Construction of a Player Agent for a Card Game Using an Ensemble Method

The 3-channel fuzzy ART network FALCON (Fusion Architecture for Learning, COgnition, and Navigation) is known as an effective method for combining reinforcement learning with state segmentation. It has been shown that FALCON is effective in making a player agent for the card game Hearts, although the agent was unable to beat an agent using the UCT algorithm developed for Monte-Carlo simulation. This study proposes an ensemble method for FALCON to make an agent stronger. The method uses nine types of learners and combines them to decide an action. Experiments demonstrate that our approach is superior to an agent using a single learner.