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

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 ${\mathbf{x}}^{\ast }$ 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.

27 pages, 17 figures

References in corpus (3)

• Qualitatively characterizing neural network optimization problems
• Addressing current challenges in cancer immunotherapy with mathematical and computational modeling
• Control of Stochastic Quantum Dynamics by Differentiable Programming

Cited by in corpus (6)

• Surrogate Modeling and Control of Medical Digital Twins
• Control of Dual-Sourcing Inventory Systems using Recurrent Neural Networks
• Spectrally Adapted Physics-Informed Neural Networks for Solving Unbounded Domain Problems
• Control of dynamical systems with neural networks
• Enhancing Dynamical System Modeling through Interpretable Machine Learning Augmentations: A Case Study in Cathodic Electrophoretic Deposition
• Reconstructing Noisy Gene Regulation Dynamics Using Extrinsic-Noise-Driven Neural Stochastic Differential Equations