2026-09-20T10:41:51Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1433902022-06-16T03:38:27Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Alizadeh, Mohammad
Hamadanian, Pouya
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2022-06-15T13:17:32Z
2022-06-15T13:17:32Z
2022-02
2022-03-04T20:59:52.765Z
https://hdl.handle.net/1721.1/143390
https://orcid.org/0000-0002-6364-4108
Recent research has turned to Reinforcement Learning (RL) to solve challenging decision problems, as an alternative to hand-tuned heuristics. RL can learn good policies without the need for modeling the environment's dynamics. Despite this promise, RL remains an impractical solution for many real-world systems problems. A particularly challenging case occurs when the environment changes over time, i.e. it exhibits non-stationarity. In this work, we characterize the challenges introduced by non-stationarity and develop a framework for addressing them to train RL agents in live systems. Such agents must explore and learn new environments, without hurting the system's performance, and remember them over time. To this end, our framework (1) identifies different environments encountered by the live system, (2) explores and trains a separate expert policy for each environment, and (3) employs safeguards to protect the system's performance. We apply our framework to two systems problems: straggler mitigation and adaptive video streaming, and evaluate it against a variety of alternative approaches using real-world and synthetic data. We show that each component of our framework is necessary to cope with non-stationarity.
S.M.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright MIT
http://rightsstatements.org/page/InC-EDU/1.0/
Reinforcement Learning in Time-Varying Systems: an Empirical Study
Thesis
application/pdf
Master
Master of Science in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="542f53de-8f70-4065-9449-dc554917f0d0">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Reinforcement Learning in Time-Varying Systems: an Empirical Study</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2022-02</PublicationDate>
<Authors>
<Author>
<DisplayName>Hamadanian, Pouya</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Recent research has turned to Reinforcement Learning (RL) to solve challenging decision problems, as an alternative to hand-tuned heuristics. RL can learn good policies without the need for modeling the environment's dynamics. Despite this promise, RL remains an impractical solution for many real-world systems problems. A particularly challenging case occurs when the environment changes over time, i.e. it exhibits non-stationarity. In this work, we characterize the challenges introduced by non-stationarity and develop a framework for addressing them to train RL agents in live systems. Such agents must explore and learn new environments, without hurting the system's performance, and remember them over time. To this end, our framework (1) identifies different environments encountered by the live system, (2) explores and trains a separate expert policy for each environment, and (3) employs safeguards to protect the system's performance. We apply our framework to two systems problems: straggler mitigation and adaptive video streaming, and evaluate it against a variety of alternative approaches using real-world and synthetic data. We show that each component of our framework is necessary to cope with non-stationarity.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>