Neural Network Approximation of Optimal Controls for Stochastic Reaction-Diffusion Equations
arXiv:2301.11926 · doi:10.1063/5.0143939
Abstract
We present a numerical algorithm that allows the approximation of optimal controls for stochastic reaction-diffusion equations with additive noise by first reducing the problem to controls of feedback form and then approximating the feedback function using finitely based approximations. Using structural assumptions on the finitely based approximations, rates for the approximation error of the cost can be obtained. Our algorithm significantly reduces the computational complexity of finding controls with asymptotically optimal cost. Numerical experiments using artificial neural networks as well as radial basis function networks illustrate the performance of our algorithm. Our approach can also be applied to stochastic control problems for high dimensional stochastic differential equations and more general stochastic partial differential equations.
arXiv comment12 figures
References in corpus (9)
- DGM: A deep learning algorithm for solving partial differential equations
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
- Deep splitting method for parabolic PDEs
- Polynomial approximation of high-dimensional Hamilton-Jacobi-Bellman equations and applications to feedback control of semilinear parabolic PDEs
- Peng's Maximum Principle for Stochastic Partial Differential Equations
- Solving high-dimensional parabolic PDEs using the tensor train format
- Deterministic Control of Stochastic Reaction-Diffusion Equations
- Neural Network Approximation of Optimal Controls for Stochastic Reaction-Diffusion Equations