Dissertation/Thesis Abstract

Using Reinforcement Learning in A Simulated Intelligent Tutoring System
by Jasti, Manohar Sai, M.S., Northern Illinois University, 2019, 54; 13904565
Abstract (Summary)

I used reinforcement learning to investigate which categories of hints are most efficient in an intelligent tutoring system for human anatomy. Efficiency is defined as minimizing the time it takes the student to learn the material. When a student gives a wrong answer, the tutor can give them a text hint, a diagrammatic hint, or a video clip. Each type of hint takes a different amount of time to deliver and takes the student a different amount of time to understand.

I built a simulator for the intelligent tutoring system to collect data from simulated students. I implemented reinforcement learning, in particular two Temporal Difference (TD) Learning techniques on this simulated data to identify the most efficient hint specific to a student and the most efficient hint for the whole student population. I show that the most efficient hint type is a function of the two times listed above.

Indexing (document details)
Advisor: Freedman, Reva
Commitee: Alhoori, Hamed, Duffin, Kirk, Naples, Virginia
School: Northern Illinois University
Department: Computer Science
School Location: United States -- Illinois
Source: MAI 81/3(E), Masters Abstracts International
Source Type: DISSERTATION
Subjects: Computer science, Education
Keywords: biology education, intelligent tutoring systems, reinforcement learning
Publication Number: 13904565
ISBN: 9781088323397
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest