Data-driven stability of stochastic mean-field type games via noncooperative neural network adversarial training
Date
2024-03
Journal Title
Journal ISSN
Volume Title
Publisher
John Wiley and Sons Inc
Abstract
We propose an approach to neural network stochastic differential games of mean-field type and its corresponding stochastic stability analysis by means of adversarial training (aka adversarial attacks). This is a class of data-driven differential games where the distribution of the variables such as the system states and the decision-makers' strategies (control inputs) is incorporated into the problem. This work casts the cooperative/noncooperative game terminology into the deep learning framework where we talk about cooperative and noncooperative neural network computations that involve learning capabilities and neural network architectures. We suggest a method to computationally validate the feasibility of the approximated solutions via neural networks and evaluate the stochastic stability of the associated closed-loop system (state feedback Nash). Moreover, we enhance the stochastic stability by enlarging the training set with adversarial initial states to obtain a more robust neural network for a particular decision-maker. Finally, a worked-out example based on the linear-quadratic mean-field type game (LQ-MTG) that illustrates our methodology is presented. © 2023 Chinese Automatic Control Society and John Wiley & Sons Australia, Ltd.
Description
item.page.type
Conference Paper
item.page.format
Keywords
adversarial training, data-driven differential games, neural networks, robustness, stochastic mean-field type games, stochastic stability, supervised machine learning
Citation
Barreiro‐Gomez, J., & Choutri, S. E. (2024). Data‐driven stability of stochastic mean‐field type games via noncooperative neural network adversarial training. Asian Journal of Control, 26(2), 778-789. https://doi.org/10.1002/asjc.3175