Novel fuzzy reinforcement learning incorporated with ant colony optimization
Xie Guang-qianga · 2011
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 was difficult for FSL to balance exploration vs.exploitation,offered an ant colony optimization FSL(ACO-FSL) by integrating the proposed ant colony optimization and the fuzzy balancer into FSL,and proved the weight vector of ACO-FSL with stationary action selection policy converged to a unique value.Simulation results show that ACO-FSL well manages balance,and outperforms FSL in terms of learning speed and action quality.