Predictive Control Using Learned State Space Models via Rolling Horizon Evolution

A large part of the interest in model-based reinforcement learning derives from the potential utility to acquire a forward model capable of strategic long term decision making. Assuming that an agent succeeds in learning a useful predictive model, it still requires a mechanism to harness it to gener...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Ovalle, Alvaro, Lucas, Simon M
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 25.06.2021
Subjects
Decision making
Deep learning
Machine learning
Prediction models
Predictive control
State space models
Visual tasks
Online AccessGet full text

Cover

More Information
Summary:A large part of the interest in model-based reinforcement learning derives from the potential utility to acquire a forward model capable of strategic long term decision making. Assuming that an agent succeeds in learning a useful predictive model, it still requires a mechanism to harness it to generate and select among competing simulated plans. In this paper, we explore this theme combining evolutionary algorithmic planning techniques with models learned via deep learning and variational inference. We demonstrate the approach with an agent that reliably performs online planning in a set of visual navigation tasks.
ISSN:2331-8422