arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.03265cs.AIcs.MA
收藏

基于超图神经网络的多Agent系统策略生成

Efficient Policy Generation in Multi-Agent Systems via Hypergraph Neural Network

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)

Bin Zhang, Yunpeng Bai, Zhiwei Xu, Dapeng Li, Guoliang Fan

摘要:

深度强化学习在多智能体系统中的应用带来了额外的挑战。在一个有众多代理的场景中,目前正在解决的最重要的问题之一是如何在不同的代理之间建立足够的协作。针对这一问题,考虑了基于邻域的Agent交互形式,提出了一种基于actor-critic方法的多智能体强化学习(MARL)算法,该算法能够自适应地构造表示Agent交互的超图结构,并通过超图卷积网络进一步实现有效的信息抽取和表示学习,从而实现有效的协作.基于不同的超图生成方法,我们提出了两种变体:行动者超图卷积批评网络(HGAC)和行动者注意力超图批评网络(ATT-HGAC)。不同设置的实验表明,我们的方法比其他现有的方法的优势。

英文摘要:

The application of deep reinforcement learning in multi-agent systems introduces extra challenges. In a scenario with numerous agents, one of the most important concerns currently being addressed is how to develop sufficient collaboration between diverse agents. To address this problem, we consider the form of agent interaction based on neighborhood and propose a multi-agent reinforcement learning (MARL) algorithm based on the actor-critic method, which can adaptively construct the hypergraph structure representing the agent interaction and further implement effective information extraction and representation learning through hypergraph convolution networks, leading to effective cooperation. Based on different hypergraph generation methods, we present two variants: Actor Hypergraph Convolutional Critic Network (HGAC) and Actor Attention Hypergraph Critic Network (ATT-HGAC). Experiments with different settings demonstrate the advantages of our approach over other existing methods.

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。

↑