基于忠诚度的多智能体联盟效用分配策略

Multi-agent System Coalition Utility Allocation Strategy Based on Loyalty

为增强多智能体系统中联盟成员效用划分的合理性,促使agent形成稳定的全局最优联盟,提出了一种基于忠诚度的多智能体联盟效用分配策略。新策略引入agent忠诚度的概念,根据agent每次参与联盟后是否服务到任务结束来对agent忠诚度进行评价,从而表示各agent的忠诚度大小,将忠诚度与各agent完成任务的能力相结合,共同决定联盟内各agent效用如何划分。理论分析和实验表明,新策略提高了对联盟效用分配的合理性,较好地满足了联盟形成机制的全局最优性、强稳定性、时效性、简单性等要求。

In order to enhance the rationality about the coalition utility allocation among agents and the stability about forming the global optimal coalition in multi-agent system,this paper proposed a coalition formation strategy based on loyalty.The new strategy introduces the conception of agent＇s loyalty,determines if one agent leaves the coalition before finishing the task or not during agent taking part in a coalition every time,and consequently evaluates the agent＇s loyalty.At the same time,the new strategy decides the coalition utility allocation by means of combining each agent＇s loyalty and their ability to finish the task.Theoretical analysis and experiment results show that the novel strategy can improve the justice of allocation for utility and achieve a global optimal solution,which is stable,speedy and simple.