中国科学院自动化研究所机构知识库

This paper presents an approach for learning the evasion strategy for the evader in pursuit-evasion against the pursuers with Deep Q-network (DQN). To give the immediate reward to the agent, we handcraft a reward function, which considers both the evader escaping from being surrounded by the pursuers and keeping distance from the pursuers. This is a combination of the artificial potential field method with deep reinforcement learning. Our learned evasion strategy is verified by a series of experiments in three different game scenarios. The training stability and the value function are analyzed respectively. The three learned agents are compared with a random agent and a repulsive agent. We show the effectiveness of our method.