No abstract

In this paper we focus on explaining to humans the behavior of autonomous agents, i.e., explainable agents. Explainable agents are useful for many reasons including scenario-based training (e.g. disaster training), tutor and pedagogical systems, agent development and debugging, gaming, and interactive storytelling. As the aim is to generate for humans plausible and insightful explanations, user evaluation of different explanations is essential. In this paper we test the hypothesis that different explanation types are needed to explain different types of actions. We present three different, generically applicable, algorithms that automatically generate different types of explanations for actions of BDIbased agents. Quantitative analysis of a user experiment (n=30), in which users rated the usefulness and naturalness of each explanation type for different agent actions, supports our hypothesis. In addition, we present feedback from the users about how they would explain the actions themselves. Finally, we hypothesize guidelines relevant for the development of explainable BDI agents.

No abstract

There is an attention shift within the gaming industry toward more natural (long-term) behavior of nonplaying characters (NPCs). Multiagent system research offers a promising technology to implement cognitive intelligent NPCs. However, the technologies used in game engines and multiagent platforms are not readily compatible due to some inherent differences of concerns. Where game engines focus on real-time aspects and thus propagate efficiency and central control, multiagent platforms assume autonomy of the agents. Increased autonomy and intelligence may offer benefits for a more compelling gameplay and may even be necessary for serious games. However, it raises problems when current game design techniques are used to incorporate state-of-the-art multiagent system technology. In this paper, we will focus on three specific problem areas that arise from this difference of view: synchronization, information representation, and communication. We argue that the current attempts for integration still fall short on some of these aspects. We show that to fully integrate intelligent agents in games, one should not only use a technical solution, but also a design methodology that is amenable to agents. The game design should be adjusted to incorporate the possibilities of agents early on in the process.