Near-optimal control of dynamical systems with neural ordinary differential equations

TL;DR

This paper investigates how hyperparameters like network structure, initialization, and optimization affect the performance of neural ODE controllers in solving optimal control problems for dynamical systems, aiming for near-optimal solutions.

Contribution

It provides a detailed analysis of hyperparameter effects on neural ODE control performance and introduces methods for efficient hyperparameter optimization in complex control tasks.

Findings

Backpropagation method impacts runtime and learning ability.

Initialization and optimizer choices significantly influence control accuracy.

Neural ODE controllers implicitly regularize control energy.

Abstract

Optimal control problems naturally arise in many scientific applications where one wishes to steer a dynamical system from a certain initial state $\mathbf{x}_0$ to a desired target state $\mathbf{x}^*$ in finite time $T$. Recent advances in deep learning and neural network-based optimization have contributed to the development of methods that can help solve control problems involving high-dimensional dynamical systems. In particular, the framework of neural ordinary differential equations (neural ODEs) provides an efficient means to iteratively approximate continuous time control functions associated with analytically intractable and computationally demanding control tasks. Although neural ODE controllers have shown great potential in solving complex control problems, the understanding of the effects of hyperparameters such as network structure and optimizers on learning performance is still very limited. Our work aims at addressing some of these knowledge gaps to conduct efficient hyperparameter optimization. To this end, we first analyze how truncated and non-truncated backpropagation through time affect runtime performance and the ability of neural networks to learn optimal control functions. Using analytical and numerical methods, we then study the role of parameter initializations, optimizers, and neural-network architecture. Finally, we connect our results to the ability of neural ODE controllers to implicitly regularize control energy.