We describe learning algorithms with formal performance guarantees which show that these problems can be efficiently addressed in the apprenticeship learning setting---the setting when expert demonstrations of the task are available. Our algorithms are guaranteed to return a control policy with performance comparable to the expert's. We evaluate performance on the same task and in the same (typically stochastic, high-dimensional and non-linear) environment as the expert.For example, for a helicopter performing in-place flips, it is known that the helicopter can be roughly centered around ... We apply our algorithm to learn trajectories and dynamics models for aerobatic flight with a remote controlled helicopter.
|Title||:||Apprenticeship Learning and Reinforcement Learning with Application to Robotic Control|
|Publisher||:||ProQuest - 2008|