DyNODE: Neural Ordinary Differential Equations for Dynamics Modeling in Continuous Control
This work addresses the challenge of learning system dynamics for model-based reinforcement learning, offering a novel approach that could improve efficiency in continuous control applications.
The authors tackled the problem of dynamics modeling in continuous control by proposing DyNODE, a neural ODE framework that incorporates control, and found that it outperforms standard neural networks in sample efficiency and predictive performance across diverse RL benchmark tasks.
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 .