Resolving Contentions Between Initial and Learned Knowledge

摘要

This work describes a problem, knowledge contention, that arises when agent knowledge learned via knowledge compilation contends with the agent's original task decomposition knowledge in the execution of agent actions. We show the circumstances under which the problem occurs, present a solution that avoids knowledge contention, and provide empirical results that show that knowledge compilation under the proposed solution leads to agents that can integrate planning, plan execution, and learning without explicit knowledge design for learning.