Integrated Learning for Goal-Driven Autonomy
ULIT JAIDEE, Hector Munoz-Avila and David Aha
Goal-driven autonomy (GDA) is a reflective model of goal reasoning that controls the focus of an agent’s planning activities by dynamically resolving unexpected discrepancies in the world state, which frequently arise when solving tasks in complex environments. Several research groups have reported that GDA agents perform well on such tasks by integrating components for discrepancy recognition, explanation, goal formulation, and goal management. However, they require substantial domain knowledge, including what constitutes a discrepancy and how to resolve it. We introduce LGDA, a learning algorithm for acquiring this knowledge, modeled as cases, that and integrates case-based reasoning and reinforcement learning methods. We assess its utility on tasks from a complex video game environment. We claim that, for these tasks and environment, LGDA can significantly outperform its ablations. Our evaluation provides evidence to support this claims. LGDA exemplifies a feasible design methodology for deployable GDA agents.