Paper Explained - AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control (Full Video Analysis)

Learning from demonstrations is a fascinating topic, but what if the demonstrations are not exactly the behaviors we want to learn? Can we adhere to a dataset of demonstrations and still achieve a specified goal? This paper uses GANs to combine goal-achieving reinforcement learning with imitation learning and learns to perform well at a given task while doing so in the style of a given presented dataset. The resulting behaviors include many realistic-looking transitions between the demonstrated movements.

OUTLINE:
0:00 - Intro & Overview
1:25 - Problem Statement
6:10 - Reward Signals
8:15 - Motion Prior from GAN
14:10 - Algorithm Overview
20:15 - Reward Engineering & Experimental Results
30:40 - Conclusion & Comments

Paper: [2104.02180] AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
Main Video: https://www.youtube.com/watch?v=wySUx
Supplementary Video: https://www.youtube.com/watch?v=O6fBS