Discovering hidden structure in factored MDPs

摘要

Markov Decision Processes (MDPs) describe a wide variety of planning scenarios ranging from military operations planning to controlling a Mars rover. However, todayʼs solution techniques scale poorly, limiting MDPsʼ practical applicability. In this work, we propose algorithms that automatically discover and exploit the hidden structure of factored MDPs. Doing so helps solve MDPs faster and with less memory than state-of-the-art techniques.