Abstract
AI research on meta-reasoning for agent self-adaptation has generally focused on modifying the agent’s reasoning processes. In this paper, we describe the use of meta-reasoning for retrospective adaptation of the agent’s domain knowledge. In particular, we consider the use of meta-knowledge for structural credit assignment in a classification hierarchy when the classifier makes an incorrect prediction. We present a scheme in which the semantics of the intermediate abstractions in the classification hierarchy are grounded in percepts in the world, and show that this scheme enables self-diagnosis and self-repair of knowledge contents at intermediate nodes in the hierarchy. We also discuss the implications of this scheme for an architecture for meta-reasoning.
