Group Behavior Learning in Multi-agent Systems Based on Social Interaction among Agents
Kun Zhang, Yoichiro Maeda, Yasutake Takahashi · University of Fukui Library (University of Fukui) · 2010
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 \tof autonomous learning ability, like that of human beings, through social interaction between agents to acquire cooperative behavior. The sharing of environment \tstates can improve cooperative ability, and \tthe changing state of the environment in the information shared by agents will improve agents’ 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 \twith an autonomous group creation ability. This is able to strengthen the cooperative behavior of the group as social agents.