This is the top rung: teleoperate, record, train, deploy -- the arc a LeRobot arm follows. An expert controller drives the agent while every (observation, action) pair is recorded. Then clone the expert: fit a straight line action = w*obs + b to the demonstrations by least squares, and deploy that policy while the expert stands down. The starter leaves the slope and intercept at zero; solve them so the clone matches the expert and reaches on its own.
Predict firstYou record an expert by teleoperation and clone the policy by least squares. What tells you the clone actually learned the expert?
The slope is the expert's behaviour written as a number, about 0.5 here. Recovering it means the clone captured the rule rather than the recording.