<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T22:03:59Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/18841" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/18841</identifier><datestamp>2025-03-26T23:34:37Z</datestamp><setSpec>com_10012_9900</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9908</setSpec><setSpec>col_10012_6</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Zahedi, Seyed Majid</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author" authority="be4e0e0a-51b7-4357-958b-eca932eebba2" confidence="600">Fardno, Fatemeh</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2022-09-29T14:04:50Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2023-09-30T04:50:05Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2022-09-29</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2022-09-27</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/10012/18841</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en">In this work, we study the application of multi-agent reinforcement learning (RL) in distributed systems. In particular, we consider a setting in which strategic clients compete over a set of heterogeneous servers. Each client receives jobs at a fixed rate. For each job, clients choose a server to run the job. The objective of each client is to minimize its average wait time. We model this setting as a Markov game and theoretically prove that the game becomes in the limit a Markov potential game (MPG). We further propose a novel mean-field reinforcement learning algorithm, combining mean-field Q-learning and fictitious play. Through rigorous experiments, we show that our algorithm outperforms naive deployment of single-agent RL, and in some cases, performs comparably to the Nash Q-learning, while being less complex in terms of memory and computation. We also empirically analyze the convergence of our proposed algorithm to a Nash equilibrium and study its performance in four benchmark examples.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en">en</dim:field>
   <dim:field mdschema="dc" element="publisher" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="dc" element="title" lang="en">Fictitious Mean-field Reinforcement Learning for Distributed Load Balancing</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Master Thesis</dim:field>
   <dim:field mdschema="dc" element="pending">false</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="department" lang="en">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="discipline" lang="en">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="grantor" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="uws-etd" element="degree" lang="en">Master of Applied Science</dim:field>
   <dim:field mdschema="uws-etd" element="embargo" qualifier="terms" lang="en">1 year</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="advisor">Zahedi, Seyed Majid</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="affiliation1" lang="en">Faculty of Engineering</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="city" lang="en">Waterloo</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="country" lang="en">Canada</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="province" lang="en">Ontario</dim:field>
   <dim:field mdschema="uws" element="typeOfResource" lang="en">Text</dim:field>
   <dim:field mdschema="uws" element="peerReviewStatus" lang="en">Unreviewed</dim:field>
   <dim:field mdschema="uws" element="scholarLevel" lang="en">Graduate</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>