Using decision theory to formalize emotions in multi-agent systems

We use the formalism of decision theory to develop principled definitions of emotional states of a rational agent. We postulate that these notions are useful for rational agent design. First, they can serve as internal states controlling the allocation of computations and time devoted to cognitive tasks under external pressures. Second, they provide a well defined implementation-independent vocabulary the agents can use to communicate their internal states to each other. Finally, they are essential during interactions with human agents in open multi-agent environments. Our approach provides a formal bridge between the rich bodies of work in cognitive science and the high-end AI architectures for designing rational artificial agents