Perceptually grounded self-diagnosis and self-repair of domain knowledge

摘要

We view incremental experiential learning in intelligent software agents as progressive agent self-adap tation. When an agent produces an incorrect behavior, then it may reflect on, and thus diagnose and repair, the reasoning and knowledge that produced the incorrect behavior. In particular, we focus on the self-diagnosis and self-repair of an agent's domain knowledge. The core issue that this article addresses is: what kind of metaknowledge may enable the agent to diagnose faults in its domain knowl edge? To address this question, we propose a representation that explicitly encodes metaknowledge in the form of Empirical Verification Procedures (EVPs). In the proposed knowledge representation, an EVP may be associated with each concept within the agent's domain knowledge. Each EVP explicitly seman tically grounds the associated concept in the agent's perception, and can thus be used as a test to deter mine the validity of knowledge of that concept during diagnosis. We present the empirical evaluation of a system, Augur, that makes use of EVP metaknowledge to adapt its own domain knowledge in the context of a particular subclass of classification problem called Compositional Classification.