mlsanityData to 14 Oct 2026

Distributed Control of Network Systems in the Space of Stabilizing Graph Neural Network Policies

arXiv 2512.18540 ↗First posted 20 Dec 2025eess.SY cs.LG cs.SYcited by 0

On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 16 of its 23 references that are in the map. First posted on arXiv 20 Dec 2025.

Builds on

16 of 23 references.

References · 16

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 506
  4. 2018Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulatorcited by 250
  5. 2019Stability Properties of Graph Neural Networkscited by 127
  6. 2022Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregationcited by 36
  7. 2024GCBF+: A Neural Graph Control Barrier Function Framework for Distributed Safe Multi-Agent Controlcited by 22
  8. 2021Learning over All Stabilizing Nonlinear Controllers for a Partially-Observed Linear Systemcited by 14
  9. 2021Distributed Linear-Quadratic Control with Graph Neural Networkscited by 12
  10. 2021Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approachcited by 12
  11. 2022Neural System Level Synthesis: Learning over All Stabilizing Policies for Nonlinear Systemscited by 11
  12. 2023On Safety and Liveness Filtering Using Hamilton-Jacobi Reachability Analysiscited by 11
4 more
  1. 2024Learning to Boost the Performance of Stable Nonlinear Systemscited by 7
  2. 2022KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Dynamical Systemscited by 5
  3. 2024Optimal distributed control with stability guarantees by training a network of neural closed-loop mapscited by 4
  4. 2025MAD: A Magnitude And Direction Policy Parametrization for Stability Constrained Reinforcement Learningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2020Synthesizing Decentralized Controllers with Graph Neural Networks and Imitation Learning
  2. 2026Mean-Field Control on Sparse Graphs: From Local Limits to GNNs via Neighborhood Distributions
  3. 2024Fully Distributed Online Training of Graph Neural Networks in Networked Systems
  4. 2024Scalable Reinforcement Learning for Linear-Quadratic Control of Networks
  5. 2026Decentralized Learning Strategies for Estimation Error Minimization with Graph Neural Networks
  6. 2026Complex-Valued GNNs for Distributed Basis-Invariant Control of Planar Systems
  7. 2026Scalable Policy Optimization for Networked Multi-Agent Reinforcement Learning with Continuous State-Action Spaces
  8. 2024Distributed Policy Gradient for Linear Quadratic Networked Control with Limited Communication Range