This contribution comprises the interplay between a multi-modal variational autoencoder and an environment to a perceived environment, on which an agent can act. Furthermore, we conclude our work with a comparison to curiosity-driven learning.
@article{arxiv.1911.00584,
title = {A Perceived Environment Design using a Multi-Modal Variational Autoencoder for learning Active-Sensing},
author = {Timo Korthals and Malte Schilling and Jürgen Leitner},
journal= {arXiv preprint arXiv:1911.00584},
year = {2019}
}
Comments
Extended Abstract for the IROS 2019 Workshop on Deep Probabilistic Generative Models for Cognitive Architecture in Robotics