Cognitively-Inspired Salience Computation for Intelligent Agents
Loading...
Authors
Somers, Sterling
Mitsopoulos, Konstantinos
Lebiere, Christian
Thomson, Robert
Issue Date
2019
Type
Conference presentations, papers, posters
Language
Keywords
salience , cognitive model , intelligent agent
Alternative Title
Abstract
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 generated by having a cognitive model using instance-based learning theory to mirror the actions of an intelligent agent, and then determining which features most uniquely contributed to the actions of the agent. We present three examples of this salience techniques, including reinforcement learning agents based in the StarCraft II and autonomous drone domains, as well as part of a risk assessment model. A benefit of our method is that it does not rely on a specific implementation of an agent, it only requires the underlying decision feature-space. It is also capable of utilizing features at different levels of abstraction
Description
Citation
Somers, S., Mitsopoulos, K., Lebiere, C., & Thomson, R. (2019). Cognitively-Inspired Salience Computation for Intelligent Agents. Proceedings of the Annual Meeting of the Cognitive Science Society, 41. Retrieved from https://escholarship.org/uc/item/2h89m785
Publisher
eScholarship