“Learning Human Behaviors from Motion Capture by Adversarial Imitation”, 2017-07-07 (; similar):
Rapid progress in deep reinforcement learning has made it increasingly feasible to train controllers for high-dimensional humanoid bodies. However, methods that use pure reinforcement learning with simple reward functions tend to produce non-human-like and overly stereotyped movement behaviors.
In this work, we extend generative adversarial imitation learning to enable training of generic neural network policies to produce human-like movement patterns from limited demonstrations consisting only of partially observed state features, without access to actions, even when the demonstrations come from a body with different and unknown physical parameters.
We leverage this approach to build sub-skill policies from motion capture data and show that they can be reused to solve tasks when controlled by a higher-level controller.