A Hierarchical Reinforcement Learning Algorithm Based On Heuristic Reward Function

摘要：

A hierarchical reinforcement learning method based on heuristic reward function is proposed to solve the problem of curse of dimcnsionality, that is the states space will grow exponentially in the number of features, and low convergence speed. The method can reduce state spaces greatly and can enhance the speed of the study. Choose actions with favorable purpose and efficiency so as to optimize reward function and enhance convergence speed. Apply this method to the Tetris game; the experiment result shows that the method can partly solve the curse of dimensionality and can enhance the convergence speed prominent.

关键词： hierarchical reinforcement learning heuristic reward function Tetris curse of dimensionality

作者: Qicui Yan Quan Liu Daojing Hu

作者单位: School of Computer Science and Technology Soochow University Suzhou, Jiangsu, 215006, China

会议类型: 国际会议

会议名称: The 2nd IEEE International Conference on Advanced Computer Control(第二届先进计算机控制国际会议 ICACC 2010)

会议地点: 沈阳

会议语种:英文

页码: 371-376

在线出版日期: 2010-03-27（万方平台首次上网日期，不代表论文的发表时间）