Proceedings of the Annual Meeting of the Cognitive Science Society

We describe a method for determining feature salience of action decisions in intelligent agents based on cognitively-inspired salience. Salience is defined as the degree of influence that a factor has on a given decision. This is generatedby having a cognitive model using instance-based learning theory to mirror the actions of an intelligent agent, and thendetermining which features most uniquely contributed to the actions of the agent. We present three examples of thissalience techniques, including reinforcement learning agents based in the StarCraft II and autonomous drone domains, aswell as part of a risk assessment model. A benefit of our method is that it does not rely on a specific implementation ofan agent, it only requires the underlying decision feature-space. It is also capable of utilizing features at different levels ofabstraction