BADGER-TL Ph II

In this Phase II project, SoarTech proposes to extend and mature our Phase I research for Behavior and Action-Driven Game Environmental Rewards in Task Learning (BADGER-TL) into a flexible behavior engine that can be rapidly deployed to meet a large number of behavior-related requirements across the full spectrum of modeling and simulation (M&S) training systems available in the DoD enterprise, including the Army’s emerging Synthetic Training Environment (STE). SoarTech is an industry leader in the development of artificial intelligence and machine learning (AI/ML)-enabled agents that generate behavior in complex environments. Our BADGER-TL approach fuses intelligent system design principles from goal-based cognitive models and deep learning approaches to create a hybrid behavior architecture providing instructors and behavioral designers the ability to rapidly inject behaviors into modeling and simulation systems. BADGER-TL leverages SoarTech’s experience in intelligent systems to produce an agent design capable of human-level reasoning and team coordination, even in novel situations, while remaining data efficient in its task learning and memory mechanisms. SoarTech will also develop human-centric interface designs that allow subject-matter experts to control and adjust intelligent agent behavior to produce desired effects, such a variable skill levels.