Derives a Riccati-free coupled FBSDE system for mean-field Stackelberg games with random coefficients via extended Lagrange multipliers and proposes a Deep FBSDE Picard Solver with neural augmented Lagrangian for numerical solution.
Deep fictitious play for stochastic differential games
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CMAD formulates compositional generation as cooperative stochastic optimal control among pre-trained diffusion models, validated on conditional MNIST against a gradient-guidance baseline.
citing papers explorer
-
Stochastic Mean-Field LQ Stackelberg Differential Games with Random Coefficients: Theory and a Deep FBSDE Picard Solver
Derives a Riccati-free coupled FBSDE system for mean-field Stackelberg games with random coefficients via extended Lagrange multipliers and proposes a Deep FBSDE Picard Solver with neural augmented Lagrangian for numerical solution.
-
CMAD: Cooperative Multi-Agent Diffusion via Stochastic Optimal Control
CMAD formulates compositional generation as cooperative stochastic optimal control among pre-trained diffusion models, validated on conditional MNIST against a gradient-guidance baseline.