Data-driven End-to-end Learning of Pole Placement Control for Nonlinear Dynamics via Koopman Invariant Subspaces

08/16/2022
by   Tomoharu Iwata, et al.
0

We propose a data-driven method for controlling the frequency and convergence rate of black-box nonlinear dynamical systems based on the Koopman operator theory. With the proposed method, a policy network is trained such that the eigenvalues of a Koopman operator of controlled dynamics are close to the target eigenvalues. The policy network consists of a neural network to find a Koopman invariant subspace, and a pole placement module to adjust the eigenvalues of the Koopman operator. Since the policy network is differentiable, we can train it in an end-to-end fashion using reinforcement learning. We demonstrate that the proposed method achieves better performance than model-free reinforcement learning and model-based control with system identification.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/15/2020

Deep Learning of Koopman Representation for Control

We develop a data-driven, model-free approach for the optimal control of...
research
09/08/2023

Computationally Efficient Data-Driven Discovery and Linear Representation of Nonlinear Systems For Control

This work focuses on developing a data-driven framework using Koopman op...
research
06/16/2020

Data Driven Control with Learned Dynamics: Model-Based versus Model-Free Approach

This paper compares two different types of data-driven control methods, ...
research
08/03/2023

End-to-End Reinforcement Learning of Koopman Models for Economic Nonlinear MPC

(Economic) nonlinear model predictive control ((e)NMPC) requires dynamic...
research
02/15/2023

On the Detection and Quantification of Nonlinearity via Statistics of the Gradients of a Black-Box Model

Detection and identification of nonlinearity is a task of high importanc...
research
02/03/2023

Koopman Operator Learning: Sharp Spectral Rates and Spurious Eigenvalues

Non-linear dynamical systems can be handily described by the associated ...
research
02/19/2021

CKNet: A Convolutional Neural Network Based on Koopman Operator for Modeling Latent Dynamics from Pixels

For systems with only known pixels, it is difficult to identify its dyna...

Please sign up or login with your details

Forgot password? Click here to reset