Kun Zhang, Yoichiro Maeda, and Yasutake Takahashi

Abstract:
Research on multi-agent systems, in which autonomous agents are able to learn cooperative behavior, has been the subject of rising expectations in recent years. We have aimed at the group behavior generation of the multi-agents who have high levels of autonomous learning ability, like that of human beings, through social interaction between agents to acquire cooperative behavior. The sharing of environment states can improve cooperative ability, and the changing state of the environment in the information shared by agents will improve agents¡Ç cooperative ability. On this basis, we use reward redistribution among agents to reinforce group behavior, and we propose a method of constructing a multi-agent system with an autonomous group creation ability. This is able to strengthen the cooperative behavior of the group as social agents.

Keywords: group behavior learning, multi-agent systems, reinforcement learning, state communication, social interaction