Argumentation-based Agents that Explain their Decisions

TL;DR

This paper presents an extension to BDI agents that uses argumentation theory to generate explanations for decision-making, particularly goal selection, demonstrated in a rescue robot scenario.

Contribution

It introduces an argumentation-based approach for explaining BDI agent decisions, including partial and complete explanations, enhancing transparency in AI agents.

Findings

Effective explanation generation for goal decisions

Application to rescue robot scenario

Improved transparency in agent reasoning

Abstract

Explainable Artificial Intelligence (XAI) systems, including intelligent agents, must be able to explain their internal decisions, behaviours and reasoning that produce their choices to the humans (or other systems) with which they interact. In this paper, we focus on how an extended model of BDI (Beliefs-Desires-Intentions) agents can be able to generate explanations about their reasoning, specifically, about the goals he decides to commit to. Our proposal is based on argumentation theory, we use arguments to represent the reasons that lead an agent to make a decision and use argumentation semantics to determine acceptable arguments (reasons). We propose two types of explanations: the partial one and the complete one. We apply our proposal to a scenario of rescue robots.