Toward Foraging for Understanding of StarCraft Agents: An Empirical Study

TL;DR

This study investigates how experienced users seek information in explanations of StarCraft AI agents, revealing significant challenges and costs that impact understanding and decision-making.

Contribution

It provides empirical insights into user foraging behaviors in Explainable AI for complex domains like StarCraft, informing future system design.

Findings

Users face difficult foraging problems

Important events are often missed

High cognitive and navigation costs encountered

Abstract

Assessing and understanding intelligent agents is a difficult task for users that lack an AI background. A relatively new area, called "Explainable AI," is emerging to help address this problem, but little is known about how users would forage through information an explanation system might offer. To inform the development of Explainable AI systems, we conducted a formative study, using the lens of Information Foraging Theory, into how experienced users foraged in the domain of StarCraft to assess an agent. Our results showed that participants faced difficult foraging problems. These foraging problems caused participants to entirely miss events that were important to them, reluctantly choose to ignore actions they did not want to ignore, and bear high cognitive, navigation, and information costs to access the information they needed.