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

06/22/2022
by   Lucas Böttcher, et al.
0

Optimal control problems naturally arise in many scientific applications where one wishes to steer a dynamical system from a certain initial state 𝐱_0 to a desired target state 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.

READ FULL TEXT

page 12

page 13

page 25

research
03/11/2021

Implicit energy regularization of neural ordinary-differential-equation control

Although optimal control problems of dynamical systems can be formulated...
research
06/16/2020

Neural Optimal Control for Representation Learning

The intriguing connections recently established between neural networks ...
research
05/24/2023

Neural Lyapunov and Optimal Control

Optimal control (OC) is an effective approach to controlling complex dyn...
research
08/28/2019

Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective

Attempts from different disciplines to provide a fundamental understandi...
research
11/08/2020

Learning Neural Event Functions for Ordinary Differential Equations

The existing Neural ODE formulation relies on an explicit knowledge of t...
research
11/24/2018

Forward Stability of ResNet and Its Variants

The residual neural network (ResNet) is a popular deep network architect...
research
06/25/2023

A Neural RDE approach for continuous-time non-Markovian stochastic control problems

We propose a novel framework for solving continuous-time non-Markovian s...

Please sign up or login with your details

Forgot password? Click here to reset