Mathematics of Deep Learning
Spring 2020

Imitation learning

Motivation

Imitation learning is the subfield concerned with learning policies from expert demonstrations. Cascading errors and distribution mismatch are the main challenges in imitation learning. Guided policy search simultaneously trains a neural network policy to imitate expert trajectories and generates additional expert trajectories which stay close to the policy. After this week you should understand the challenges of designing an imitation learning algorithm such as GPS.

Topics

Required reading

Optional reading

Questions