Intelligent Agents for Real-Time Story Adaptation for Training Assessment

Simulation-based training offers the potential for relatively low cost training available at any time and almost any duty station. However, a main drawback of simulation-based training is the lack of oversight in the training process. Simulations often depend on a fixed number of pre-defined training scenarios that are designed to test training objectives but often do not deliver a training experience customized to the specific trainee’s current level of skill and understanding. We propose developing an Interactive Storytelling Architecture for Training (ISAT) using an intelligent agent, the director, that assembles training scenarios designed to test the skill level of specific trainees. The director also acts in the course of the execution of the training scenario to provide indirect feedback about trainee actions, subtly adapting the training environment to stress skills and suggest remediation. The ISAT prototype will show how the director can use a skill model both to create a multi-scene training narrative to test specific skills and also to act within the evolution of a scene to provide feedback and guidance to a trainee. Implementation will enable preliminary evaluation of ISAT. We will use three evaluation dimensions to evaluate ISAT—authenticity of context, training effectiveness, and cost factors.