Neural optimal controller for stochastic systems via pathwise HJB operator

The aim of this work is to develop deep learning-based algorithms for high-dimensional stochastic control problems based on physics-informed learning and dynamic programming. Unlike classical deep learning-based methods relying on a probabilistic representation of the solution to the Hamilton--Jacobi--Bellman (HJB) equation, we introduce a pathwise operator associated with the HJB equation so that we can define a problem of physics-informed learning. According to whether the optimal control has an explicit representation, two numerical methods are proposed to solve the physics-informed learning problem. We provide an error analysis on how the truncation, approximation and optimization errors affect the accuracy of these methods. Numerical results on various applications are presented to illustrate the performance of the proposed algorithms.