Year: 2023
Type: preprint
Abstract: 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}.
Source: arXiv (Cornell University)
Authors: Lyu, Xubo, Hu, Hanyang, Siriya, Seth, Pu, Ye, Chen, Mo
Institution: The University of Melbourne
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4387210474