profile photo

Zhehui Huang

I am a first-year Computer Science Ph.D. Student at the Robotics Embedded Systems Laboratory (RESL), University of Southern California, where I am advised by Prof. Gaurav Sukhatme and working on deep reinforcement learning and robotics.

I received a master's degree in Computer Science from University of Southern California. I received a bachelor's degree in Computer Science from Harbin Institute of Technology.

Email  |  CV  |  Bio  |  Google Scholar  |  Twitter  |  Github  |  Linkedin


I'm interested in deep reinforcement learning, deep learning, and robotics.

Decentralized Control of Quadrotor Swarms with End-to-end Deep Reinforcement Learning
Sumeet Batra*, Zhehui Huang*, Aleksei Petrenko*, Tushar Kumar,
Artem Molchanov, Gaurav Sukhatme
CoRL, 2021
webpage | pdf | code

Trained policy based on self-built simulator quad-swarm-rl , by using deep reinforcement learning and using sim-to-real transfer to deploy the policy on the real world quadrotors.

Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning
Aleksei Petrenko, Zhehui Huang, Tushar Kumar, Gaurav Sukhatme
Vladlen Koltun
ICML, 2020
webpage | pdf | code

Sample Factory is the fastest open source single-machine RL implementations (see paper for details). If you plan to train RL agents on large amounts of experience, consider using it. Sample Factory can significantly speed up the experimentation or allow you to collect more samples in the same amount of time and achieve better performance.

Modified version of template from this and this.