Deep intrinsically motivated continuous actor-critic for efficient robotic visuomotor skill learning

In this paper, we present a new intrinsically motivated actor-critic algorithm for learning continuous motor skills directly from raw visual input. Our neural architecture is composed of a critic and an actor network. Both networks receive the hidden representation of a deep convolutional autoencode...

Full description

Bibliographic Details
Main Authors: Hafez Muhammad Burhan, Weber Cornelius, Kerzel Matthias, Wermter Stefan
Format: Article
Language:English
Published: De Gruyter 2019-01-01
Series:Paladyn: Journal of Behavioral Robotics
Subjects:
Online Access:https://doi.org/10.1515/pjbr-2019-0005