Description: The video shows the robot learning a towel folding task using our algorithm. The exploratory and expansion layers run 10 and 5 times, 
respectively. Once all 15 motions have been played back on the robot, the reinforcement learning iterates until convergence. The video shows each 
exploratory and expansion layer trial as well as the reinforcement learning trials until convergence, along with each trial's reward. 
The final learned motion is demonstrated at the end of the video. The authors of the paper strongly recommend downloading and watching 
the accompanying video, to get more insight into the way actions are performed on the robot. More videos, in higher resolutions, 
can be found at http://robotics.ucmerced.edu/Robotics/IROS2011/.

Player Information: The video is encoded using MPEG-1. This is a universal format that should be read by most, if not all, video players. 
The video was successfully played on Windows Media Player, VLC, Media Player Classic, QuickTime, RealPlayer, and iTunes. 

Contact Information:
Stefano Carpin
School of Engineering
University of California, Merced
scarpin@ucmerced.edu