综合进化稳定的规范体系
Synthesising Evolutionarily Stable Normative Systems
摘要:
在多主体系统领域内,规范系统是协调相互依赖活动的广泛使用的框架。与规范性制度有关的一个关键问题是,如何综合各种规范,有效地完成一项协调任务,遵守这些规范构成制度内行为者的一种理性选择。在这项工作中,我们引入了一个框架的规范系统,有效地协调多代理系统,其规范可能会被理性的代理人通过的合成。我们的方法源于进化博弈论。我们的框架认为,多智能体系统中,进化的力量导致成功的规范,以繁荣和传播的代理人口,而不成功的规范被丢弃。这个进化的规范合成过程的输出是规范的系统,其遵守形式的代理人的理性选择。我们经验表明,我们的方法的有效性,通过在模拟交通领域的实证评估。
英文摘要:
Within the area of multi-agent systems, normative systems are a widely used framework for the coordination of interdependent activities. A crucial problem associated with normative systems is that of synthesising norms that effectively accomplish a coordination task and whose compliance forms a rational choice for the agents within the system. In this work, we introduce a framework for the synthesis of normative systems that effectively coordinate a multi-agent system and whose norms are likely to be adopted by rational agents. Our approach roots in evolutionary game theory. Our framework considers multi-agent systems in which evolutionary forces lead successful norms to prosper and spread within the agent population, while unsuccessful norms are discarded. The outputs of this evolutionary norm synthesis process are normative systems whose compliance forms a rational choice for the agents. We empirically show the effectiveness of our approach through empirical evaluation in a simulated traffic domain.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。