Learning to Control a Smart Home Environment
Diane J. Cook, Manfred Huber, Karthik Gopalratnam, G. Michael Youngblood · 2003
The goal of the MavHome (Managing An Intelligent Versatile Home) project is to create a home that acts as an intelligent agent. In this paper, we introduce the MavHome architecture and two learning algorithms that play central roles in the smart home. The first algorithm predicts actions the inhabitant will take in the home. The second algorithm learns a policy to control the home. Effectiveness of the algorithms on smart home data is presented and we document the application of the technology in a working smart home environment.