Latent Representation Prediction Networks
Hlynsson, H. D.,
Schüler, M.,
Schiewer, R.,
Glasmachers, T., &
Wiskott, L.arXiv preprint arXiv:2009.09439
@article{HlynssonSchülerSchiewerEtAl2020,
author = {Hlynsson, Hlynur Davíð and Schüler, Merlin and Schiewer, Robin and Glasmachers, Tobias and Wiskott, Laurenz},
title = {Latent Representation Prediction Networks},
journal = {arXiv preprint arXiv:2009.09439},
year = {2020},
}
Winter Term 2021/2022
Summer Term 2021
Winter Term 2020/2021
Summer Term 2020
Summer Term 2019
Pairing the EfferenceNet with a good but generic feature map allows us to perform an accurate search in the latent space of manipulating unseen objects. This remarkably simple method, inspired by the neurology of the cerebellum, reveals a promising line of future work. We validate our method by on a viewpoint-matching task derived from the NORB data set.
In model-free multi-task reinforcement learning (RL), abundant work shows that a shared policy network can improve performance across the different tasks. The rationale behind this is that an agent can learn similarities that all tasks have in common and thus effectively enrich the sample count for all tasks at hand. In model-based multi-task RL however, we found evidence suggesting that a dynamics model can suffer from task confusion or catastrophic interference if it is trained on multiple tasks at once.