GA-Based Q-CMAC Applied to Airship Evasion Problem
Yuka Akisato, Keiji Suzuki, and Azuma Ohuchi
Faculty of Engineering, Hokkaido University, N13 W8, Sapporo 060-8628, Japan
The purpose of this research is to acquire an adaptive control policy of an airship in a dynamic, continuous environment based on reinforcement learning combined with evolutionary construction. The state space for reinforcement learning becomes huge because the airship has great inertia and must sense huge amounts of information from a continuous environment to behave appropriately. To reduce and suitably segment state space, we propose combining CMAC-based Q-learning and its evolutionary state space layer construction. Simulation showed the acquisition of state space segmentation enabling airships to learn effectively.