Towards Self-Adaptive Resilient Swarms Using Multi-Agent Reinforcement Learning
Towards Self-Adaptive Resilient Swarms Using Multi-Agent Reinforcement Learning
复制标题
DOI：
10.5220/0012462800003654
复制
发表时间：
2024
期刊：
影响因子：
--
通讯作者：
Rafael Pina;V. D. Silva;Corentin Artaud
中科院分区：
文献类型：
--
作者：
Rafael Pina;V. D. Silva;Corentin Artaud
：合作群的智能代理最近已被用于几个不同的应用领域。有能力让几个单位一起工作来完成一项任务，可以大大扩展可以解决的挑战范围。然而，这些群集是由容易遭受外部攻击甚至内部故障的机器组成的。如果蜂群中的某些元素出现故障，其他元素必须能够适应队友的故障，并仍然实现目标。在本文中，我们研究了可能的故障在成群的合作代理的影响，通过使用多智能体强化学习（MARL）。更具体地说，我们研究了当一个或多个队友在训练期间开始表现异常时，MARL代理的反应以及如何转移到测试中。我们的研究结果表明，虽然普通的MARL方法可能能够适应简单的缺陷，但当这些缺陷变得更加复杂时，它们就不能很好地适应。在这个意义上，我们展示了如何独立学习者可以作为一个潜在的方向，未来的研究，以适应故障群使用MARL。通过这项工作，我们希望能够激励进一步的研究，使用MARL创建更强大的智能群。
: Cooperative swarms of intelligent agents have been used recently in several different fields of application. The ability to have several units working together to accomplish a task can drastically extend the range of challenges that can be solved. However, these swarms are composed of machines that are susceptible to suffering external attacks or even internal failures. In cases where some of the elements of the swarm fail, the others must be capable of adjusting to the malfunctions of the teammates and still achieve the objectives. In this paper, we investigate the impact of possible malfunctions in swarms of cooperative agents through the use of Multi-Agent Reinforcement Learning (MARL). More specifically, we investigate how MARL agents react when one or more teammates start acting abnormally during their training and how that transfers to testing. Our results show that, while common MARL methods might be able to adjust to simple flaws, they do not adapt well when these become more complex. In this sense, we show how independent learners can be used as a potential direction of future research to adapt to malfunctions in swarms using MARL. With this work, we hope to motivate further research to create more robust intelligent swarms using MARL.