State representation learning with recurrent capsule networks
Annabi, L. & 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 Science & Technology > Computer Science |
Download (417kB) | Preview
Export
Downloads
Downloads per month over past year
Metadata
MetadataActions (login required)
Admin Login