平均场对策的一种策略迭代法
A policy iteration method for Mean Field Games
摘要：
策略迭代法是求解最优控制问题的经典算法。本文介绍了平均场对策系统的一种策略迭代法，并研究了该方法的收敛性。我们还介绍了合适的离散化数值求解平稳和发展的问题。我们证明了离散问题的策略迭代法的收敛性，并在一维和二维的一些例子上研究了该算法的性能。
英文摘要：
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.
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。
