu, H Wu, Y Wang - Journal of Building Engineering, 2022 - Elsevier
… , we review the reinforcement learning methods applied to control and manage buildings,
outline … The results show that the framework outperforms the expert-based solution. Henze [25] …

[HTML][HTML] Controlling distributed energy resources via deep reinforcement learning for load flexibility and energy efficiency

S Touzani, AK Prakash, Z Wang, S Agarwal, M Pritoni… - Applied Energy, 2021 - Elsevier
expertise and it is time consuming, making this approach difficult to scale. Since buildings
are heterogeneous… research that have applied RL in building controls 2.2, and consequently, …

A review of recent advances on reinforcement learning for smart home energy management

H Zhang, D Wu, B Boulet - 2020 IEEE Electric Power and …, 2020 - ieeexplore.ieee.org
… -intensive modelling and extensive expertise, MPC has shown its … Plus, to accelerate the
training process, the approach … Considering the continuous operations of heterogeneous home …

[HTML][HTML] Reinforcement learning-based intelligent control strategies for optimal power management in advanced power distribution systems: A survey

M Al-Saadi, M Al-Greer, M Short - Energies, 2023 - mdpi.com
… to pre-initialize the Q-learning table and accelerate the management process. Furthermore,
the FCS … [94] was the frequency regulator of the AC microgrid with heterogeneous BESSs. A …