A New Approach for Solving a Control Stochastic Problem Driven by a Diffusion Process with Jumps
In this paper, we focus on the numerical solution of high-dimensional stochastic optimal control problems, whose system states are modeled as jump-diffusion processes. Through the maximum principle and deep neural networks, we restate the original control problem as a variational problem, and we introduce specialized algorithms to solve this new formulation. The algorithms and the various architectures employed have been introduced. The mean-variance portfolio selection problem in a financial market consisting of two kinds of assets in a jump-diffusion process settin