Professor Héctor Muñoz-Avila, from Lehigh University in the US, is now spending part of his sabbatical here at IDI. In the AI group. His research covers several areas, and he is especially well known for his work on combining case-based reasoning with other machine learning and problem solving methods, particularly applied to planning problems and games. Hector will give a talk on Thursday this week:
Time: Thursday 20th, 12.15
Place: Room 454
Speaker: Héctor Muñoz-Avila
Title: Goal-Driven Autonomy; Reflective learning for Real-Time
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. Examples of such environments include computer games where adversaries pursue different strategies to counter the agent’s goals. GDA agents have performed well on such environments by integrating methods for discrepancy recognition, explanation, goal formulation, and goal management. My research focuses on learning algorithms for acquiring GDA knowledge that integrates case-based reasoning and reinforcement learning methods. I demonstrate uses of GDA for automated playing real-time strategy games such as Warcraft 2 and Starcraft.