Data-driven stability of stochastic mean-field type games via noncooperative neural network adversarial training

DOI10.1002/ASJC.3175MaRDI QIDQ6583308FDOQ6583308

Authors: Julian Barreiro-Gomez, Salah Eddine Choutri 

Publication date: 6 August 2024

Published in: Asian Journal of Control (Search for Journal in Brave)

Recommendations

• Deep fictitious play for stochastic differential games
• A dynamical neural network approach for solving stochastic two-player zero-sum games
• A General Framework for Learning Mean-Field Games
• Game on Random Environment, Mean-Field Langevin System, and Neural Networks

zbMATH Keywords

robustnessneural networksstochastic stabilitysupervised machine learningadversarial trainingdata-driven differential gamesstochastic mean-field type games

Mathematics Subject Classification ID

Systems theory; control (93-XX)

Cites Work

• Mean field games
• Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
• Probabilistic analysis of mean-field games
• Mean field games and mean field type control theory
• A general stochastic maximum principle for SDEs of mean-field type
• Stochastic maximum principle in the mean-field controls
• A maximum principle for SDEs of mean-field type
• Anonymous sequential games
• A stochastic maximum principle for general mean-field systems
• Mean field type control with congestion. II: An augmented Lagrangian method
• Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games. I: The ergodic case
• Hierarchical mean-field type control of price dynamics for electricity in smart grid
• Hierarchical structures and leadership design in mean-field-type games with polynomial cost

This page was built for publication: Data-driven stability of stochastic mean-field type games via noncooperative neural network adversarial training

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6583308)