Using Q-Learning to Personalize Pedagogical Policies for Addition Problems
Amanda Shen, Cortney Weintz, Takara Truong
CS 229 Spring 2021: Machine Learning
About
The prevalence of COVID-19 over the past year has illuminated the need for effective digital education tools. With students studying from home, teachers have struggled to provide their students with adequately challenging coursework.
Our project aims to solve this issue in the context of math. More specifically, our goal is to encourage thoughtful learning by supplying students with personalized two-number addition problems that take time to solve but that we expect the student can still answer correctly.
Our solution is to model the process of selecting a math problem to give a student as a Markov Decision Process (MDP) and then use Q-learning to determine the best policy for arriving at the most optimally challenging two-number addition problem for that student.
Final Report: [pdf]
table showing the state representation for the math problem and some examples