Zheyuan Hu

I am a 4th year undergraduate student at UC Berkeley, graduating Dec. 2023 with degrees in Computer Science and Applied Mathematics. My research advisor at BAIR is Professor Sergey Levine. Previously, I had the privilege of working with Professor Abhishek Gupta and Dr. Kelvin Xu.

My research interests are in robot learning, specifically in methods enabling robots to acquire skills rapidly and scalably in the real world. This includes sample-efficient reinforcement learning, learning from both offline and online data, and learning from human demonstrations and feedback. Most recently, I have worked on dexterous manipulation challenges, reset-free learning, solving long horizon tasks, and reusing prior data to accelerate acquisition of new tasks in real world settings.

My next research goal is to build algorithms and systems that allows robots to learn a manipulation skill under minutes of real world interactions.

GitHub / Google Scholar / LinkedIn

Research

SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning

Jianlan Luo*, Zheyuan Hu*, Charles Xu, Siri Gadipudi, Archit Sharma, Rehaan Ahmad, Stefan Schaal, Chelsea Finn, Abhishek Gupta, Sergey Levine
Under Review at IEEE International Conference on Robotics and Automation (ICRA) 2024.
paper / video / website /

SERL (Sample-Efficient Robotic reinforcement Learning) provides an open-source software framework that aims to facilitate wider adoption of RL in real-world robotics.

REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation

Zheyuan Hu*, Aaron Rovinsky*, Jianlan Luo, Vikash Kumar, Abhishek Gupta, Sergey Levine
Conference on Robot Learning (CoRL) 2023.
paper / video / website /

REBOOT learns dexterous manipulation skills autonomously and entirely in the real world in less than 8 hours by bootstrapping from prior data. The method achieves 2X speed up than learning from scratch. Our method is tested on a multi-fingered robot hand learning dexterous in-hand rotation tasks.

Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance

Kelvin Xu*, Zheyuan Hu*, Ria Doshi, Aaron Rovinsky, Vikash Kumar, Abhishek Gupta, Sergey Levine
IEEE International Conference on Robotics and Automation (ICRA) 2023
paper / video / website /

AVAIL allows robots to learn long horizon manipulation skills through autonomous real-world interaction without manual engineering, using a framework for users to breakdown a long task into multiple sub-tasks with image examples and deep RL. The method was tested on a four-finger robot hand and complex dexterous manipulation tasks in the real world.

Design and source code from Jon Barron's website