Artificial Intelligence Imitation Learning - Tutorial - 2018 ICML

Recorded July 11th, 2018 at the 2018 International Conference on Machine Learning
Presented by Yisong Yue (Caltech) and Hoang M Le (Caltech)
"In this tutorial, we aim to present to researchers and industry practitioners a broad overview of imitation learning techniques and recent applications. Imitation learning is a powerful and practical alternative to reinforcement learning for learning sequential decision-making policies. Also known as learning from demonstrations or apprenticeship learning, imitation learning has benefited from recent progress in core learning techniques, increased availability and fidelity of demonstration data, as well as the computational advancements brought on by deep learning. We expect the tutorial to be highly relevant for researchers & practitioners who have interests in reinforcement learning, structured prediction, planning and control. The ideal audience member should have familiarity with basic supervised learning concepts. No knowledge of reinforcement learning techniques will be assumed."

[@williamschram]

I would like to see more discussion of the tools used to record the expert actions in parallel with the policy decisions. Can they be prerecorded or do they need to be provided in real-time with the simulation? Real-time will work for a driver in a live car, but won't work for 32 simultaneous simulations of an Atari game with one expert.

[@erikm9768]

Very interesting but the lip syncing was comparable to work from two decades ago

[@dmeister2909]

I guess it's worth mentioning that the whole video seems to be unsynchronized, so that makes the overall demo less impressive.