Zhehui Huang

I am a third-year Computer Science Ph.D. Student at the University of Southern California (USC), advised by Prof. Gaurav Sukhatme.

Previously, I received a master's degree in Computer Science at USC. I completed my bachelor's degree in Computer Science at Harbin Institute of Technology.

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

News

Research

My goal is to build intelligent agents that with the ability to perform complex tasks robustly and safely within unstructured environments via autonomous and unsupervised adaptation to the environment. I mainly focus on reinforcement learning, robot learning and foundation models.

Robotic Learning

At the moment, my main research problem is to control quadrotor swarms to navigate in complex environments based on limited compute resource.

Conference

Investigate the relationship between the performance and model size.

Learn end-to-end deep reinforcement learning policies to control quadrotor swarms to navigate in obstacle-rich environments.

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.

Workshop

Deep Reinforcement Learning

At the moment, my main research problem is exploring better on-policy algorithm than PPO.

Conference

In this work we have shown how FixPO is able to combine the guarantees of trust region methods with the computational efficiency and rewards of proximal methods. FixPO enforces its trust region via KL penalization, which is flexible and well understood in the machine learning community. In future work, we would like to extend our work to a multi-task setting.

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.

Foundation Models

At the moment, my main research problem is investigating LLMs for robotics.

Conference

In this work, we investigate LLMs for vehicle routing problems. We construct a dataset that can be used as a benchmark for LLMs in vehicle routing problems. We propose a framework with self-debugging and self-verification. We show GPT-4 outperforms Claude 3 Opus, and Gemini 1.0 Pro

Modified version of template from this and this.