2026-09-18T17:34:02Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1224142023-07-31T13:12:51Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Eytan Modiano.
Liu, Bai(Aerospace scientist)Massachusetts Institute of Technology.
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics.
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
2019-10-04T21:33:15Z
2019-10-04T21:33:15Z
2019
2019
https://hdl.handle.net/1721.1/122414
1119730914
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
61 pages
eng
Massachusetts Institute of Technology
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
Aeronautics and Astronautics.
Reinforcement learning in network control
Thesis
application/pdf
2019-10-04T21:33:13Z
Publication
Master
Aero
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="1f52fef8-0283-4846-9d2b-6e4708806539">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Reinforcement learning in network control</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2019</PublicationDate>
<Authors>
<Author>
<DisplayName>Liu, Bai(Aerospace scientist)Massachusetts Institute of Technology.</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Aeronautics and Astronautics.</Keyword>
<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.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>