Learning with curricula for sparse-reward tasks in deep reinforcement learning
Name
1193028699-MIT.pdf
Size
2.6 MB
Format
Adobe PDF
Checksum (MD5)
ba2b8300ff1374ab5a1fb1cd837b3633
Author(s)
Rane, Sunayana.
Advisor(s)
Joshua Tenenbaum and Max Kleiman-Weiner.
Date Issued
2020
Publisher
Massachusetts Institute of Technology
Abstract
From an early age, humans spend a great deal of time playing in and exploring in their environments. We don't go from zero to AlphaZero without stopping to learn many other things along the way, and we don't learn these things alone. In many human societies, schooling and culture guide learning by providing a curricula for what is considered "intelligent" behavior. In this work I demonstrate how drawing from a curriculum developed to coax apes into successfully learning tasks can also improve performance of artificial agents, particularly in sparse-reward scenarios. I also demonstrate where curriculum learning falls short, and what these experimental results suggest for efforts in developing human-like artificial intelligence.
Description
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020
Cataloged from the official PDF of thesis.
Includes bibliographical references (pages 73-75).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided.
Persistent DSpace Link
