Reinforcement learning in network control

Thesis: S.M., Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, 2019

Bibliographic Details
Main Author: Liu, Bai(Aerospace scientist)Massachusetts Institute of Technology.
Other Authors: Eytan Modiano.
Format: Thesis
Language:eng
Published: Massachusetts Institute of Technology 2019
Subjects:
Online Access:https://hdl.handle.net/1721.1/122414
_version_ 1826191688407711744
author Liu, Bai(Aerospace scientist)Massachusetts Institute of Technology.
author2 Eytan Modiano.
author_facet Eytan Modiano.
Liu, Bai(Aerospace scientist)Massachusetts Institute of Technology.
author_sort Liu, Bai(Aerospace scientist)Massachusetts Institute of Technology.
collection MIT
description Thesis: S.M., Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, 2019
first_indexed 2024-09-23T08:59:48Z
format Thesis
id mit-1721.1/122414
institution Massachusetts Institute of Technology
language eng
last_indexed 2024-09-23T08:59:48Z
publishDate 2019
publisher Massachusetts Institute of Technology
record_format dspace
spelling mit-1721.1/1224142023-07-31T13:12:51Z Reinforcement learning in network control Liu, Bai(Aerospace scientist)Massachusetts Institute of Technology. Eytan Modiano. Massachusetts Institute of Technology. Department of Aeronautics and Astronautics. Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Aeronautics and Astronautics. 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). 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. by Bai Liu. S.M. S.M. Massachusetts Institute of Technology, Department of Aeronautics and Astronautics 2019-10-04T21:33:15Z 2019-10-04T21:33:15Z 2019 2019 Thesis https://hdl.handle.net/1721.1/122414 1119730914 eng 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. http://dspace.mit.edu/handle/1721.1/7582 61 pages application/pdf Massachusetts Institute of Technology
spellingShingle Aeronautics and Astronautics.
Liu, Bai(Aerospace scientist)Massachusetts Institute of Technology.
Reinforcement learning in network control
title Reinforcement learning in network control
title_full Reinforcement learning in network control
title_fullStr Reinforcement learning in network control
title_full_unstemmed Reinforcement learning in network control
title_short Reinforcement learning in network control
title_sort reinforcement learning in network control
topic Aeronautics and Astronautics.
url https://hdl.handle.net/1721.1/122414
work_keys_str_mv AT liubaiaerospacescientistmassachusettsinstituteoftechnology reinforcementlearninginnetworkcontrol