IEEE - Institute of Electrical and Electronics Engineers, Inc. - Using Parameterized Black-Box Priors to Scale Up Model-Based Policy Search for Robotics

2018 IEEE International Conference on Robotics and Automation (ICRA)

Author(s): Konstantinos Chatzilygeroudis ; Jean-Baptiste Mouret
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 May 2018
Conference Location: Brisbane, QLD, Australia
Conference Date: 21 May 2018
Page(s): 5,121 - 5,128
ISBN (Electronic): 978-1-5386-3081-5
ISBN (USB): 978-1-5386-3080-8
ISSN (Electronic): 2577-087X
DOI: 10.1109/ICRA.2018.8461083
Regular:

The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a... View More

Advertisement