Recovery from Incorrect Knowledge in Soar

Abstract

Incorrect knowledge can be a problem for any intelligent system. Soar is a proposal for the underlying architecture that supports intelligence. It has a single representation of long-term memory and a single learning mechanism called chunking. This paper investigates the problem of recovery from incorrect knowledge in Soar. Recovery is problematic in Soar because of the simplicity of chunking: it does not modify existing productions, nor does it analyze the long-term memory during learning. In spite of these limitations, we demonstrate a domain-independent approach to recovery from incorrect control knowledge and present extensions to this approach for recovering from all types of incorrect knowledge. The key idea is to correct decisions instead of long-term knowledge. Soar's architecture allows this corrections to occur in parallel with normal processing. This approach does not require any changes to the Soar architecture and because of Soar's uniform representations for tasks and knowledge, this approach can be used for all tasks and sub-tasks in Soar.