Skip to main content

A Transfer Learning Strategy for Improving the Data Efficiency of Deep Reinforcement Learning Control in Smart Buildings

by Kadir Amasyali, Yan Liu, Helia Zandi
Publication Type
Conference Paper
Book Title
2024 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT)
Publication Date
Page Numbers
1 to 5
Publisher Location
New Jersey, United States of America
Conference Name
The 2024 Conference on Innovative Smart Grid Technologies, North America (ISGT NA 2024)
Conference Location
Washington, District of Columbia, United States of America
Conference Sponsor
Conference Date

Reinforcement learning (RL) is a powerful tool that has shown promising results in many domains such as robotics and game-playing. Because RL algorithms learn optimal control policies by continuously interacting with their environments, these algorithms require a lot of data to learn, which limits their application to a wide range of domains. For this reason, there is an immense need for improving the training and data efficiency of RL. Towards addressing this research gap, this paper proposes a transfer learning (TL) approach to improve the efficiency of the RL algorithms by reducing data need and, thus, reducing training time. To demonstrate the proposed approach, a knowledge transfer from a set of buildings to another building was conducted. The results show that the proposed TL approach is a promising method that can efficiently harness the information from similar RL tasks and reduce the data needs of RL algorithms.