论文部分内容阅读
首先介绍了基于表格Ｑ－ｌｅａｒｎｉｎｇ 的方法，然后提出了一种用神经网络实现的Ｑ－ｌｅａｒｎｉｎｇ 方法，利用这种方法实现机器人避碰行为学习，并进行了仿真试验．最后讨论了提高强化学习速度的方法．
Firstly, the method based on form Q-learning is introduced. Then a Q-learning method based on neural network is proposed. By this method, robot avoidance behavior learning is simulated and simulated. Finally, we discuss ways to improve the speed of intensive learning.