Using Participatory Paradigm to Learn Human Behaviour

Since the end of the seventies, the utilization of multi-agents simulations has spread out. A typical use of these simulations concerns the modeling of human behavior. In this application case, a key point to ensure the simulation realism is the definition of the agent behavior. Unfortunately, designing such behavior is often complex. In order to help the definition of human behavior, we propose an approach based on the participatory paradigm. In our approach, a human actor directly plays the role of an agent in the simulation. Knowledge about its behavior is extracted from analysis of the logs. In this context, we propose to formalize the human behavior by means of utility functions. An experiment, carried out in the domain of rescue simulation, is presented. This first experiment shows promising results for our approach.