Solving Stochastic Optimal Control Problem via Stochastic Maximum Principle with Deep Learning Method
Solving Stochastic Optimal Control Problem via Stochastic Maximum Principle with Deep Learning Method
复制标题
利用深度学习方法通过随机极大值原理解决随机最优控制问题
DOI：
10.1007/s10915-022-01979-5
复制
发表时间：
2020-07
影响因子：
2.5
通讯作者：
Xichuan Zhang
中科院分区：
文献类型：
--
作者：
Shaolin Ji;Shige Peng;Ying Peng;Xichuan Zhang
In this paper, we aim to solve the high dimensional stochastic optimal control problem from the view of the stochastic maximum principle via deep learning. By introducing the extended Hamiltonian system which is essentially a Forward Backward Stochastic Differential Equation (FBSDE) with a maximum condition, we reformulate the original control problem as a new one. According to whether the optimal control has an explicit representation, three algorithms are proposed to solve the new control problem. Numerical results for different examples demonstrate the effectiveness of our proposed algorithms, especially in high dimensional cases. And even if the optimal control \\(\\tilde{u}\\) in the maximum condition may not be solved explicitly, our algorithms can still deal with the stochastic optimal control problem. An important application of our proposed method is to calculate the sub-linear expectations, which correspond to a kind of fully nonlinear Partial Differential Equations (PDEs).
登录
查看更多内容
DOI：
10.1016/0016-0032(83)90059-5
发表时间：
1983-05
影响因子：
4.1
作者：
A. Bensoussan
通讯作者：
A. Bensoussan
DOI：
--
发表时间：
1999-06
期刊：
--
影响因子：
--
作者：
J. Yong;X. Zhou
通讯作者：
J. Yong;X. Zhou
影响因子：
1.8
作者：
N. Krylov
通讯作者：
N. Krylov
DOI：
10.1007/978-3-662-59903-7
发表时间：
2010-02
期刊：
Probability Theory and Stochastic Modelling
影响因子：
--
作者：
S. Peng
通讯作者：
S. Peng
影响因子：
10.2
作者：
J. Bismut
通讯作者：
J. Bismut