Empirical Inference Conference Paper 2008

Policy Learning: A Unified Perspective with Applications in Robotics

Policy Learning approaches are among the best suited methods for high-dimensional, continuous control systems such as anthropomorphic robot arms and humanoid robots. In this paper, we show two contributions: firstly, we show a unified perspective which allows us to derive several policy learning algorithms from a common point of view, i.e, policy gradient algorithms, natural-gradient algorithms and EM-like policy learning. Secondly, we present several applications to both robot motor primitive learning as well as to robot control in task space. Results both from simulation and several different real robots are shown.

Author(s): Peters, J. and Kober, J. and Nguyen-Tuong, D.
Book Title: EWRL 2008
Journal: Recent Advances in Reinforcement Learning: 8th European Workshop (EWRL 2008)
Pages: 220-228
Year: 2008
Month: November
Day: 0
Editors: Girgin, S. , M. Loth, R. Munos, P. Preux, D. Ryabko
Publisher: Springer
Bibtex Type: Conference Paper (inproceedings)
Address: Berlin, Germany
DOI: 10.1007/978-3-540-89722-4_17
Event Name: 8th European Workshop on Reinforcement Learning
Event Place: Villeneuve d‘Ascq, France
Digital: 0
Electronic Archiving: grant_archive
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik
Links:

BibTex

@inproceedings{5177,
  title = {Policy Learning: A Unified Perspective with Applications in Robotics},
  journal = {Recent Advances in Reinforcement Learning: 8th European Workshop (EWRL 2008)},
  booktitle = {EWRL 2008},
  abstract = {Policy Learning approaches are among the best suited methods for high-dimensional, continuous control systems such as anthropomorphic robot arms and humanoid robots. In this paper, we show two contributions: firstly, we show a unified perspective which allows us to derive several policy learning algorithms from a common point of view, i.e, policy gradient algorithms, natural-gradient algorithms and EM-like policy learning. Secondly, we present several applications to both robot motor primitive learning as well as to robot control in task space. Results both from simulation and several different real robots are shown.},
  pages = {220-228},
  editors = {Girgin, S. , M. Loth, R. Munos, P. Preux, D. Ryabko},
  publisher = {Springer},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Berlin, Germany},
  month = nov,
  year = {2008},
  slug = {5177},
  author = {Peters, J. and Kober, J. and Nguyen-Tuong, D.},
  month_numeric = {11}
}