Edinburgh Research Archive logo

Edinburgh Research Archive

University of Edinburgh homecrest
View Item 
  •   ERA Home
  • Informatics, School of
  • Informatics Publications
  • View Item
  •   ERA Home
  • Informatics, School of
  • Informatics Publications
  • View Item
  • Login
JavaScript is disabled for your browser. Some features of this site may not work without it.

Value Function Approximation on Non-Linear Manifolds for Robot Motor Control

Robotics and Automation

View/Open
0948.pdf (978.3Kb)
Date
04/2007
Author
Sugiyama, Masashi
Hachiya, Hirotaka
Towell, Christopher
Vijayakumar, Sethu
Metadata
Show full item record
Abstract
The least squares approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular and useful choice as a basis function. However, it does not allow for discontinuity which typically arises in realworld reinforcement learning tasks. In this paper, we propose a new basis function based on geodesic Gaussian kernels, which exploits the non-linear manifold structure induced by the Markov decision processes. The usefulness of the proposed method is successfully demonstrated in a simulated robot arm control and Khepera robot navigation.
URI
http://hdl.handle.net/1842/3714
Collections
  • Informatics Publications
  • Informatics Report Series

Library & University Collections HomeUniversity of Edinburgh Information Services Home
Privacy & Cookies | Takedown Policy | Accessibility | Contact
Privacy & Cookies
Takedown Policy
Accessibility
Contact
feed RSS Feeds

RSS Feed not available for this page

 

 

All of ERACommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsPublication TypeSponsorSupervisorsThis CollectionBy Issue DateAuthorsTitlesSubjectsPublication TypeSponsorSupervisors
LoginRegister

Library & University Collections HomeUniversity of Edinburgh Information Services Home
Privacy & Cookies | Takedown Policy | Accessibility | Contact
Privacy & Cookies
Takedown Policy
Accessibility
Contact
feed RSS Feeds

RSS Feed not available for this page