Learning from Limited Demonstrations: Lessons We have Learned

Abstract

In this talk, I will explore the role of expert demonstrations in robotics, particularly their dual function as biomimetic benchmarks and accelerators of the learning process. While ideal expert motions are often unattainable, I will discuss three innovative approaches for learning from constrained demonstrations, showcasing their successful application in legged robotics. The presentation will encompass a variety of methods, including generative adversarial imitation learning, unsupervised skill discovery, and the integration of self-supervised models with representation and curriculum learning strategies.

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.