English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Natural Actor-Critic

Peters, J., & Schaal, S. (2008). Natural Actor-Critic. Neurocomputing, 71(7-9), 1180-1190. doi:10.1016/j.neucom.2007.11.026.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-CA1F-2 Version Permalink: http://hdl.handle.net/21.11116/0000-0003-315C-F
Genre: Journal Article

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Peters, J1, 2, Author              
Schaal, S, Author              
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: In this paper, we suggest a novel reinforcement learning architecture, the Natural Actor-Critic. The actor updates are achieved using stochastic policy gradients em- ploying Amari’s natural gradient approach, while the critic obtains both the natural policy gradient and additional parameters of a value function simultaneously by lin- ear regression. We show that actor improvements with natural policy gradients are particularly appealing as these are independent of coordinate frame of the chosen policy representation, and can be estimated more efficiently than regular policy gra- dients. The critic makes use of a special basis function parameterization motivated by the policy-gradient compatible function approximation. We show that several well-known reinforcement learning methods such as the original Actor-Critic and Bradtke’s Linear Quadratic Q-Learning are in fact Natural Actor-Critic algorithms. Empirical evaluations illustrate the effectiveness of our techniques in comparison to previous methods, and also demonstrate their applicability for learning control on an anthropomorphic robot arm.

Details

show
hide
Language(s):
 Dates: 2008-03
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1016/j.neucom.2007.11.026
BibTex Citekey: 4863
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Neurocomputing
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Amsterdam : Elsevier
Pages: - Volume / Issue: 71 (7-9) Sequence Number: - Start / End Page: 1180 - 1190 Identifier: ISSN: 0925-2312
CoNE: https://pure.mpg.de/cone/journals/resource/954925566733