mlsanityData to 14 Oct 2026

Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approach

arXiv 2112.09046 ↗First posted 16 Dec 2021eess.SY cs.LG cs.SYcited by 12

Not on the map. Why?

Abstract (arXiv)

Large-scale cyber-physical systems require that control policies are distributed, that is, that they only rely on local real-time measurements and communication with neighboring agents. Optimal Distributed Control (ODC) problems are, however, highly intractable even in seemingly simple cases. Recent work has thus proposed training Neural Network (NN) distributed controllers. A main challenge of NN controllers is that they are not dependable during and after training, that is, the closed-loop system may be unstable, and the training may fail due to vanishing and exploding gradients. In this paper, we address these issues for networks of nonlinear port-Hamiltonian (pH) systems, whose modeling power ranges from energy systems to non-holonomic vehicles and chemical reactions. Specifically, we embrace the compositional properties of pH systems to characterize deep Hamiltonian control policies with built-in closed-loop stability guarantees, irrespective of the interconnection topology and the chosen NN parameters. Furthermore, our setup enables leveraging recent results on well-behaved neural ODEs to prevent the phenomenon of vanishing gradients by design. Numerical experiments corroborate the dependability of the proposed architecture, while matching the performance of general neural network policies.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 20 of its 38 references that are in the map. First posted on arXiv 16 Dec 2021.

Builds on

20 of 38 references.

References · 20

  1. 2018Neural Ordinary Differential Equationscited by 3,779
  2. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
  3. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 366
  4. 2015Unitary Evolution Recurrent Neural Networkscited by 294
  5. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 289
  6. 2018Learning-based Model Predictive Control for Safe Explorationcited by 120
  7. 2018The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systemscited by 88
  8. 2017On orthogonality and learning recurrent networks with long term dependenciescited by 83
  9. 2017Orthogonal Recurrent Neural Networks with Scaled Cayley Transformcited by 83
  10. 2019Learning Decentralized Controllers for Robot Swarms with Graph Neural Networkscited by 62
  11. 2021Hamiltonian-based Neural ODE Networks on the SE(3) Manifold For Dynamics Learning and Controlcited by 38
  12. 2019Graph Policy Gradients for Large Scale Robot Controlcited by 28
8 more
  1. 2021Hamiltonian Deep Neural Networks Guaranteeing Non-vanishing Gradients by Designcited by 18
  2. 2020An Ode to an ODEcited by 17
  3. 2020Offset-free setpoint tracking using neural network controllerscited by 10
  4. 2021Communication Topology Co-Design in Graph Recurrent Neural Network Based Distributed Controlcited by 7
  5. 2020Graph Neural Networks for Distributed Linear-Quadratic Controlcited by 5
  6. 2021Learning Deep Energy Shaping Policies for Stability-Guaranteed Manipulationcited by 5
  7. 2021A unified framework for Hamiltonian deep neural networkscited by 4
  8. 2021A Unified Passivity-Based Framework for Control of Modular Islanded AC Microgridscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 1; 2024: 3; 2025: 2; 2026: 1.

12 papers.

  1. 2022Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applicationscited by 30
  2. 2022Compositional Learning of Dynamical System Models Using Port-Hamiltonian Neural Networkscited by 18
  3. 2022Neural System Level Synthesis: Learning over All Stabilizing Policies for Nonlinear Systemscited by 11
  4. 2022Thermodynamics of learning physical phenomenacited by 10
  5. 2023How to Learn and Generalize From Three Minutes of Data: Physics-Constrained and Uncertainty-Aware Neural Stochastic Differential Equationscited by 10
  6. 2022Differentiable Safe Controller Design through Control Barrier Functionscited by 8
  7. 2024Learning to Boost the Performance of Stable Nonlinear Systemscited by 7
  8. 2024Neural Port-Hamiltonian Differential Algebraic Equations for Compositional Learning of Electrical Networkscited by 2
  9. 2025L2RU: a Structured State Space Model with prescribed L2-boundcited by 1
  10. 2026Controller Design for Structured State-space Models via Contraction Theorycited by 1
  11. 2024Structured Deep Neural Network-Based Backstepping Trajectory Tracking Control for Lagrangian Systemscited by 0
  12. 2025Distributed Control of Network Systems in the Space of Stabilizing Graph Neural Network Policiescited by 0