Stability Via Adversarial Training of Neural Network Stochastic Control of Mean-Field Type
This addresses stability issues in data-driven control systems for applications like multi-agent systems, but it appears incremental as it builds on existing adversarial training methods.
The paper tackles the problem of neural network mean-field-type control by using adversarial training to enhance stability, resulting in a more robust neural network validated through a linear-quadratic example.
In this paper, we present an approach to neural network mean-field-type control and its stochastic stability analysis by means of adversarial inputs (aka adversarial attacks). This is a class of data-driven mean-field-type control where the distribution of the variables such as the system states and control inputs are incorporated into the problem. Besides, we present a methodology to validate the feasibility of the approximations of the solutions via neural networks and evaluate their stability. Moreover, we enhance the stability by enlarging the training set with adversarial inputs to obtain a more robust neural network. Finally, a worked-out example based on the linear-quadratic mean-field type control problem (LQ-MTC) is presented to illustrate our methodology.