Distributed Control of Network Systems in the Space of Stabilizing Graph Neural Network Policies
For control engineers and researchers, it provides a method to ensure stability in distributed reinforcement learning with GNN policies, though the approach is incremental over existing Youla parameterizations.
This paper introduces a policy parameterization that embeds Graph Neural Networks into a Youla-like framework to guarantee closed-loop stability for distributed control of networked systems, validated through numerical experiments.
We study distributed control of networked systems through reinforcement learning, where neural policies must be simultaneously scalable, expressive and stabilizing. We introduce a policy parameterization that embeds Graph Neural Networks (GNNs) into a Youla-like magnitude-direction parameterization, yielding distributed stochastic controllers that guarantee network-level closed-loop stability by design. The magnitude is implemented as a stable operator consisting of a GNN acting on disturbance feedback, while the direction is a GNN acting on local observations. We prove robustness of the policy to perturbations in both the graph topology and model parameters. Numerical experiments validate the effectiveness of the proposed approach.