Transferable Reinforcement Learning for Smart Homes: Preprint

Xiangyu Zhang, Xin Jin, Charles Tripp, David Biagioni, Peter Graf, Huaiguang Jiang

Research output: Contribution to conferencePaper


To harness the great amount of untapped resources at the demand side, smart home technology plays a vital role in solving the "last mile" problem in smart grid. Reinforcement learning (RL), which has demonstrated an outstanding performance in solving many sequential decision-making problems, can be a great candidate to be used in smart home control. For instance, many studies have started investigating the load scheduling problem under dynamic pricing scheme. Based on those, this study aims at providing an affordable solution to encourage a higher smart home adoption rate. Specifically, we investigate combining transfer learning (TL) with RL to reduce the training cost of an optimal RL control policy. Given an optimal policy for a benchmark home, TL can jump-start the RL training of a policy for a new home, which has different appliances and user preferences. Simulation results show that by leveraging TL, RL training converges faster and requires much less computing time for new homes that are similar to the benchmark home. In all, this study proposes a cost-effective approach for training RL control policies for homes at scale, which ultimately reduces the controller's implementation costs, increases the adoption rate of RL controllers, and makes more homes grid-interactive.
Original languageAmerican English
Number of pages8
StatePublished - 2020
EventFirst International Workshop on Reinforcement Learning for Energy Management in Buildings and Cities (RLEM) -
Duration: 17 Nov 202017 Nov 2020


ConferenceFirst International Workshop on Reinforcement Learning for Energy Management in Buildings and Cities (RLEM)

NREL Publication Number

  • NREL/CP-2C00-77933


  • home energy management
  • reinforcement learning
  • smart home
  • transfer learning


Dive into the research topics of 'Transferable Reinforcement Learning for Smart Homes: Preprint'. Together they form a unique fingerprint.

Cite this