A Stochastic Gradient Descent Approach for Stochastic Optimal Control

A Stochastic Gradient Descent Approach for Stochastic Optimal Control

Year:    2020

Author:    Richard Archibald, Feng Bao, Jiongmin Yong

East Asian Journal on Applied Mathematics, Vol. 10 (2020), Iss. 4 : pp. 635–658

Abstract

In this work, we introduce a stochastic gradient descent approach to solve the stochastic optimal control problem through stochastic maximum principle. The motivation that drives our method is the gradient of the cost functional in the stochastic optimal control problem is under expectation, and numerical calculation of such an expectation requires fully computation of a system of forward backward stochastic differential equations, which is computationally expensive. By evaluating the expectation with single-sample representation as suggested by the stochastic gradient descent type optimisation, we could save computational efforts in solving FBSDEs and only focus on the optimisation task which aims to determine the optimal control process.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/eajam.190420.200420

East Asian Journal on Applied Mathematics, Vol. 10 (2020), Iss. 4 : pp. 635–658

Published online:    2020-01

AMS Subject Headings:   

Copyright:    COPYRIGHT: © Global Science Press

Pages:    24

Keywords:    Stochastic optimal control stochastic gradient descent maximum principle forward backward stochastic differential equations.

Author Details

Richard Archibald

Feng Bao

Jiongmin Yong

  1. Convergence Analysis for an Online Data-Driven Feedback Control Algorithm

    Liang, Siming | Sun, Hui | Archibald, Richard | Bao, Feng

    Mathematics, Vol. 12 (2024), Iss. 16 P.2584

    https://doi.org/10.3390/math12162584 [Citations: 0]
  2. Error Analysis of the Feedback Controls Arising in the Stochastic Linear Quadratic Control Problems

    Wang, Yanqing

    Journal of Systems Science and Complexity, Vol. 36 (2023), Iss. 4 P.1540

    https://doi.org/10.1007/s11424-023-1102-7 [Citations: 2]
  3. Strong rates of convergence for a space-time discretization of the backward stochastic heat equation, and of a linear-quadratic control problem for the stochastic heat equation

    Prohl, Andreas | Wang, Yanqing

    ESAIM: Control, Optimisation and Calculus of Variations, Vol. 27 (2021), Iss. P.54

    https://doi.org/10.1051/cocv/2021052 [Citations: 11]
  4. Strong error estimates for a space-time discretization of the linear-quadratic control problem with the stochastic heat equation with linear noise

    Prohl, Andreas | Wang, Yanqing

    IMA Journal of Numerical Analysis, Vol. 42 (2022), Iss. 4 P.3386

    https://doi.org/10.1093/imanum/drab069 [Citations: 6]
  5. Convergence rates of a discrete feedback control arising in mean-field linear quadraticoptimal control problems

    Yanqing, Wang

    SCIENTIA SINICA Mathematica, Vol. 53 (2023), Iss. 8 P.1145

    https://doi.org/10.1360/SCM-2021-0663 [Citations: 0]
  6. A Safe And Efficient Parameter Optimization Method For Quadrotor: Onboard Implementation And Experiment

    Yi, Feng | Zhao, Shulong | Wang, Xiangke

    2022 41st Chinese Control Conference (CCC), (2022), P.1717

    https://doi.org/10.23919/CCC55666.2022.9902057 [Citations: 0]
  7. Error analysis of a discretization for stochastic linear quadratic control problems governed by SDEs

    Wang, Yanqing

    IMA Journal of Mathematical Control and Information, Vol. 38 (2021), Iss. 4 P.1148

    https://doi.org/10.1093/imamci/dnab031 [Citations: 3]
  8. A Multilevel Monte Carlo Approach for a Stochastic Optimal Control Problem Based on the Gradient Projection Method

    Ye, Changlun | Luo, Xianbing

    AppliedMath, Vol. 3 (2023), Iss. 1 P.98

    https://doi.org/10.3390/appliedmath3010008 [Citations: 0]
  9. An Efficient Numerical Algorithm for Solving Data Driven Feedback Control Problems

    Archibald, Richard | Bao, Feng | Yong, Jiongmin | Zhou, Tao

    Journal of Scientific Computing, Vol. 85 (2020), Iss. 2

    https://doi.org/10.1007/s10915-020-01358-y [Citations: 11]