Novel fuzzy reinforcement learning incorporated with ant colony optimization
一种新的基于蚁群优化的模糊强化学习算法

Fuzzy sarsa learning (FSL) is one of fuzzy reinforcement learning algorithms based on sarsa architecture. FSL approximates the action value function and is an on-policy method. In each fuzzy rules, actions are selected according to the proposed modified Softmax formula. Because it is difficult for FSL to balance exploration vs. exploitation, an ant colony optimization FSL (ACO-FSL) is offered by integrating the proposed ant colony optimization and the fuzzy balancer into FSL, and the weight vector of ACO-FSL with stationary action selection policy converges to a unique value is proved. Simulation results show that ACO-FSL well manager balance, and outperforms FSL in terms of learning speed and action quality.