Policy Learning for Motor Skills

Peters, J; Schaal, S

doi:10.1007/978-3-540-69162-4_25

Local TagsRelease HistoryDetailsSummary

Policy Learning for Motor Skills

Peters, J., & Schaal, S. (2008). Policy Learning for Motor Skills. In M. Ishikawa, K. Doya, H. Miyamoto, & T. yamakawa (Eds.), Neural Information Processing: 14th International Conference, ICONIP 2007, Kitakyushu, Japan, November 13-16 (pp. 233-242). Berlin, Germany: Springer.

Item is Released

show all hide all

Basic

show hide

Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-C909-7 Version Permalink: http://hdl.handle.net/21.11116/0000-0003-432B-2

Genre: Conference Paper

Files

show Files

Locators

show

hide

Locator:
https://link.springer.com/content/pdf/10.1007%2F978-3-540-69162-4_25.pdf (Publisher version)

Description:
-

Creators

show

hide

Creators:
Peters, J^{1, 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, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794

Content

show

hide

Free keywords: -

Abstract: Policy learning which allows autonomous robots to adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this paper, we investigate the ingredients for a general approach policy learning with the goal of an application to motor skill refinement in order to get one step closer towards human-like performance. For doing so, we study two major components for such an approach, i.e., firstly, we study policy learning algorithms which can be applied in the general setting of motor skill learning, and, secondly, we study a theoretically well-founded general approach to representing the required control structures for task representation and execution.

Details

show

hide

Language(s):

Dates: Published in Print: 2008-06

Publication Status: Published in print

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: DOI: 10.1007/978-3-540-69162-4_25
BibTex Citekey: 4869

Degree: -

Event

show

hide

Title: 14th International Conference on Neural Information Processing (ICONIP 2007)

Place of Event: Kitakyushu, Japan

Start-/End Date: 2007-11-13 - 2007-11-16

Legal Case

show

Project information

show

Source 1

show

hide

Title: Neural Information Processing: 14th International Conference, ICONIP 2007, Kitakyushu, Japan, November 13-16

Source Genre: Proceedings

Creator(s):
Ishikawa, M, Editor
Doya, K, Editor
Miyamoto, H, Editor
yamakawa, T, Editor

Affiliations:
-

Publ. Info: Berlin, Germany : Springer

Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 233 - 242 Identifier: ISBN: 978-3-540-69159-4