The Self Organization of Context for Learning in MultiAgent Games

Reinforcement learning is an effective machine learning paradigm in domains represented by compact and discrete state-action spaces. In high-dimensional and continuous domains, tile coding with linear function approximation has been widely used to circumvent the curse of dimensionality, but it suffers from the drawback that human-guided identification of features is required to create effective tilings. The challenge is to find tilings that preserve the context necessary to evaluate the value of a state-action pair while limiting memory requirements. The technique presented in this paper addresses the difficulty of identifying context in highdimensional domains. We have chosen RoboCup simulated soccer as a domain because its high-dimensional continuous state space makes it a formidable challenge for reinforcement learning algorithms. Using self-organizing maps and reinforcement learning in a two-pass process, our technique scales to large state spaces without requiring a large amount ...

• Type: Conference
• Year: 2006
• Where: AIIDE
• Authors: Christopher D. White, Dave Brogan
• Keywords: AIIDE 2006, Artificial Intelligence, Machine Learning Paradigm, Reinforcement Learning, State Space