arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2208.01430cs.MA
收藏

多智能体异构交互问题的一个模型

A Model for Multi-Agent Heterogeneous Interaction Problems

Christopher D. Hsu, Mulugeta A. Haile, Pratik Chaudhari

AI总结:

本文提出一个受免疫系统启发的多智能体交互模型,利用交叉反应核使防御团队以极少类型智能体最优对抗异构攻击者,并提炼控制原则,与强化学习等方法对比。

摘要:

我们引入了一个多智能体交互问题的模型,以理解异构智能体团队应如何组织其资源来应对异构攻击者团队。该模型的灵感来源于人体免疫系统如何应对多种病原体。该模型的关键属性是一个“交叉反应”核,它使得特定的防御者类型能够对某些攻击者类型做出强烈反应,而对少数不同类型的攻击者反应较弱。我们展示了由于这种交叉反应,防御者团队能够仅使用极少种类的防御智能体来最优地对抗异构攻击者团队,从而最小化其资源。我们在不同设置下研究该模型,以刻画针对异构智能体团队控制问题的一系列指导原则,例如,伤害对次优防御者分布的敏感性,以及防御者之间的竞争通过分散计算实现接近最优的控制行为。我们还将该模型与现有方法进行了比较,包括强化学习策略、边界防御和覆盖控制。

英文摘要:

We introduce a model for multi-agent interaction problems to understand how a heterogeneous team of agents should organize its resources to tackle a heterogeneous team of attackers. This model is inspired by how the human immune system tackles a diverse set of pathogens. The key property of this model is a ``cross-reactivity'' kernel which enables a particular defender type to respond strongly to some attacker types but weakly to a few different types of attackers. We show how due to such cross-reactivity, the defender team can optimally counteract a heterogeneous attacker team using very few types of defender agents, and thereby minimize its resources. We study this model in different settings to characterize a set of guiding principles for control problems with heterogeneous teams of agents, e.g., sensitivity of the harm to sub-optimal defender distributions, and competition between defenders gives near-optimal behavior using decentralized computation of the control. We also compare this model with existing approaches including reinforcement-learned policies, perimeter defense, and coverage control.

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。

↑