DeepAI AI Chat
Log In Sign Up

Sparse Representation Learning with Modified q-VAE towards Minimal Realization of World Model

by   Taisuke Kobayashi, et al.
National Institute of Informatics

Extraction of low-dimensional latent space from high-dimensional observation data is essential to construct a real-time robot controller with a world model on the extracted latent space. However, there is no established method for tuning the dimension size of the latent space automatically, suffering from finding the necessary and sufficient dimension size, i.e. the minimal realization of the world model. In this study, we analyze and improve Tsallis-based variational autoencoder (q-VAE), and reveal that, under an appropriate configuration, it always facilitates making the latent space sparse. Even if the dimension size of the pre-specified latent space is redundant compared to the minimal realization, this sparsification collapses unnecessary dimensions, allowing for easy removal of them. We experimentally verified the benefits of the sparsification by the proposed method that it can easily find the necessary and sufficient six dimensions for a reaching task with a mobile manipulator that requires a six-dimensional state space. Moreover, by planning with such a minimal-realization world model learned in the extracted dimensions, the proposed method was able to exert a more optimal action sequence in real-time, reducing the reaching accomplishment time by around 20


page 13

page 16

page 17

page 20

page 23

page 24


Disentangling Variational Autoencoders

A variational autoencoder (VAE) is a probabilistic machine learning fram...

Probabilistic Autoencoder using Fisher Information

Neural Networks play a growing role in many science disciplines, includi...

FONDUE: an algorithm to find the optimal dimensionality of the latent representations of variational autoencoders

When training a variational autoencoder (VAE) on a given dataset, determ...

Improving Molecule Properties Through 2-Stage VAE

Variational autoencoder (VAE) is a popular method for drug discovery and...

GLSO: Grammar-guided Latent Space Optimization for Sample-efficient Robot Design Automation

Robots have been used in all sorts of automation, and yet the design of ...

Estimation of User's World Model Using Graph2vec

To obtain advanced interaction between autonomous robots and users, robo...

Learning a Representation Map for Robot Navigation using Deep Variational Autoencoder

The aim of this work is to use Variational Autoencoder (VAE) to learn a ...