Cooperate to compete : composable planning and inference in multi-agent reinforcement learning
Name
1078636205-MIT.pdf
Description
Full printable version
Size
880.62 KB
Format
Adobe PDF
Checksum (MD5)
df73e7cd8eb7380f35a7fc90548cb443
Author(s)
Shum, Michael M
Advisor(s)
Joshua B. Tenenbaum and Max Kleiman-Weiner.
Date Issued
2018
Publisher
Massachusetts Institute of Technology
Abstract
Cooperation within a competitive social situation is a essential part of human social life. This requires knowledge of teams and goals as well as an ability to infer the intentions of both teammates and opponents from sparse and noisy observations of their behavior. We describe a formal generative model that composes individual planning programs into rich and variable teams. This model constructs optimal coordinated team plans and uses these plans as part of a Bayesian inference of collaborators and adversaries of varying intelligence. We study these models in two environments: a complex continuous Atari game Warlords and a grid-world stochastic game, and compare our model with human behavior.
Description
Thesis: M. Eng. in Computer Science and Engineering, Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018.
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 51-54 ).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.
Persistent DSpace Link
