Inference of the Intentions of Unknown Agents in a Theory of Mind Setting

Autonomous agents may be required to form an understanding of other agents for which they don’t possess a model. In such cases, they must rely on their previously gathered knowledge of agents, and ground the observed behaviors in the models this knowledge describes by theory of mind reasoning. To give flesh to this process, in this paper we propose an algorithm to ground observations on a combination of priorly possessed Belief-Desire-Intention models, while using rationality to infer unobservable variables. This allows to jointly infer beliefs, goals and intentions of an unknown observed agent by using only available models.