no code implementations • 1 Jan 2021 • Luca Lach, Timo Korthals, Malte Schilling, Helge Ritter
Therefore, this paper investigates the issues of joint training approaches and explores incorporation of policy gradients from RL into the VAE's latent space to find a task-specific latent space representation.
1 code implementation • 21 May 2020 • Malte Schilling, Kai Konen, Frank W. Ohl, Timo Korthals
Locomotion is a prime example for adaptive behavior in animals and biological control principles have inspired control architectures for legged robots.
no code implementations • 1 Nov 2019 • Timo Korthals, Malte Schilling, Jürgen Leitner
This contribution comprises the interplay between a multi-modal variational autoencoder and an environment to a perceived environment, on which an agent can act.
no code implementations • ICLR 2019 • Timo Korthals, Marc Hesse, Jürgen Leitner
The application of multi-modal generative models by means of a Variational Auto Encoder (VAE) is an upcoming research topic for sensor fusion and bi-directional modality exchange.
no code implementations • 18 Mar 2019 • Timo Korthals
This work gives an in-depth derivation of the trainable evidence lower bound obtained from the marginal joint log-Likelihood with the goal of training a Multi-Modal Variational Autoencoder (M$^2$VAE).
no code implementations • 12 Sep 2018 • Timo Korthals, Jürgen Leitner, Ulrich Rückert
We investigate a reinforcement approach for distributed sensing based on the latent space derived from multi-modal deep generative models.