RT Conference Proceedings
SR 00
A1 Annabi, L.
A1 Garcia Ortiz, M.
T1 State representation learning with recurrent capsule networks
YR 2018
FD 07 Dec 2018
AB 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
T2 Workshop on Modeling the Physical World: Perception, Learning, and Control, NeurIPS 2018 - 32nd Conference on Neural Information Processing Systems
ED Montreal, Canada
AV Unpublished
LK https://openaccess.city.ac.uk/id/eprint/22453/