Saved in:
Bibliographic Details
Main Authors: Tomar, Manan, Hansen-Estruch, Philippe, Bachman, Philip, Lamb, Alex, Langford, John, Taylor, Matthew E., Levine, Sergey
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.09533
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866907978199728128
author Tomar, Manan
Hansen-Estruch, Philippe
Bachman, Philip
Lamb, Alex
Langford, John
Taylor, Matthew E.
Levine, Sergey
author_facet Tomar, Manan
Hansen-Estruch, Philippe
Bachman, Philip
Lamb, Alex
Langford, John
Taylor, Matthew E.
Levine, Sergey
contents We introduce a new family of video prediction models designed to support downstream control tasks. We call these models Video Occupancy models (VOCs). VOCs operate in a compact latent space, thus avoiding the need to make predictions about individual pixels. Unlike prior latent-space world models, VOCs directly predict the discounted distribution of future states in a single step, thus avoiding the need for multistep roll-outs. We show that both properties are beneficial when building predictive models of video for use in downstream control. Code is available at \href{https://github.com/manantomar/video-occupancy-models}{\texttt{github.com/manantomar/video-occupancy-models}}.
format Preprint
id arxiv_https___arxiv_org_abs_2407_09533
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Video Occupancy Models
Tomar, Manan
Hansen-Estruch, Philippe
Bachman, Philip
Lamb, Alex
Langford, John
Taylor, Matthew E.
Levine, Sergey
Computer Vision and Pattern Recognition
Artificial Intelligence
We introduce a new family of video prediction models designed to support downstream control tasks. We call these models Video Occupancy models (VOCs). VOCs operate in a compact latent space, thus avoiding the need to make predictions about individual pixels. Unlike prior latent-space world models, VOCs directly predict the discounted distribution of future states in a single step, thus avoiding the need for multistep roll-outs. We show that both properties are beneficial when building predictive models of video for use in downstream control. Code is available at \href{https://github.com/manantomar/video-occupancy-models}{\texttt{github.com/manantomar/video-occupancy-models}}.
title Video Occupancy Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2407.09533