Simulated Teachable Agents for Training Environments (STATE)

Training simulations that currently support Small Unit Decision-Making (SUDM) training are laborious to configure and expensive to manage with live personnel, which results in training that is limited in scope. Current simulations require numerous pucksters to control simulated entities, driving up the manpower costs of conducting simulation-based training. To fulfill the roles of pucksters in simulation-based training environments, Charles River Analytics proposes to design and demonstrate Simulated Teachable Agents for Training Environments (STATE). We will base STATE on two existing capabilities: (1) SAMPLE, our in-house cognitive modeling architecture that implements Kleins model of Recognition-Primed Decision-making (RPD); and (2) AgentWorks, our in-house, intelligent agent development and run-time platform. STATE augments these capabilities with a Graphical Agent Teaching Interface and a suite of Behavior Learning Algorithms to develop and adapt SUDM-related behavior models. The result of the STATE effort will be a suite of tools that empowers a Trainer user base (as opposed to an engineering user base) to rapidly specify, train, and implement new agent behaviors for simulation-based training.