About me
Hi, thanks for visiting my homepage!
I'm a postdoctoral researcher working with Jeff Schneider at the Robotics Institute (RI), where my focus is on plasma control of the DIII-D tokamak. My goal is to design better control policies via reinforcement learning (RL) and broader machine learning frameworks. We work closely with the Plasma Control Group at Princeton Plasma Physics Laboratory (PPPL).
I received my PhD degree in Computer Science and Engineering at The Chinese University of Hong Kong (CUHK), where I’m blessed to be under co-supervision of Farzan Farnia and Ho-fung Leung. My thesis research focuses on provably efficient reinforcement learning and its applications to adaptive selections of LLMs and generative AI models.
Research Interests
-
Tokamak Plasma Control
How can we design better feedback control of Tokamak plasma via RL?
-
Provably efficient RL
How optimal behaviors be sample-efficiently learned?
-
Generative AI
How can RL and online learning assist the training, generation, and evaluation of generative models?
