Reinforcement fuzzy control using Ant Colony Optimization

This paper proposes the design of a fuzzy controller by Ant Colony Optimization (ACO) incorporated with Fuzzy-Q Learning, called ACO-FQ, with reinforcements. For a fuzzy controller, we list all candidate consequent control actions of each fuzzy rule. Each candidate in the consequent part of a rule is assigned with a corresponding Q-value. Searching for the best one among all combinations is partially based on pheromone trail and partially based on Q-values. To verify the performance of ACO-FQ, reinforcement fuzzy control of water bath temperature control system is simulated.