{firstname}m@cs.stanford.edu
I am a PhD Student at Stanford University advised by Prof. Emma Brunskill. I am also a part of the Stanford AI Lab and the Stanford Machine Learning Group. My research goal is to create practical Reinforcement Learning and Bandit algorithms suitable for real world applications (education, recommendation systems, etc). This involves a variety of interesting research considerations such as methods for utilizing structure, expert/domain knowledge, and prior data. During my PhD, I was fortunate to collaborate with WarChild Holland, Adobe Research and Salesforce Research. Before Stanford, I obtained a B.S in Electrical Engineering from UCLA and was adivsed by Prof. Richard Wesel and Prof. Jonathan Aurnou.
(In Preparation) Modeling Bounded Rationality in Multi-Agent Simulations with Rationally Inattentive Reinforcement Learning
Link to Code
Tong Mu, Stephan Zheng, Alexander Trott
Constraint Sampling Reinforcement Learning: Incorporating Expertise For
Faster Learning
Link to Code
Tong Mu, Georgios Theocharous, David Arbour, Emma Brunskill
AAAI 2022
Automatic Adaptive Sequencing in a Foreign Language Game
Tong Mu, Shuhan Wang, Erik Andersen, Emma Brunskill
ITS 2021, Best Short Paper Award
Towards Suggesting Actionable Interventions for Wheel Spinning Students
Tong Mu, Andrea Jetten, Emma Brunskill
EDM 2020 (Educational Data Mining)
There is also an article from Stanford HAI about this.
Click here for a list of all publications.
2021 Summer, Research Intern at Salesforce Research, advised by Alex Trott and Stephan Zheng
2020 Summer, Research Intern at Adobe Research, advised by Georgios Theocharous and David Arbour
2019 Fall, Visiting Researcher at WarChild Holland
2017 Fall, Joined Prof. Emma Brunskill’s Group
2016 Fall, Began PhD at Stanford University
2016 Spring, Graduated UCLA with a B.S. In Electrical Engeineering