I am a fifth-year Ph.D. student in Computing Science at the University of Alberta, focusing on reinforcement learning, which I believe is the most promising way to artificial general intelligence. I am honored to be supervised by Professor Rich Sutton.
My long-term research goal is to build simple, general, and scalable learning and planning algorithms for the reinforcement learning problem. I am particularly interested in designing these algorithms 1) that maximize the long-term average-reward objective, 2) with function approximation, and 3) with temporal abstractions.
Previously, I earned my Bachelor's degree in Electrical and Computer Engineering (ECE) from Shanghai Jiao Tong University (SJTU), where I worked in SJTU Speech Lab, supervised by Professor Kai Yu. After that, I earned my Master's degree, also in ECE, from the University of Michigan. I had a great experience working in Intelligent Robotics Lab when I was in Michigan, supervised by Professor Ben Kuipers.
Email: wan6@ualberta.ca
Education
University of Alberta
Ph.D. candidate
Computing Science
2017-2022 (expected)
University of Michigan
Master of Science in Engineering
Electrical and Computer Engineering
2015-2017
Shanghai Jiao Tong University
Bachelor of Science in Engineering
Electrical and Computer Engineering
2011-2015
Work Experience
J.P. Morgan,
London, UK
AI Research Intern
2022
Quebec Artificial Intelligence Institute (Mila), Montreal, Canada
Research Intern
2021
Huawei Technologies,
Edmonton, Canada
Research Intern
2019
Yitu Technology
Shanghai, China
Software Engineer Intern
2017
Tusimple
San Diego, US
Software Research Engineer Intern
2016
Publications
Planning with Expectation Models for Control.
Off-policy Maximum Entropy Reinforcement Learning: Soft Actor-Critic with Advantage Weighted Mixture Policy (SAC-AWMP).
Code
Services
Journal Reviewer: TMLR
Conference Reviewer: NeurIPS, ICML, ICLR, CoLLAs
Workshop Reviewer: Decision Aware RL workshop at ICML2022, RL4RealLife workshop at ICML2021
Organizer: Continuing (Non-Episodic) RL problems social at ICML2021.
Volunteer: ICML 2022 session moderator
Teaching
Reinforcement Learning II (COMPT 609) 2020, 2021, 2022 Teaching Assistant. Guest lecture: A Second Tutorial on Tabular TD(λ), Slides
Reinforcement Learning I (COMPT 366) 2018 Teaching Assistant
Skiing
Winter is long, skiing is fun.
Marmot Basin, Jasper, Canada
Photo from a video filmed by Shangtong Zhang
Blackcomb Glacier Ice Cave, Whistler, Canada