基于模糊神经网络再励学习控制器设计及其在倒车模型中的应用

考虑到神经网络学习算法的特点，给出了一种基于再励学习的自组织模糊CPN。它结合了模糊自组织CPN和再励算法的优点，在控制过程中在线调整网络结构以及对网络参数学习，学习效率高，控制结构简单。可以不要求受控对象的学习模型，实现在线控制，应用在倒车模型中仿真结果展示了所设计系统的良好控制性能。

Design of the controller based on reinforcement learning and its application on truck backer-upper

Several learning algorithms of neural networks are studied and a reinforcement learning based on fuzzy self-organizing CPN controller for uncertain system is presented. The structure and parameters of the control system are tuning on-line and the learning algorithm is fast learning speed. Simulation results with the control system applied to the truck backer-upper model show the good performance of the proposed system.