Octi Zhang

Octi Zhang is a software engineer at NVIDIA and an affiliated researcher with the University of Washington, where he completed his undergraduate degree in computer science. He is a core engineer on the Isaac Lab project, a GPU-accelerated simulation framework for multi-modal robot learning. He is best known for his research on scaling reinforcement learning for robot control, including the Success Guided Sampling method and work on emergent dexterity through diverse resets and large-scale RL.