English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Relative Entropy Policy Search

Peters, J., Mülling, K., & Altun, Y. (2010). Relative Entropy Policy Search. In M. Fom, & D. Poole (Eds.), Twenty-Fourth National Conference on Artificial Intelligence (AAAI-10) (pp. 1607-1612). Menlo Park, CA, USA: AAAI Press.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-BF48-A Version Permalink: http://hdl.handle.net/21.11116/0000-0002-81CB-7
Genre: Conference Paper

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Peters, J1, 2, Author              
Mülling, K1, 2, Author              
Altun, Y1, 2, Author              
Fox D. Poole, M., Editor
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: Policy search is a successful approach to reinforcement learning. However, policy improvements often result in the loss of information. Hence, it has been marred by premature convergence and implausible solutions. As first suggested in the context of covariant policy gradients (Bagnell and Schneider 2003), many of these problems may be addressed by constraining the information loss. In this paper, we continue this path of reasoning and suggest the Relative Entropy Policy Search (REPS) method. The resulting method differs significantly from previous policy gradient approaches and yields an exact update step. It works well on typical reinforcement learning benchmark problems.

Details

show
hide
Language(s):
 Dates: 2010-07
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: BibTex Citekey: 6439
 Degree: -

Event

show
hide
Title: Twenty-Fourth National Conference on Artificial Intelligence (AAAI-10)
Place of Event: Atlanta, GA, USA
Start-/End Date: 2010-07-11 - 2010-07-15

Legal Case

show

Project information

show

Source 1

show
hide
Title: Twenty-Fourth National Conference on Artificial Intelligence (AAAI-10)
Source Genre: Proceedings
 Creator(s):
Fom, M, Editor
Poole, D, Editor
Affiliations:
-
Publ. Info: Menlo Park, CA, USA : AAAI Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 1607 - 1612 Identifier: ISBN: 978-1-577-35463-5