Paying Attention to What’s Important: Using Focus of Attention to Improve Unsupervised Learning

Adaptive autonomous agents have to learn about the effects of their actions so as to be able to improve their performance and adapt to long term changes. The problem of correlating actions with changes in sensor data is O(n 2 ) and therefore computationally infeasible for any non-trivial application. We propose to make this problem more manageable by using focus of attention. In particular, we discuss two complementary methods for focus of attention: perceptual selectivity restricts the set of sensor data the agent attends to at a particular instant, while cognitive selectivity restricts the set of internal structures that is updated at a particular instant. We present results of an implemented algorithm, a variant of the schema mechanism [Drescher 91], which employs these two forms of focus of attention. The results demonstrate that incorporating focus of attention dramatically improves the tractability of learning action models without affecting the quality of the knowledge learned, at the relatively small cost of doubling the number of training examples required to learn the same knowledge.