Using Planning to Train Crisis Decision Makers

Training for crisis decision makers poses a number of challenges that range from the necessity to foster creative decision making to the need of creating engaging and realistic scenarios in support of experiential learning. This article describes our effort to build an end-to-end intelligent system, called the Pandora-Box, that supports a trainer in populating a 4-5 hours training session with exercises for a class of decision makers to teach them how to achieve joint decisions under stress. The paper gives a comprehensive view of the current system and in particular focuses on how AI planning technology has been customized to serve this purpose. Aspects considered are: (a) the timeline-based representation that acts as the core component for creating training sessions and unifying different concepts of the Pandora domain; (b) the combination of planning and execution functionalities to maintain and dynamically adapt a "lesson plan" on the basis of both trainees-trainer interactions and individual behavioral features and performance; (c) the importance of keeping the trainer in the loop preserving his/her responsibility in creating content for the class but endowing him/her with a set of new functionalities.