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, naturalgradient 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.

• Type: Conference
• Year: 2008
• Where: EWRL
• Authors: Jan Peters, Jens Kober, Duy Nguyen-Tuong
• Keywords: EWRL 2008, Machine Learning, Policy Gradient Algorithms, Policy Learning Algorithms, Policy Learning Approaches