Learning Control Policies for Virtual Grasping Applications
Graphics Interface 2010 poster
Sheldon Andrews Paul G. Kry Doina Precup
School of Computer Science, McGill University


We present a novel application of reinforcement learning to grasp synthesis in a physically based virtual environment. We use pre-defined controllers and learn a policy for choosing among them. Advice from a human is incorporated to guide exploration. Our approach is straightforward and has success in learning stable grasps that generalize across objects. Furthermore, the appearance of the resulting simulated trajectories resemble natural grasping motions.


Extended Abstract

S. Andrews, P. G. Kry, and D. Precup, Learning Control Policies for Virtual Grasping Applications, Presented at Graphics Interface 2010 poster session