一类连续状态与动作空间下的加权Q学习

针对连续状态与动作空间下的控制问题，提出了一类连续状态与动作空间下的加权Q学习算法，应用改进的增长神经气算法动态构建径向基网络的隐合层，实现状态空间的自适应构建。在基于径向基网络实现的标准Q学习基础上，利用加权Q学习算法用以解决具有连续动作输出的控制问题。仿真实例验证了所提算法的有效性。

A kind of weighted Q-learning for continuous state and action spaces

Aiming at control problems of continuous state and action spaces, a kind of weighted Q-learning was proposed to solve the application under the condition of continuous state and action spaces. The hidden layer of RBF network was designed dynamically by virtue of the modified growing neural gas algorithm so as to realize the adaptive understanding of the continuous state space. Based on the standard Q-learning implemented by RBF network, the weighted Q-learning was used to solve the control problem with continuous action outputs. Simulation result verified the validity of the algorithm.