arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.11551math.OCcs.NAmath.NA
收藏

一个平均场对策反问题

A mean field game inverse problem

Lisang Ding, Wuchen Li, Stanley Osher, Wotao Yin

摘要:

平均场博弈出现在包括经济学、工程学和机器学习在内的各个领域。他们研究大群体中的战略决策,其中个体通过某些平均场量相互作用。比赛的地面指标和运行成本至关重要,但往往是未知的或只有部分已知。在本文中,我们提出了平均场博弈反问题模型,以重建地面指标和相互作用的核心,在运行成本。观测的是宏观运动,具体来说,密度分布和速度场的代理。它们在一定程度上会被噪声破坏。我们的模型是偏微分方程约束的最优化问题,可以用一阶原对偶方法求解。此外,我们使用Bregman迭代法来寻找最佳的模型参数。我们数值证明,我们的模型是有效的和强大的噪声。

英文摘要:

Mean-field games arise in various fields including economics, engineering, and machine learning. They study strategic decision making in large populations where the individuals interact via certain mean-field quantities. The ground metrics and running costs of the games are of essential importance but are often unknown or only partially known. In this paper, we propose mean-field game inverse-problem models to reconstruct the ground metrics and interaction kernels in the running costs. The observations are the macro motions, to be specific, the density distribution, and the velocity field of the agents. They can be corrupted by noise to some extent. Our models are PDE constrained optimization problems, which are solvable by first-order primal-dual methods. Besides, we apply Bregman iterations to find the optimal model parameters. We numerically demonstrate that our model is both efficient and robust to noise.

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。

↑