关键词: Q学习算法，MAS，围捕问题，共享经验

Abstract: The aim of the research is to improve the efficicnce of multi-agent "lcaring algorithm. This paper proposed a method of multi-agent C}learning with sharing experience based on the pursuit problem. This algorithm simulats human behavior of a learning team, and all agents share a common utimate goal of capturing the prey, at the same time every agent gets their own milestones through negotiations. I}he learning process is divided into some stages. After a learning stage,there will be a stage summary. Then good learning experience will be shared with each other in order to facilitate the next stage of learning. I}he agents who learn fast and well can help the ones who learn slow and not well,so in this way the performance of the system is enhanced. The simulation results prove that the呀learning algorithm with sharing experience in learning process can improve the performance of learning systems and efficient convergence to the optimal strategy.

Key words: Q-learning algorithm, MAS, Pursuit problem, Sharing experience