arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.00165cs.MA
收藏

面向去中心化多智能体强化学习的动态图通信

Dynamic Graph Communication for Decentralised Multi-Agent Reinforcement Learning

Ben McClusky

AI总结:

本文提出一种面向动态网络环境的去中心化多智能体通信框架,通过图注意力网络与多轮通信目标定位机制优化路由决策,在稀疏奖励环境中提升平均奖励9.5%并降低通信开销6.4%。

摘要:

本文提出了一种面向在动态网络环境中运行的去中心化多智能体系统的新型通信框架。该框架集成到多智能体强化学习系统中,旨在通过高效通信优化网络的集体知识,从而增强决策能力。主要贡献包括:将静态网络数据包路由场景适配到具有节点故障的动态环境;在循环消息传递框架中引入图注意力网络层;并提出一种多轮通信目标定位机制。该方法使得基于注意力的聚合机制能够在稀疏奖励、动态网络数据包路由环境中仅通过强化学习成功训练。实验结果表明路由性能得到改善,与基线系统相比,平均奖励提高了9.5%,通信开销降低了6.4%。本研究还探讨了在关键基础设施和军事场景中部署此类系统的伦理与法律影响,指出了当前局限性,并提出了未来研究的潜在方向。

英文摘要:

This work presents a novel communication framework for decentralized multi-agent systems operating in dynamic network environments. Integrated into a multi-agent reinforcement learning system, the framework is designed to enhance decision-making by optimizing the network's collective knowledge through efficient communication. Key contributions include adapting a static network packet-routing scenario to a dynamic setting with node failures, incorporating a graph attention network layer in a recurrent message-passing framework, and introducing a multi-round communication targeting mechanism. This approach enables an attention-based aggregation mechanism to be successfully trained within a sparse-reward, dynamic network packet-routing environment using only reinforcement learning. Experimental results show improvements in routing performance, including a 9.5 percent increase in average rewards and a 6.4 percent reduction in communication overhead compared to a baseline system. The study also examines the ethical and legal implications of deploying such systems in critical infrastructure and military contexts, identifies current limitations, and suggests potential directions for future research.

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。

↑