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

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 .

9 pages, 5 figures

References in corpus (9)

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