arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.02437stat.MLcs.LG
收藏

通过动态聚类协议实现多智能体多资源分配的去中心化强化学习

Decentralized Reinforcement Learning for Multi-Agent Multi-Resource Allocation via Dynamic Cluster Agreements

Univ Rennes(雷恩大学);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所);IRISA(法国雷恩信息与自动化系统研究所)

Antonio Marino, Esteban Restrepo, Claudio Pacchierotti, Paolo Robuffo Giordano

AI总结:

本文提出了一种基于动态聚类的去中心化强化学习方法,用于多智能体多资源分配问题,实现了更稳定和鲁棒的协调性能。

摘要:

本文解决了在去中心化方式下为多个智能体分配异构资源的挑战。我们提出的方法Liquid-Graph-Time Clustering-IPPO(LGTC-IPPO)基于独立近端策略优化(IPPO),通过整合动态聚类共识机制,使智能体能够根据资源需求形成并适应局部子团队。这种去中心化协调策略减少了对全局信息的依赖并增强了可扩展性。我们评估了LGTC-IPPO与标准多智能体强化学习基线和集中专家解决方案在不同团队规模和资源分布下的性能。实验结果表明,LGTC-IPPO在智能体数量或资源类型增加时仍能实现更稳定的奖励、更好的协调性和鲁棒性。此外,我们展示了动态聚类如何使智能体能够高效重新分配资源,也适用于有放回资源的场景。

英文摘要:

This paper addresses the challenge of allocating heterogeneous resources among multiple agents in a decentralized manner. Our proposed method, Liquid-Graph-Time Clustering-IPPO, builds upon Independent Proximal Policy Optimization (IPPO) by integrating dynamic cluster consensus, a mechanism that allows agents to form and adapt local sub-teams based on resource demands. This decentralized coordination strategy reduces reliance on global information and enhances scalability. We evaluate LGTC-IPPO against standard multi-agent reinforcement learning baselines and a centralized expert solution across a range of team sizes and resource distributions. Experimental results demonstrate that LGTC-IPPO achieves more stable rewards, better coordination, and robust performance even as the number of agents or resource types increases. Additionally, we illustrate how dynamic clustering enables agents to reallocate resources efficiently also for scenarios with discharging resources.

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。

↑