자료유형  

 학위논문

Control Number  

0017162876

International Standard Book Number  

9798382741130

Dewey Decimal Classification Number  

519

Main Entry-Personal Name  

Adler, Saghar.

Publication, Distribution, etc. (Imprint  

[S.l.] : University of Michigan., 2024

Publication, Distribution, etc. (Imprint  

Ann Arbor : ProQuest Dissertations & Theses, 2024

Physical Description  

158 p.

General Note  

Source: Dissertations Abstracts International, Volume: 85-12, Section: B.

General Note  

Advisor: Subramanian, Vijay Gautam.

Dissertation Note  

Thesis (Ph.D.)--University of Michigan, 2024.

Summary, Etc.  

요약Recently, reinforcement learning methodologies have been applied to solve sequential decision-making problems in various fields, such as robotics and autonomous control, communication and networking, and resource allocation and scheduling. Despite great practical success, there has been less progress in developing theoretical performance guarantees for such complex systems. This dissertation aims to address the limitations of current theoretical frameworks and extend the applicability of learning-based control methods to more complex, real-life domains discussed above. This objective is achieved in two different settings using the inherent structural properties of the Markov decision processes used to model such systems. For admission control in systems modeled by the Erlang-B blocking model with unknown arrival and service rates, in the first setting, we use model knowledge to compensate for the lack of reward signals. Here, we propose a learning algorithm based on the self-tuning adaptive control and not only prove that our algorithm is asymptotically optimal but also provide finite-time regret guarantees. The second setting develops a framework to address the challenge of applying reinforcement learning methods to Markov decision processes with countably infinite state spaces and unbounded cost functions. An existing learning algorithm based on Thompson sampling with dynamically-sized episodes is extended to countably infinite state space using the ergodicity properties of Markov decision processes. We establish asymptotic optimality of our learning-based control policy by providing a sub-linear (in time-horizon) regret guarantee. Our framework is focused on models that arise in queueing system models of communication networks, computing systems, and processing networks. Hence, to demonstrate the applicability of our method, we also apply it to the problem of controlling two queueing systems with unknown dynamics.

Subject Added Entry-Topical Term  

Applied mathematics.

Subject Added Entry-Topical Term  

Engineering.

Index Term-Uncontrolled  

Reinforcement learning

Index Term-Uncontrolled  

Learning in queueing systems

Index Term-Uncontrolled  

Markov decision processes

Index Term-Uncontrolled  

Asymptotic optimality

Added Entry-Corporate Name  

University of Michigan Electrical and Computer Engineering

Host Item Entry  

Dissertations Abstracts International. 85-12B.

Electronic Location and Access  

로그인을 한후 보실 수 있는 자료입니다.

Control Number  

joongbu:657760