DyNODE: Neural Ordinary Differential Equations for Dynamics Modeling in Continuous Control

2020/09/09 by V. M. Martinez Alvarez, Alvarez, Victor M. Martinez, Rares Rosca +3 · 2 citations
Computer Science · Engineering · #Advanced Control Systems Optimization #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #Reinforcement Learning in Robotics #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2009.04278

openalex publication_date 2020/09/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present a novel approach (DyNODE) that captures the underlying dynamics of a system by incorporating control in a neural ordinary differential equation framework. We conduct a systematic evaluation and comparison of our method and standard neural network architectures for dynamics modeling. Our results indicate that a simple DyNODE architecture when combined with an actor-critic reinforcement learning (RL) algorithm that uses model predictions to improve the critic's target values, outperforms canonical neural networks, both in sample efficiency and predictive performance across a diverse range of continuous tasks that are frequently used to benchmark RL algorithms. This approach provides a new avenue for the development of models that are more suited to learn the evolution of dynamical systems, particularly useful in the context of model-based reinforcement learning. To assist related work, we have made code available at https://github.com/vmartinezalvarez/DyNODE .

Citations

• Learning Continuous Control Policies by Stochastic Value Gradients
• End-to-End Training of Deep Visuomotor Policies
• Guided Policy Search as Approximate Mirror Descent
• Model-Ensemble Trust-Region Policy Optimization
• Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning
• Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• Benchmarking Model-Based Reinforcement Learning

Cited by

• Linear Power System Modeling and Analysis Across Wide Operating Ranges: A Hierarchical Neural State-Space Equation Approach
• G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration

Related

• ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence
• Control of dynamical systems with neural networks
• Identifying Ordinary Differential Equations for Data-efficient Model-based Reinforcement Learning
• Neural Control: Concurrent System Identification and Control Learning with Neural ODE
• Unconstrained Parametrization of Dissipative and Contracting Neural Ordinary Differential Equations