English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Imitation and Reinforcement Learning for Motor Primitives with Perceptual Coupling

Kober, J., Mohler, B., & Peters, J. (2010). Imitation and Reinforcement Learning for Motor Primitives with Perceptual Coupling. In O. Sigaud, & J. Peters (Eds.), From Motor Learning to Interaction Learning in Robots (pp. 209-225). Berlin, Germany: Springer.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Kober, J1, 2, Author              
Mohler, B2, 3, Author              
Peters, J1, 2, 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              
3Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797              

Content

show
hide
Free keywords: -
 Abstract: Traditional motor primitive approaches deal largely with open-loop policies which can only deal with small perturbations. In this paper, we present a new type of motor primitive policies which serve as closed-loop policies together with an appropriate learning algorithm. Our new motor primitives are an augmented version version of the dynamical system-based motor primitives [Ijspeert et al(2002)Ijspeert, Nakanishi, and Schaal] that incorporates perceptual coupling to external variables. We show that these motor primitives can perform complex tasks such as Ball-in-a-Cup or Kendama task even with large variances in the initial conditions where a skilled human player would be challenged. We initialize the open-loop policies by imitation learning and the perceptual coupling with a handcrafted solution. We first improve the open-loop policies and subsequently the perceptual coupling using a novel reinforcement learning method which is particularly well-suited for dynamical system-based motor primitives.

Details

show
hide
Language(s):
 Dates: 2010-01
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1007/978-3-642-05181-4_10
BibTex Citekey: 6234
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: From Motor Learning to Interaction Learning in Robots
Source Genre: Book
 Creator(s):
Sigaud, O, Editor
Peters, J1, 2, Editor            
Affiliations:
1 Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795            
2 Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794            
Publ. Info: Berlin, Germany : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 209 - 225 Identifier: ISBN: 978-3-642-05181-4

Source 2

show
hide
Title: Studies in Computational Intelligence
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 264 Sequence Number: - Start / End Page: - Identifier: -