I am a first-year Ph.D. student at the School of Artificial Intelligence (SAI), Shanghai Jiao Tong University (SJTU), supervised by Prof. Shuai Li.

Previously, I obtained my Master’s degree from the Antai College of Economics and Management, Shanghai Jiao Tong University, where I was advised by Prof. Kai Wang. Prior to that, I completed my undergraduate studies at Xi’an Jiaotong University, under the supervision of Prof. Haishan Ye.

My research interests lie in reinforcement learning theory and deep reinforcement learning.

I firmly believe that Reinforcement Learning is indispensable for the next generation of AGI. However, current Deep RL suffers from severe sample inefficiency, revealing a fundamental mismatch between theory and empirical practice. My research aims to decode the underlying mechanisms of RL within deep learning contexts, striving to design RL frameworks that rival the sample efficiency of supervised learning.