English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Reinforcement learning by reward-weighted regression for operational space control

Peters, J., & Schaal, S. (2007). Reinforcement learning by reward-weighted regression for operational space control. In Z. Ghahramani (Ed.), ICML '07: 24th International Conference on Machine Learning (pp. 745-750). New York, NY, USA: ACM Press.

Item is

Files

show Files
hide Files
:
ICML-2007-Peters.pdf (Any fulltext), 399KB
Name:
ICML-2007-Peters.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show
hide
Description:
-

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: Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of the known optimization or reinforcement learning algorithms can be used in online learning control for robots, as they are either prohibitively slow, do not scale to interesting domains of complex robots, or require trying out policies generated by random search, which are infeasible for a physical system. Using a generalization of the EM-base reinforcement learning framework suggested by Dayan amp;amp;amp;amp; Hinton, we reduce the problem of learning with immediate rewards to a reward-weighted regression problem with an adaptive, integrated reward transformation for faster convergence. The resulting algorithm is efficient, learns smoothly without dangerous jumps in solution space, and works well in applications of complex high degreeof-freedom robots.

Details

show
hide
Language(s):
 Dates: 2007-06
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1145/1273496.1273590
BibTex Citekey: 4493
 Degree: -

Event

show
hide
Title: 24th Annual International Conference on Machine Learning (ICML 2007)
Place of Event: Corvallis, OR, USA
Start-/End Date: 2007-06-20 - 2007-06-24

Legal Case

show

Project information

show

Source 1

show
hide
Title: ICML '07: 24th International Conference on Machine Learning
Source Genre: Proceedings
 Creator(s):
Ghahramani, Z, Editor
Affiliations:
-
Publ. Info: New York, NY, USA : ACM Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 745 - 750 Identifier: ISBN: 978-1-59593-793-3