Haonan Yu

Research Scientist
Baidu Research
CV / Google Scholar / GitHub @yu239

I focus on the problem of learning to ground language in both vision and control with deep reinforcement learning as the primary tool, under weak or no supervision. I believe that language itself is a critical tool for an intelligent agent to master the ability of reasoning and skill transfer.

My previous work (during PhD) was mainly about learning to ground language in realistic video, but with much more expensive supervision.

I received a Ph.D. degree in Computer Engineering from Purdue University in 2016.



PaddlePaddle - Baidu's open-source deep learning platform which I occasionally contribute to.

XWorld - A C++/Python simulator package for reinforcement learning research.