City Research Online

State representation learning with recurrent capsule networks

Annabi, L. and Garcia Ortiz, M. ORCID: 0000-0003-4729-7457 (2018). State representation learning with recurrent capsule networks. Paper presented at the Workshop on Modeling the Physical World: Perception, Learning, and Control, NeurIPS 2018 - 32nd Conference on Neural Information Processing Systems, 07 Dec 2018, Montreal, Canada.

Abstract

Unsupervised learning of compact and relevant state representations has beenproved very useful at solving complex reinforcement learning tasks Ha and Schmid-huber (2018). In this paper, we propose a recurrent capsule network Hinton et al.(2011) that learns such representations by trying to predict the future observationsin an agent’s trajectory

Publication Type: Conference or Workshop Item (Paper)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments: School of Mathematics, Computer Science & Engineering > Computer Science
URI: http://openaccess.city.ac.uk/id/eprint/22453
[img]
Preview
Text - Accepted Version
Download (417kB) | Preview

Export

Downloads

Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login