Rating is available when the video has been rented.
This feature is not available right now. Please try again later.
Uploaded on Jun 14, 2007
This video demonstrates an Aibo learning the XOR task, where it receives a reward following either a red or a blue stimulus, but not when both are presented together. The Temporal Difference learning aspect allows the robot to learn when the reward should have been presented, so that it can handle real-time interactions.
Published in the proceedings of the Second International Conference on Development and Learning (ICDL 2002)