Deep Reinforcement Learning

Towards Intelligent Multi-Zone Thermal Control with Multi- Agent Deep Reinforcement Learning
In this paper, we investigate the multi-zone thermal control with optimized energy usage and canonical thermal comfort modeling. A multi-zone thermal control algorithm (MOCA) is proposed to solve the problem by deriving optimal control policies.
Jie Li, Wei Zhang, Guanyu Gao, Yonggang Wen, Guangyu Jin, Georgios Christopoulos
DeepComfort: Energy-Efficient Thermal Comfort Control in Buildings via Reinforcement Learning
We implement a building thermal comfort control simulation environment and evaluate the performance under various settings of DDPG based approach.
Guanyu Gao, Jie Li, Yonggang Wen