We present a method to train neural network controllers with guaranteed stability margins. The method is applicable to linear time-invariant plants interconnected with uncertainties and nonlinearities that are described by integral quadratic constraints. The type of stability margin we consider is the disk margin. Our training method alternates between a training step to maximize reward and a stability margin-enforcing step. In the stability margin enforcing-step, we solve a semidefinite program to project the controller into the set of controllers for which we can certify the desired disk margin.
@article{arxiv.2409.09184,
title = {Stability Margins of Neural Network Controllers},
author = {Neelay Junnarkar and Murat Arcak and Peter Seiler},
journal= {arXiv preprint arXiv:2409.09184},
year = {2026}
}