I am a research scientist at Horizon Robotics, working on learning-based robotics. Previously, I worked at Facebook AI Research and Baidu Research on embodied AI in virtual worlds.

I love writing code and building things. I am a co-author and an active maintainer of ALF, an RL framework emphasizing on the flexibility and easiness of implementing a complex RL system involving many different algorithm components.

My long-term career goal is to build a generalist agent (whether it is virtual or physical) with a wide range of skills to assist people with tedious daily tasks. By doing so, I aim to free up more time for humans to focus on creative pursuits—such as writing, drawing, and imagining—activities that truly define our humanity.

ALF - Agent Learning Framework (ALF) is a PyTorch reinforcement learning framework emphasizing on the flexibility and easiness of implementing complex algorithms involving many different components.
TAAC - Temporally abstract actor-critic algorithm for efficient continuous control.
XWorld - A simulator package for RL research with language task support.
FLARE - A reinforcement learning framework for training embodied agents with PyTorch.

I like playing video games, especially ARPG. So far my favorite games are souls-like, by FromSoftware.