A Pursuit-Evasion Algorithm Based on Hierarchical Reinforcement Learning

作者：Liu, Shuhua^*; Liu, Jie; Cheng, Yu

来源：Information-An International Interdisciplinary Journal, 2010, 13(3): 635-645.

• Hierarchical Reinforcement Learning
• Option algorithm
• SMDP
• Pursuit-Evasion Strategy

This paper proposes a pursuit-evasion algorithm based on the Option method from hierarchical reinforcement learning and applies it in multi-robot pursuit-evasion games 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 Low-level learning, then design a new mechanism in order to make the learning process perform in parallel. The simulation result shows that the Option algorithm can efficiently reduce the complexity of pursuit-evasion task, avoid traditional reinforcement learning curse of dimensionality and improve the learning results.

• 出版日期2010-5
• 单位东北师范大学