arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.23174cs.GT
收藏

近似求解具有有限状态空间的连续时间均场博弈

Approximately Solving Continuous-Time Mean Field Games with Finite State Spaces

Technische Universität Darmstadt(达姆施塔特工业大学);Huawei Technologies Co., Ltd.(华为技术有限公司)

Yannick Eich, Christian Fabian, Kai Cui, Heinz Koeppl

AI总结:

本文提出了一种基于正则化方法的近似算法,用于求解具有有限状态空间的连续时间均场博弈问题,通过扩展固定点迭代和假想玩法规则,提高了计算效率和实用性。

摘要:

均场博弈(MFGs)提供了一个强大的框架,用于建模大规模多智能体系统。本文研究了在连续时间中定义、具有离散状态空间的MFGs,其中智能体的动力学由连续时间马尔可夫链控制,这在种群动态和排队网络等应用中具有相关性。尽管先前研究主要集中在连续时间离散状态MFGs的理论方面,但有效计算方法仍不完善。受离散时间方法的启发,我们通过正则化方法近似经典纳什均衡,从而获得更易于计算的求解算法。具体而言,我们定义了连续时间MFGs的正则化均衡,并将经典固定点迭代法和假想玩法规则扩展到这些均衡上。我们通过示例性数值实验验证了我们方法的有效性和实用性。

英文摘要:

Mean field games (MFGs) offer a powerful framework for modeling large-scale multi-agent systems. This paper addresses MFGs formulated in continuous time with discrete state spaces, where agents' dynamics are governed by continuous-time Markov chains -- relevant to applications like population dynamics and queueing networks. While prior research has largely focused on theoretical aspects of continuous-time discrete-state MFGs, efficient computational methods for determining equilibria remain underdeveloped. Inspired by discrete-time approaches, we approximate the classical Nash equilibria by regularization methods, enabling more computationally tractable solution algorithms. Specifically, we define regularized equilibria for continuous-time MFGs and extend the classical fixed-point iteration and fictitious play algorithm to these equilibria. We validate the effectiveness and practicality of our approach via illustrative numerical examples.

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。

↑