ESANN
2006
14 years 1 months ago
2006
We focus on neuro-dynamic programming methods to learn state-action value functions and outline some of the inherent problems to be faced, when performing reinforcement learning in...
ICRA
1995
IEEE
14 years 4 months ago
1995
IEEE
This paper presents a method of vision-based reinforcement learning by which a robot learns to shoot a ball into a goal, and discusses several issues in applying the reinforcement...
ICRA
2009
IEEE
14 years 7 months ago
2009
IEEE
Abstract— Least-squares policy iteration is a useful reinforcement learning method in robotics due to its computational efficiency. However, it tends to be sensitive to outliers...