arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.09705cs.AI
收藏

分布式多Agent深度强化学习抗噪声鲁棒协调

Distributed Multi-Agent Deep Reinforcement Learning for Robust Coordination against Noise

Waseda University(早稻田大学)

Yoshinari Motokawa, Toshiharu Sugawara

摘要:

在多智能体系统中,降噪技术对于提高整个系统的可靠性非常重要,因为智能体需要依赖有限的环境信息来与周围的智能体开发合作和协调的行为。然而,以前的研究往往采用集中式降噪方法,在嘈杂的多智能体环境中建立强大的和通用的协调,而分布式和分散的自主智能体更合理的现实世界的应用。在本文中,我们介绍了一个\emph{distributed attentional actor architecture model for a multi-agent system}(DA 3-X),使用它,我们证明了与DA 3-X的代理可以有选择地学习噪声环境和合作行为。我们通过比较使用和不使用DA 3-X的学习方法来实验评估DA 3-X的有效性,并表明使用DA 3-X的代理可以比基线代理实现更好的性能。此外,我们可视化DA 3-X的\emph{attentional weights}热图,以分析决策过程和协调行为如何受到噪声的影响。

英文摘要:

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.

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。

↑