Publikation
Policy Learning - A Unified Perspective with Applications in Robotics
Jan Peters; Jens Kober; Duy Nguyen-Tuong
In: Sertan Girgin; Manuel Loth; Rémi Munos; Philippe Preux; Daniil Ryabko (Hrsg.). Recent Advances in Reinforcement Learning, 8th European Workshop, Revised and Selected Papers. European Workshop on Reinforcement Learning (EWRL-2008), June 30 - July 3, Villeneuve d'Ascq, France, Pages 220-228, Lecture Notes in Computer Science, Vol. 5323, Springer, 2008.
Zusammenfassung
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.