Reinforcement learning in network control
Name
1119730914-MIT.pdf
Size
2.27 MB
Format
Adobe PDF
Checksum (MD5)
98504e327ce964313f0dc7c0a759716d
Author(s)
Liu, Bai(Aerospace scientist)Massachusetts Institute of Technology.
Advisor(s)
Eytan Modiano.
Date Issued
2019
Publisher
Massachusetts Institute of Technology
Abstract
With the rapid growth of information technology, network systems have become increasingly complex. In particular, designing network control policies requires knowledge of underlying network dynamics, which are often unknown, and need to be learned. Existing reinforcement learning methods such as Q-Learning, Actor-Critic, etc. are heuristic and do not offer performance guarantees. In contrast, model-based learning methods offer performance guarantees, but can only be applied with bounded state spaces. In the thesis, we propose to use model-based reinforcement learning. By applying Lyapunov analysis, our algorithm can be applied to queueing networks with unbounded state spaces. We prove that under our algorithm, the average queue backlog can get arbitrarily close to the optimal result. We also implement simulations to illustrate the effectiveness of our algorithm.
Description
Thesis: S.M., Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, 2019
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 59-91).
Subjects
Aeronautics and Astronautics.
MIT Department
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
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
