Learning for Control from Multiple Demonstrations thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Learning for Control from Multiple Demonstrations

Published on Aug 12, 200810528 Views

We consider the problem of learning to follow a desired trajectory when given a small number of demonstrations from a sub-optimal expert. We present an algorithm that (i) extracts the---initially unkn

Related categories