Stable reinforcement learning with autoencoders for tactile and visual data

Herke van Hoof(Amsterdam University of the Arts), Jan Peters(Technische Universität Darmstadt), Nutan Chen(Technical University of Munich), Patrick van der Smagt(Fortiss), Maximilian Karl(Technical University of Munich)
Unknown
October 1, 2016
Cited by 143


Related Papers

Reinforcement learning in robotics: A survey
|The International Journal of Robotics Research|2013|3.1k
Natural Actor-Critic
|Neurocomputing|2008|751
Model learning for robot control: a survey
|Cognitive Processing|2011|503