Fuzzy Model-Based Reinforcement Learning

Model-based reinforcement learning methods are known to be highly efficient with respect to the number of trials required for learning optimal policies. In this article a novel fuzzy model-based reinforcement learning approach, fuzzy prioritized sweeping (F-PS), is presented. The approach is capable of learning strategies for Markov decision problems with continuous state and action spaces. The output of the algorithm are Takagi-Sugeno fuzzy systems approximating the Q-functions corresponding to the given control problems. From these Q-functions optimal control strategies can be easily derived. The effectiveness of the F-PS approach is shown by applying it to the task of selecting optimal framework signal plans in urban traffic networks. It is shown that the method outperforms existing model-based approaches.