Neural networks for differential games
Preprint
Abstract
We study deterministic optimal control problems for differential games with finite horizon. We propose new approximations of the strategies in feedback form, and show error estimates and a convergence result of the value in some weak sense for one of the formulations. This result applies in particular to neural networks approximations. This work follows some ideas introduced in Bokanowski, Prost and Warin (PDEA, 2023) for deterministic optimal control problems, yet with a simplified approach for the error estimates, which allows to consider a global optimization scheme instead of a time-marching scheme. We also give a new approximation result between the continuous and the semi-discrete optimal control value in the game setting, improving the classical convergence order under some assumptions on the dynamical system. Numerical examples are performed on elementary academic problems related to backward reachability, with exact analytic solutions given, as well as a two-player game in presence of state constraints. We use stochastic gradient type algorithms in order to deal with the min-max problem.Keywords
All Related Versions
This publication has 35 references indexed in Scilit:
- Neural networks for first order HJB equations and application to front propagation with obstacle termsPartial Differential Equations and Applications, 2023
- Deep Neural Networks Algorithms for Stochastic Control Problems on Finite Horizon: Numerical ApplicationsMethodology and Computing in Applied Probability, 2021
- Suboptimal Feedback Control of PDEs by Solving HJB Equations on Adaptive Sparse GridsJournal of Scientific Computing, 2016
- Discontinuous Galerkin finite element methods for time-dependent Hamilton–Jacobi–Bellman equations with Cordes coefficientsNumerische Mathematik, 2015
- An Adaptive Sparse Grid Semi-Lagrangian Scheme for First Order Hamilton-Jacobi Bellman EquationsJournal of Scientific Computing, 2012
- Some Recent Aspects of Differential Game TheoryDynamic Games and Applications, 2010
- Numerical Methods for the Pricing of Swing Options: A Stochastic Control ApproachMethodology and Computing in Applied Probability, 2006
- Zero-sum state constrained differential games: existence of value for Bolza problemInternational Journal of Game Theory, 2006
- Optimal Control and Viscosity Solutions of Hamilton-Jacobi-Bellman Equations1997
- Existence of extended value for differential games of generalized pursuit-evasionJournal of Differential Equations, 1973