IEEE - Institute of Electrical and Electronics Engineers, Inc. - Off-line path integral reinforcement learning using stochastic robot dynamics approximated by sparse pseudo-input Gaussian processes: Application to humanoid robot motor learning in the real environment

2013 IEEE International Conference on Robotics and Automation (ICRA)

Author(s): Norikazu Sugimoto ; Jun Morimoto
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 May 2013
Conference Location: Karlsruhe, Germany
Conference Date: 6 May 2013
Page(s): 1,311 - 1,316
ISBN (Electronic): 978-1-4673-5643-5
ISBN (Paper): 978-1-4673-5641-1
ISSN (Paper): 1050-4729
DOI: 10.1109/ICRA.2013.6630740
Regular:

We develop fast reinforcement learning (RL) framework using the approximated dynamics of a humanoid robot. Although RL is a useful non-linear optimizer, applying it to real robotic systems is... View More

Advertisement