DeepKoCo: Efficient latent planning with a task-relevant Koopman representation

This paper presents DeepKoCo, a novel model-based agent that learns a latent Koopman representation from images. This representation allows DeepKoCo to plan efficiently using linear control methods, such as linear model predictive control. Compared to traditional agents, DeepKoCo learns task-relevan...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-09
Main Authors: Bas van der Heijden, Ferranti, Laura, Kober, Jens, Babuska, Robert
Format: Article
Language:English
Subjects:
Control methods
Control tasks
Dynamics
Invariants
Linear control
Predictive control
Representations
Task complexity
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents DeepKoCo, a novel model-based agent that learns a latent Koopman representation from images. This representation allows DeepKoCo to plan efficiently using linear control methods, such as linear model predictive control. Compared to traditional agents, DeepKoCo learns task-relevant dynamics, thanks to the use of a tailored lossy autoencoder network that allows DeepKoCo to learn latent dynamics that reconstruct and predict only observed costs, rather than all observed dynamics. As our results show, DeepKoCo achieves similar final performance as traditional model-free methods on complex control tasks while being considerably more robust to distractor dynamics, making the proposed agent more amenable for real-life applications.
ISSN:2331-8422