A Pursuit-Evasion Algorithm Based on Hierarchical Reinforcement Learning

摘要：

This paper proposed a pursuit-evasion algorithm based on the Option method from hierarchical reinforcement learning and applied it into multi-robot pursuitevasion game in 2D-Dynamic environment. The algorithm efficiency is studied by comparing it with Q-learning. We decompose the complex task with option method, and divide the learning process into two parts: High-level learning and Lowlevel learning, then design a new mechanism in order to make the learning process perform parallel. The simulation result shows the Option algorithm can efficiently reduce the complexity of pursuit-evasion task, avoid traditional reinforcement learning curse of dimensionality, and improve the learning result.

关键词： Pursuit Evasion Problem Reinforcement Learning

作者: Jie Liu Shuhua Liu Hongyan Wu Yu Zhang

作者单位: Computer Science School Northeast Normal University Changchun,China,130117

会议类型: 国际会议

会议名称: 2009 International Conference on Measuring Technology and Mechatronics Automation(ICMTMA 2009)(2009年检测技术与机械自动化国际会议)

会议地点: 长沙

会议语种:英文

页码: 1426-1430

在线出版日期: 2009-04-11（万方平台首次上网日期，不代表论文的发表时间）