Stochastic Mean-Field LQ Stackelberg Differential Games with Random Coefficients: Theory and a Deep FBSDE Picard Solver

TL;DR

This paper develops a theoretical framework and a deep learning-based numerical solver for stochastic mean-field LQ Stackelberg differential games with random coefficients, addressing complexities from mean-field interactions and randomness.

Contribution

It introduces a Riccati-free coupled FBSDE approach and a Deep FBSDE Picard Solver that maintains Stackelberg order and handles mean-field randomness.

Findings

The Deep FBSDE Picard Solver effectively converges and is stable under various conditions.

Numerical results demonstrate the solver's accuracy and robustness in different scenarios.

Application to a financial model illustrates practical utility.

Abstract

This paper studies a stochastic mean-field linear-quadratic Stackelberg differential game with random coefficients. The interaction between mean-field terms and random coefficients precludes the direct use of conventional decoupling techniques. We apply an extended Lagrange multiplier method to derive an affine operator representation of the follower's optimal response. The induced leader problem is then formulated as a generalized stochastic LQ control problem with operator-valued coefficients, and the Stackelberg optimal control is characterized through a Riccati-free coupled FBSDE system. We further develop a Deep FBSDE Picard Solver that preserves the Stackelberg order through follower-response learning, response-sensitivity extraction, leader optimization, and neural augmented Lagrangian enforcement of mean-field consistency constraints. Numerical studies covering convergence diagnostics, discretization sensitivity, Riccati calibration, ablation tests, stability under control perturbations, Stackelberg--Nash comparisons, and a financial application support the effectiveness of the proposed framework.