mlsanityData to 14 Oct 2026

Control of dynamical systems with neural networks

arXiv 2510.12810 ↗First posted 6 Oct 2025eess.SY cs.LG cs.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

Control problems frequently arise in scientific and industrial applications, where the objective is to steer a dynamical system from an initial state to a desired target state. Recent advances in deep learning and automatic differentiation have made applying these methods to control problems increasingly practical. In this paper, we examine the use of neural networks and modern machine-learning libraries to parameterize control inputs across discrete-time and continuous-time systems, as well as deterministic and stochastic dynamics. We highlight applications in multiple domains, including biology, engineering, physics, and medicine. For continuous-time dynamical systems, neural ordinary differential equations (neural ODEs) offer a useful approach to parameterizing control inputs. For discrete-time systems, we show how custom control-input parameterizations can be implemented and optimized using automatic-differentiation methods. Overall, the methods presented provide practical solutions for control tasks that are computationally demanding or analytically intractable, making them valuable for complex real-world applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 43 of its 135 references that are in the map. First posted on arXiv 6 Oct 2025.

Builds on

43 of 135 references.

References · 43

  1. 2018Neural Ordinary Differential Equationscited by 3,779
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  3. 2014Deep Learning in Neural Networks: An Overviewcited by 770
  4. 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 599
  5. 2018Is Q-learning Provably Efficient?cited by 487
  6. 2016Input Convex Neural Networkscited by 414
  7. 2022Conformal prediction beyond exchangeabilitycited by 355
  8. 2019Improving Sample Efficiency in Model-Free Reinforcement Learning from Imagescited by 274
  9. 2019Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learningcited by 212
  10. 2019Symplectic ODE-Net: Learning Hamiltonian Dynamics with Controlcited by 184
  11. 2017Sparse identification of nonlinear dynamics for model predictive control in the low-data limitcited by 140
  12. 2022Safe Planning in Dynamic Environments using Conformal Predictioncited by 119
31 more
  1. 2017Continuously Differentiable Exponential Linear Unitscited by 73
  2. 2017Deep Reinforcement Learning for Sepsis Treatmentcited by 71
  3. 2019Pontryagin Differentiable Programming: An End-to-End Learning and Control Frameworkcited by 52
  4. 2021Optimal control of PDEs using physics-informed neural networkscited by 52
  5. 2022LyaNet: A Lyapunov Framework for Training Neural ODEscited by 44
  6. 2021Implicit energy regularization of neural ordinary-differential-equation controlcited by 29
  7. 2022Automatic Differentiation of Programs with Discrete Randomnesscited by 29
  8. 2023Physics-Informed Machine Learning for Modeling and Control of Dynamical Systemscited by 28
  9. 2021KNODE-MPC: A Knowledge-based Data-driven Predictive Control Framework for Aerial Robotscited by 26
  10. 2020Neural Ordinary Differential Equation Control of Dynamics on Graphscited by 24
  11. 2022Interpretable Polynomial Neural Ordinary Differential Equationscited by 24
  12. 2023A Survey on Physics Informed Reinforcement Learning: Review and Open Problemscited by 24
  13. 2022Differentiable Agent-based Epidemiologycited by 21
  14. 2022Physics-Informed Model-Based Reinforcement Learningcited by 18
  15. 2020Input Convex Neural Networks for Building MPCcited by 17
  16. 2018Why ReLU Units Sometimes Die: Analysis of Single-Unit Error Backpropagation in Neural Networkscited by 12
  17. 2024Uncertainty Quantification of Surrogate Models using Conformal Predictioncited by 11
  18. 2022Near-optimal control of dynamical systems with neural ordinary differential equationscited by 9
  19. 2023Gradient-free training of neural ODEs for system identification and control using ensemble Kalman inversioncited by 9
  20. 2024Surrogate Modeling and Control of Medical Digital Twinscited by 8
  21. 2022Control of Dual-Sourcing Inventory Systems using Recurrent Neural Networkscited by 6
  22. 2024What You See is Not What You Get: Neural Partial Differential Equations and The Illusion of Learningcited by 5
  23. 2022Neural ODEs as Feedback Policies for Nonlinear Optimal Controlcited by 4
  24. 2024Control of Medical Digital Twins with Artificial Neural Networkscited by 3
  25. 2025Synchronization of Kuramoto oscillators via HEOL, and a discussion on AIcited by 3
  26. 2020A stochastic approach to the synchronization of coupled oscillatorscited by 2
  27. 2023Koopman-Based Surrogate Models for Multi-Objective Optimization of Agent-Based Systemscited by 1
  28. 2024Hardware Neural Control of CartPole and F1TENTH Race Carcited by 1
  29. 2024Koopman operator based identification of nonlinear networkscited by 1
  30. 2025Deep Learning Model Predictive Control for Deep Brain Stimulation in Parkinson's Diseasecited by 1
  31. 2025Opt-ODENet: A Neural ODE Framework with Differentiable QP Layers for Safe and Stable Control Design (longer version)cited by 1

Built on by

Not cited yet.