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.

Reinforcement Learning for Humanoid Robots - Policy Gradients and Beyond

View/Open
0220.pdf (2.654Mb)
Date
07/2004
Author
Vijayakumar, Sethu
Peters, Jan
Schaal, Stefan
Metadata
Show full item record
Abstract
Reinforcement learning offers one of the most general frameworks to take traditional robotics towards true autonomy and versatility. However, applying reinforcement learning to high dimensional movement systems like humanoid robots remains an unsolved problem. In this paper, we discuss different approaches of reinforcement learning in terms of their applicability in humanoid robotics. Methods can be coarsely classified in to three different categories, i.e., greedy methods, ’vanilla’ policy gradient methods, and natural gradient methods. We discuss that greedy methods are not likely to scale into the domain humanoid robotics as they are problematic when used with function approximation. Vanilla’ policy gradient methods on the other hand have been successfully applied on real-world robots including at least one humanoid robot [3]. We demonstrate that these methods can be significantly improved using the natural policy gradient instead of the regular policy gradient. A derivation of the natural policy gradient is provided, proving that the average policy gradient of Kakade[10] is indeed the true natural gradient. A general algorithm for estimating the natural gradient, the Natural Actor-Critic algorithm, is introduced. This algorithm converges to the nearest local minimum of the cost function with respect to the Fisher information metric under suitable conditions. The algorithm outperforms non-natural policy gradients by far in a cart-pole balancing evaluation, and for learning non-linear dynamic motor primitives for humanoid robot control. It offers a promising route for the development of reinforcement learning for truly high-dimensionally continuous state-action systems.
URI
http://hdl.handle.net/1842/3710
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