mlsanityData to 7 Oct 2026

Neural ODEs as Feedback Policies for Nonlinear Optimal Control

arXiv 2210.11245 ↗First posted 20 Oct 2022math.OC cs.AI cs.SYcited by 4

Not on the map. Why?

Abstract (arXiv)

Neural ordinary differential equations (Neural ODEs) define continuous time dynamical systems with neural networks. The interest in their application for modelling has sparked recently, spanning hybrid system identification problems and time series analysis. In this work we propose the use of a neural control policy capable of satisfying state and control constraints to solve nonlinear optimal control problems. The control policy optimization is posed as a Neural ODE problem to efficiently exploit the availability of a dynamical system model. We showcase the efficacy of this type of deterministic neural policies in two constrained systems: the controlled Van der Pol system and a bioreactor control problem. This approach represents a practical approximation to the intractable closed-loop solution of nonlinear control problems.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 22 of its 88 references that are in the map. First posted on arXiv 20 Oct 2022.

Builds on

22 of 88 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2018Neural Ordinary Differential Equationscited by 3,733
  4. 2017Constrained Policy Optimizationcited by 928
  5. 2015Automatic differentiation in machine learning: a surveycited by 846
  6. 2014Deep Learning in Neural Networks: An Overviewcited by 765
  7. 2020Universal Differential Equations for Scientific Machine Learningcited by 345
  8. 2017Stable Architectures for Deep Neural Networkscited by 340
  9. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  10. 2018Differentiable MPC for End-to-end Planning and Controlcited by 178
  11. 2019Lyapunov-based Safe Policy Optimization for Continuous Controlcited by 140
  12. 2018A Tour of Reinforcement Learning: The View from Continuous Controlcited by 129
10 more
  1. 2020Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODEcited by 76
  2. 2018Efficient representation and approximation of model predictive control laws via deep learningcited by 55
  3. 2019Pontryagin Differentiable Programming: An End-to-End Learning and Control Frameworkcited by 48
  4. 2021Continuous-Time Model-Based Reinforcement Learningcited by 39
  5. 2019DiffEqFlux.jl - A Julia Library for Neural Differential Equationscited by 33
  6. 2019Stochastic data-driven model predictive control using Gaussian processescited by 19
  7. 2020Learning Constrained Adaptive Differentiable Predictive Control Policies With Guaranteescited by 10
  8. 2020Chance Constrained Policy Optimization for Process Control and Optimizationcited by 10
  9. 2020Faster Policy Learning with Continuous-Time Gradientscited by 8
  10. 2021A Unifying Modeling Abstraction for Infinite-Dimensional Optimizationcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 2.

4 papers.

  1. 2025Machine Learning Methods for Small Data and Upstream Bioprocessing Applications: A Comprehensive Reviewcited by 4
  2. 2023Continuous-Time Reinforcement Learning: New Design Algorithms with Theoretical Insights and Performance Guaranteescited by 0
  3. 2024Lyapunov Neural ODE State-Feedback Control Policiescited by 0
  4. 2025Control of dynamical systems with neural networkscited by 0