Fuzzy advantage learning
Xinghui Yan, Zhidong Deng, Zhanquan Sun · 2002
Based on advantage learning and fuzzy inference systems (FISs), fuzzy advantage learning (FAL) is presented. In FAL, a FIS is applied to introduce strong generalization ability and to generate continuous actions for advantage learning. This approach is illustrated and compared to other reinforcement learning methods. The simulation study on inverted pendulum control shows its effectiveness with faster learning speed.