Distributed Control of Network Systems in the Space of Stabilizing Graph Neural Network Policies
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911719135117312 |
|---|---|
| author | Cao, John Furieri, Luca |
| author_facet | Cao, John Furieri, Luca |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_18540 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Distributed Control of Network Systems in the Space of Stabilizing Graph Neural Network Policies Cao, John Furieri, Luca Systems and Control Machine Learning Optimization and Control 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. |
| title | Distributed Control of Network Systems in the Space of Stabilizing Graph Neural Network Policies |
| topic | Systems and Control Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2512.18540 |