arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.08493cs.MAcs.AIcs.LGcs.RO

自主移动接入应用中无人机集群的协调多智能体强化学习

Coordinated Multi-Agent Reinforcement Learning for Unmanned Aerial Vehicle Swarms in Autonomous Mobile Access Applications

Korea University(高丽大学);Ajou University(亚洲大学)

Chanyoung Park, Haemin Lee, Won Joon Yun, Soyi Jung, Joongheon Kim

AI总结:

本文针对自主移动接入场景,提出基于CTDE的多智能体深度强化学习方法,用单一神经网络集中训练多无人机协作,以最大化总服务质量。

摘要:

本文提出了一种新颖的基于集中式训练与分布式执行(CTDE)的多智能体深度强化学习(MADRL)方法,用于自主移动接入应用中多架无人机(UAV)的控制。为此,在集中式训练中利用单一神经网络实现多个智能体之间的协作,同时最大化移动接入应用中的总服务质量(QoS)。

英文摘要:

This paper proposes a novel centralized training and distributed execution (CTDE)-based multi-agent deep reinforcement learning (MADRL) method for multiple unmanned aerial vehicles (UAVs) control in autonomous mobile access applications. For the purpose, a single neural network is utilized in centralized training for cooperation among multiple agents while maximizing the total quality of service (QoS) in mobile access applications.

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。

↑