3 papers
cs.LG2026
Gaussian process policy iteration with additive Schwarz acceleration for forward and inverse HJB and mean field game problems
Xianjin Yang, Jingguo Zhang
In this paper, we propose a Gaussian Process (GP)-based policy iteration framework for addressing both forward and inverse problems in Hamilton--Jacobi--Bellman (HJB) equations and…
math.OC2026
A Globally Convergent Flow for Time-Dependent Mean Field Games and a Solver-Agnostic Framework for Inverse Problems
Hanwei Yan, Xianjin Yang, Jingguo Zhang
Mean field games (MFGs) describe the limiting behavior of large populations of strategically interacting agents. This paper addresses two numerical challenges for MFGs: globally co…
cs.LG2025
Learning Surrogate Potential Mean Field Games via Gaussian Processes: A Data-Driven Approach to Ill-Posed Inverse Problems
Jingguo Zhang, Xianjin Yang, Chenchen Mou +1
Mean field games (MFGs) describe the collective behavior of large populations of interacting agents. In this work, we tackle ill-posed inverse problems in potential MFGs, aiming to…