Quantifying means-end reasoning skills in simulation-based training: a logic-based approach

Abstract

We develop a logic-based approach for designing simulation-based training scenarios. Our methodology embodies a concise definition of the scenario concept and integrates the notions of training goals, acceptable versus unacceptable actions and performance scoring. The approach applies classical artificial intelligence (AI) planning to extract coherent plays from a causal description of the training domain. The domain- and task-specific parts are defined in a high-level action description language [Formula: see text]. Generic causal and temporal logic is added when the causal theory is compiled into the underlying Answer Set Programming (ASP) language. The ASP representation is used to derive a scoring function that reflects the quality of a play or training session, based on a distinction of states and actions into green (acceptable) and red (unacceptable) ones. To that end, we add to the casual theory a set of norms that specify an initial assignment of colors. The ASP engine uses these norms as axioms and propagates colors by consulting the causal theory. We prove that any set of such norms constitutes a conservative extension of the underlying causal theory. With this work, we hope to lay the foundation for the development of design and analysis tools for exercise managers. We envision a software system that lets an exercise manager view all plays of a tentative scenario design, with expediency information and scores for each possible play. Our approach is applicable to any domain in which means-ends reasoning is pertinent. We illustrate the approach in the domain of crisis response and management.