论文标题
分布式的多代理深钢筋学习，以抗噪声的强大协调
Distributed Multi-Agent Deep Reinforcement Learning for Robust Coordination against Noise
论文作者
论文摘要
在多机构系统中，降噪技术对于提高整体系统的可靠性很重要，因为必须依靠有限的环境信息来与周围药物开发合作和协调的行为。但是，以前的研究经常采用集中式降噪方法来在嘈杂的多机构环境中构建强大和多功能的协调，而分布式和分散的自主剂对于现实世界应用更合理。在本文中，我们引入了一个多代理系统}（DA3-X）的\ emph {分布式的注意参与者体系结构模型，我们证明了具有DA3-X的代理可以有选择地学习嘈杂的环境并进行合作。我们通过比较带有和不带有DA3-X的学习方法来实验评估DA3-X的有效性，并表明具有DA3-X的代理可以比基线药物获得更好的性能。此外，我们可视化从DA3-X的\ emph {注意权重}的热图，以分析决策过程和协调行为如何受噪声影响。
In multi-agent systems, noise reduction techniques are important for improving the overall system reliability as agents are required to rely on limited environmental information to develop cooperative and coordinated behaviors with the surrounding agents. However, previous studies have often applied centralized noise reduction methods to build robust and versatile coordination in noisy multi-agent environments, while distributed and decentralized autonomous agents are more plausible for real-world application. In this paper, we introduce a \emph{distributed attentional actor architecture model for a multi-agent system} (DA3-X), using which we demonstrate that agents with DA3-X can selectively learn the noisy environment and behave cooperatively. We experimentally evaluate the effectiveness of DA3-X by comparing learning methods with and without DA3-X and show that agents with DA3-X can achieve better performance than baseline agents. Furthermore, we visualize heatmaps of \emph{attentional weights} from the DA3-X to analyze how the decision-making process and coordinated behavior are influenced by noise.
