Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations

Abstract

We review solutions to expert acquisition simplification in imitation learning and compare state-of-the-art methods for inferring reward functions from partial and potentially physically incompatible demonstrations for agile skill development.

Chenhao Li

Reinforcement Learning for Robotics

My research interests focus on the general field of robot learning, including reinforcement learning, developmental robotics and legged intelligence.