Bayesian nonparametric approaches for reinforcement learning in partially observable domains
Name
818202173-MIT.pdf
Description
Full printable version
Size
16.62 MB
Format
Adobe PDF
Checksum (MD5)
65f41045bfd5d131dc44d2017a3ffc5c
Author(s)
Doshi-Velez, Finale
Advisor(s)
Nicholas Roy.
Alternative Title
Bayesian nonparametric methods for reinforcement learning in partially observable domains
Date Issued
2012
Publisher
Massachusetts Institute of Technology
Abstract
Making intelligent decisions from incomplete information is critical in many applications: for example, medical decisions must often be made based on a few vital signs, without full knowledge of a patient's condition, and speech-based interfaces must infer a user's needs from noisy microphone inputs. What makes these tasks hard is that we do not even have a natural representation with which to model the task; we must learn about the task's properties while simultaneously performing the task. Learning a representation for a task also involves a trade-off between modeling the data that we have seen previously and being able to make predictions about new data streams. In this thesis, we explore one approach for learning representations of stochastic systems using Bayesian nonparametric statistics. Bayesian nonparametric methods allow the sophistication of a representation to scale gracefully with the complexity in the data. We show how the representations learned using Bayesian nonparametric methods result in better performance and interesting learned structure in three contexts related to reinforcement learning in partially-observable domains: learning partially observable Markov Decision processes, taking advantage of expert demonstrations, and learning complex hidden structures such as dynamic Bayesian networks. In each of these contexts, Bayesian nonparametric approach provide advantages in prediction quality and often computation time.
Description
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2012.
Cataloged from PDF version of thesis.
Includes bibliographical references (p. 149-163).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
M.I.T. theses are protected by
copyright. They may be viewed from this source for any purpose, but
reproduction or distribution in any format is prohibited without written
permission. See provided URL for inquiries about permission.
copyright. They may be viewed from this source for any purpose, but
reproduction or distribution in any format is prohibited without written
permission. See provided URL for inquiries about permission.
Persistent DSpace Link
