arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.01613math.OCcs.LGcs.NAmath.NA
收藏

平均场控制与对策数值解的机器学习算法的收敛性分析:II --有限时域情形

Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games: II -- The Finite Horizon Case

René Carmona, Mathieu Laurière

摘要:

本文提出了有限时域McKean-Vlasov动力学最优控制的两种数值方法。这两种方法都是基于引入一个合适的损失函数定义的神经网络的参数。这允许使用机器学习工具和随机梯度下降的有效实现,以便执行优化。在第一种方法中,损失函数直接源于最优控制问题。第二种方法处理一个通用的前向-后向随机微分方程系统(FBSLP)的McKean-Vlasov型,并依赖于适当的平均场控制问题的重新制定。为了保证我们的数值方案如何近似的原始平均场控制问题的解决方案,我们引入了一个新的最优化问题,直接服从数值计算,我们严格提供了一个差错率。提供了几个数值例子。这两种方法都可以很容易地应用于具有共同噪声的某些问题,而现有技术则不是这种情况。此外,虽然第一种方法是为平均场控制问题而设计的,但第二种方法更一般,也可以应用于平均场博弈理论中产生的FBBND。

英文摘要:

We propose two numerical methods for the optimal control of McKean-Vlasov dynamics in finite time horizon. Both methods are based on the introduction of a suitable loss function defined over the parameters of a neural network. This allows the use of machine learning tools, and efficient implementations of stochastic gradient descent in order to perform the optimization. In the first method, the loss function stems directly from the optimal control problem. The second method tackles a generic forward-backward stochastic differential equation system (FBSDE) of McKean-Vlasov type, and relies on suitable reformulation as a mean field control problem. To provide a guarantee on how our numerical schemes approximate the solution of the original mean field control problem, we introduce a new optimization problem, directly amenable to numerical computation, and for which we rigorously provide an error rate. Several numerical examples are provided. Both methods can easily be applied to certain problems with common noise, which is not the case with the existing technology. Furthermore, although the first approach is designed for mean field control problems, the second is more general and can also be applied to the FBSDE arising in the theory of mean field games.

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。

↑