Chris White and David Brogan
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 limit- ing memory requirements. The technique presented in this paper addresses the difficulty of identifying context in high-dimensional 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 of domain knowledge to automatically form abstractions over the state space. Results show that our algorithm learns to play the game of soccer better than a contemporary hand-coded opponent.