arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2410.07976stat.MLcs.LG
收藏

解决多智能体强化学习中的旋转学习动力学

Addressing Rotational Learning Dynamics in Multi-Agent Reinforcement Learning

CISPA Helmholtz Center for Information Security(CISPA亥姆霍兹信息安全中心);Universität des Saarlandes(萨尔大学);Politecnico di Milano(米兰理工大学);University of California, Berkeley(加利福尼亚大学伯克利分校)

Baraah A. M. Sidahmed, Tatjana Chavdarova

AI总结:

本文将MARL重述为变分不等式问题,并把可处理旋转动力学的梯度VI方法集成到现有算法中,从而提升均衡收敛与团队协作表现。

摘要:

多智能体强化学习(MARL)已成为一种通过智能体之间的合作与竞争来解决复杂问题的强大范式,并在各个领域得到广泛应用。尽管取得了成功,MARL仍面临可复现性危机。我们表明,这一问题在一定程度上与相互竞争的智能体目标所产生的旋转优化动力学有关,并且需要标准优化算法之外的方法。我们利用变分不等式(VIs)重新表述MARL方法,为解决此类问题提供了一个统一框架。借助为VI设计的优化技术,我们提出了一种通用方法,将能够处理旋转动力学的基于梯度的VI方法集成到现有MARL算法中。实验结果表明,其在多个基准测试中取得了显著的性能提升。在零和博弈Rock–paper–scissors和Matching pennies中,VI方法更好地收敛到均衡策略;在Multi-Agent Particle Environment: Predator-prey中,它们也增强了团队协作。这些结果凸显了先进优化技术在MARL中的变革潜力。

英文摘要:

Multi-agent reinforcement learning (MARL) has emerged as a powerful paradigm for solving complex problems through agents' cooperation and competition, finding widespread applications across domains. Despite its success, MARL faces a reproducibility crisis. We show that, in part, this issue is related to the rotational optimization dynamics arising from competing agents' objectives, and require methods beyond standard optimization algorithms. We reframe MARL approaches using Variational Inequalities (VIs), offering a unified framework to address such issues. Leveraging optimization techniques designed for VIs, we propose a general approach for integrating gradient-based VI methods capable of handling rotational dynamics into existing MARL algorithms. Empirical results demonstrate significant performance improvements across benchmarks. In zero-sum games, Rock--paper--scissors and Matching pennies, VI methods achieve better convergence to equilibrium strategies, and in the Multi-Agent Particle Environment: Predator-prey, they also enhance team coordination. These results underscore the transformative potential of advanced optimization techniques in MARL.

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。

↑