Task-Oriented Koopman-Based Control with Contrastive Encoder

We present task-oriented Koopman-based control that utilizes end-to-end reinforcement learning and contrastive encoder to simultaneously learn the Koopman latent embedding, operator, and associated linear controller within an iterative loop. By prioritizing the task cost as the main objective for co...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-11
Main Authors: Lyu, Xubo, Hu, Hanyang, Siriya, Seth, Ye Pu, Chen, Mo
Format: Article
Language:English
Subjects:
Coders
Control systems design
Controllers
Iterative methods
Nonlinear systems
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present task-oriented Koopman-based control that utilizes end-to-end reinforcement learning and contrastive encoder to simultaneously learn the Koopman latent embedding, operator, and associated linear controller within an iterative loop. By prioritizing the task cost as the main objective for controller learning, we reduce the reliance of controller design on a well-identified model, which, for the first time to the best of our knowledge, extends Koopman control from low to high-dimensional, complex nonlinear systems, including pixel-based tasks and a real robot with lidar observations. Code and videos are available \href{https://sites.google.com/view/kpmlilatsupp/}{here}.
ISSN:2331-8422