Simulation within simulation for agent decision-making: Theoretical foundations from cognitive science to operational computer model

• Generic computational model of mental simulation.
• The architecture proposes three modes – reactivity, predictability, and adaptability.
• First illustration shows a dog making predictions and testing different strategies.
• Second illustration is a 3D juggler plays with virtual jugglers, humans and robots.

This article deals with artificial intelligence models inspired from cognitive science. The scope of this paper is the simulation of the decision-making process for virtual entities. The theoretical framework consists of concepts from the use of internal behavioral simulation for human decision-making. Inspired from such cognitive concepts, the contribution consists in a computational framework that enables a virtual entity to possess an autonomous world of simulation within the simulation. It can simulate itself (using its own model of behavior) and simulate its environment (using its representation of other entities). The entity has the ability to anticipate using internal simulations, in complex environments where it would be extremely difficult to use formal proof methods. Comparing the prediction and the original simulation, its predictive models are improved through a learning process. Illustrations of this model are provided through two implementations. First illustration is an example showing a shepherd, his herd and dogs. The dog simulates the sheep’s behavior in order to make predictions testing different strategies. Second, an artificial 3D juggler plays in interaction with virtual jugglers, humans and robots. For this application, the juggler predicts the behavior of balls in the air and uses prediction to coordinate its behavior in order to juggle.