Tensor decomposition and parallelization of Markov Decision Processes
Name
959551440-MIT.pdf
Description
Full printable version
Size
7.92 MB
Format
Adobe PDF
Checksum (MD5)
ab66d8fb7339b3b944274ba74c5001f3
Author(s)
Smart, David P. (David Paul)
Advisor(s)
Olivier de Weck.
Date Issued
2016
Publisher
Massachusetts Institute of Technology
Abstract
Markov Decision Processes (MDPs) with large state spaces arise frequently when applied to real world problems. Optimal solutions to such problems exist, but may not be computationally tractable, as the required processing scales exponentially with the number of states. Unsurprisingly, investigating methods for efficiently determining optimal or near-optimal policies has generated substantial interest and remains an active area of research. A recent paper introduced an MDP representation as a tensor composition of a set of smaller component MDPs, and suggested a method for solving an MDP by decomposition into its tensor components and solving the smaller problems in parallel, combining their solutions into one for the original problem. Such an approach promises an increase in solution efficiency, since each smaller problem could be solved exponentially faster than the original. This paper develops this MDP tensor decomposition and parallelization algorithm, and analyzes both its computational performance and the optimality of its resultant solutions.
Description
Thesis: S.M., Massachusetts Institute of Technology, Computation for Design and Optimization Program, 2016.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 85-81).
Subjects
Computation for Design and Optimization Program.
MIT Department
Massachusetts Institute of Technology. Computation for Design and Optimization Program
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.
Persistent DSpace Link
