Reducing Human Efforts for Expert Acquisition in Imitation Learning

Abstract

We analyze human involvement in generic imitation learning settings, especially in the data collection phase. We also review methods that aim to reduce such human efforts in the training loop, by either inferring learning signals from poor demonstrations, or extracting latent skills from noisy datasets.

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.