Neural networks for first order HJB equations and application to front propagation with obstacle terms

TL;DR

This paper develops neural network methods to solve first-order Hamilton-Jacobi-Bellman equations in deterministic control problems, with applications to front propagation models involving obstacle constraints, providing error estimates and numerical validation.

Contribution

It introduces a new neural network approach tailored for deterministic HJB equations, extending previous stochastic methods and addressing error propagation without diffusion.

Findings

Effective for dimensions 2 to 8

Handles non-smooth value functions

Provides precise average norm error estimates

Abstract

We consider a deterministic optimal control problem with a maximum running cost functional, in a finite horizon context, and propose deep neural network approximations for Bellman's dynamic programming principle, corresponding also to some first-order Hamilton-Jacobi-Bellman equations. This work follows the lines of Hur\'e et al. (SIAM J. Numer. Anal., vol. 59 (1), 2021, pp. 525-557) where algorithms are proposed in a stochastic context. However, we need to develop a completely new approach in order to deal with the propagation of errors in the deterministic setting, where no diffusion is present in the dynamics. Our analysis gives precise error estimates in an average norm. The study is then illustrated on several academic numerical examples related to front propagations models in the presence of obstacle constraints, showing the relevance of the approach for average dimensions (e.g. from $2$ to $8$), even for non-smooth value functions.