I am a first-year Ph.D. student in Computing Science at the University of Alberta, focusing on reinforcement learning, which I believe is the way to artificial intelligence. I am honored to be supervised by Professor Rich Sutton.

My current interest is in deeply understanding classical reinforcement learning algorithms, which includes, for example, 1) different problem settings, 2) assumptions, intuitions, convergence, and empirical performance of different algorithms. My other interests include model-based RL, off-policy learning and policy gradients methods.

Previously, I earned my Bachelor degree in Electrical and Computer Engineering (ECE) from Shanghai Jiao Tong University (SJTU), where I worked in SJTU Speech Lab, advised by Professor Kai Yu. After that I earned my master degree, also in ECE, from University of Michigan. I had a great experience working in Intelligent Robotics Lab, advised by Professor Ben Kuipers.

Email: wan6@ualberta.ca