Learning a model of dynamics from high-dimensional images can be a core ingredient for success in many applications across different domains, especially in sequential decision making. However, currently prevailing methods based on latent-variable models are limited to working with low resolution images only. In this work, we show that some of the issues with using high-dimensional observations arise from the discrepancy between the dimensionality of the latent and observable space, and propose solutions to overcome them.
@article{arxiv.1911.00756,
title = {Beta DVBF: Learning State-Space Models for Control from High Dimensional Observations},
author = {Neha Das and Maximilian Karl and Philip Becker-Ehmck and Patrick van der Smagt},
journal= {arXiv preprint arXiv:1911.00756},
year = {2019}
}