A Learning Architecture for Automating the Intelligent Environment

G. Michael Youngblood, Diane J. Cook, Lawrence B. Holder

Abstract: Developing technologies and systems for perception and perspicacious automated control of home and workplace environments is a challenging problem. We present a complete agent architecture for learning to automate the intelligent environment and discuss the development, deployment, and techniques utilized in our working intelligent environments. Empirical evaluation of our approach has proven its effectiveness at reducing inhabitant interactions by 72.2%.