Stable reinforcement learning with autoencoders for tactile and visual data.

Herke van Hoof Nutan Chen Maximilian Karl Patrick van der Smagt Jan Peters

Published in: IROS (2016)

Keyphrases

visual data
reinforcement learning
visual information
contextual information
multimedia data
visual features
video sequences
image data
video data
high dimensional
high dimensional data
learning algorithm
image content
image sequences
machine learning
co occurrence
data model
object recognition