Policy gradient methods
From Scholarpedia
| This article has not been peer-reviewed or accepted for publication yet; It may be unfinished, contain inaccuracies, or unapproved changes. | ||||||||||||||||||||
Author: Dr. Jan Peters, Max-Planck Institute, Germany & University of Southern California, USC
on Amazon.Dr. Jan Peters accepted the invitation on 27 April 2007
This article will briefly cover: the state of the art in policy gradient methods starting with the policy gradient theorem and ending with the Natural Actor-Critic.
| Invited by: | Dr. Eugene M. Izhikevich, Editor-in-Chief of Scholarpedia, the peer-reviewed open-access encyclopedia |
