By Topic

The importance of variance reduction in policy gradient method

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Tak Kit Lau ; Dept. of Mech. & Autom. Eng., Chinese Univ. of Hong Kong, Hong Kong, China ; Yun-hui Liu

Reinforcement learning (RL) has been applied to a wide range of motion control problems in robotics. In particular, policy gradient method (PGM) emerges as a powerful subset of RL that can learn effectively from one's experience. However, when the dynamics is stochastic and is short of samples for learning, the performance of PGM becomes inconsistent and heavily relies on the tweaking of the learning rate. In this work, we argue that this degeneration is mainly due to the high variance in the gradient. Through theoretical justifications, simulations and experiments, we verify that by applying a variance suppression, which is called local baseline, on the gradient, PGM can then be applied to some previously untouchable problems.

Published in:

American Control Conference (ACC), 2012

Date of Conference:

27-29 June 2012