Rational Learning: Finding a Balance Between Utility and Efficiency

Learning is an important aspect of intelligent behavior. Unfortunately, learning rarely comes for free. Techniques developed by machine learning can improve the abilities of an agent but they often entail considerable computational expense. Furthermore, there is an inherent tradeoff between the power and efficiency of learning techniques. This poses a dilemma to a learning agent that must act in the world under a variety of resource constraints. This article considers the problem of rational learning algorithms that dynamically adjust their behavior based on the larger context of overall performance goals and resource constraints.