论文标题
平均现场游戏的政策迭代方法
A policy iteration method for Mean Field Games
论文作者
论文摘要
政策迭代方法是一种用于解决最佳控制问题的经典算法。在本文中，我们介绍了一种用于平均现场游戏系统的策略迭代方法，并研究了该过程与问题解决方案的融合。我们还引入了合适的离散化，以在数值上解决固定问题和进化问题。我们显示了离散问题的策略迭代方法的收敛性，并在维度一和两个方面的某些示例中研究了拟议算法的性能。
The policy iteration method is a classical algorithm for solving optimal control problems. In this paper, we introduce a policy iteration method for Mean Field Games systems, and we study the convergence of this procedure to a solution of the problem. We also introduce suitable discretizations to numerically solve both stationary and evolutive problems. We show the convergence of the policy iteration method for the discrete problem and we study the performance of the proposed algorithm on some examples in dimension one and two.
