Behaviour Explanation via Causal Analysis of Mental States: A Preliminary Report
This work provides a formal framework for explaining agent behavior through causal analysis of mental states, specifically targeting multiagent systems, but it is incremental as it builds directly on prior research.
The paper addresses the limitation of an existing causal knowledge framework by extending it to include motivational states, enabling reasoning about causes of motivational states and motivation-altering actions as causes of observed effects, and demonstrates its application in explaining agent behavior in communicative multiagent contexts.
Inspired by a novel action-theoretic formalization of actual cause, Khan and Lespérance (2021) recently proposed a first account of causal knowledge that supports epistemic effects, models causal knowledge dynamics, and allows sensing actions to be causes of observed effects. To date, no other study has looked specifically at these issues. But their formalization is not sufficiently expressive enough to model explanations via causal analysis of mental states as it ignores a crucial aspect of theory of mind, namely motivations. In this paper, we build on their work to support causal reasoning about conative effects. In our framework, one can reason about causes of motivational states, and we allow motivation-altering actions to be causes of observed effects. We illustrate that this formalization along with a model of goal recognition can be utilized to explain agent behaviour in communicative multiagent contexts.