Home

Chongyu (Chay) Zhu

Ph.D. Candidate at University of Toronto

I am a Ph.D. candidate at the University of Toronto, supervised by Prof. Chi-Guhn Lee. My research lies at the intersection of Robotics, Reinforcement Learning, and Simulation to Reality.

Combining physical intuition from Mechanics with modern RL, I am passionate about bridging the gap between theoretical control principles and modern data-driven approaches through RL methods.

My current research focuses on three key pillars:

• Robot Simulation: Developing custom, physics-rich environments in NVIDIA Isaac Sim to bridge the sim-to-real gap.
• Offline Skill Discovery: Leveraging offline datasets to extract reusable primitive skills for long-horizon planning tasks.
• RL Systems Optimization: Enhancing computational efficiency through structural innovations in grouping, scheduling, and communication architectures.