<?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>2026-11-22T05:09:19Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/20596" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/20596</identifier><datestamp>2025-03-26T23:35:34Z</datestamp><setSpec>com_10012_9924</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9934</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">Lemieux, Christiane</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author" authority="c8626839-b9ca-4ef2-90ac-31aa82d8a445" confidence="600">Orok, Gavin</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2024-05-24T17:20:54Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2024-05-24T17:20:54Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2024-05-24</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2024-05-22</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/10012/20596</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en">Machine learning involves many challenging integrals that can be estimated using numerical&#xd;
methods. One application of these methods which has been explored in recent work is the estimation&#xd;
of policy gradients for reinforcement learning. They found that for many standard continuous control&#xd;
problems, the numerical methods randomized Quasi-Monte Carlo (RQMC) and Array-RQMC that used low-discrepancy point sets improved the efficiency of both policy evaluation and policy gradient-based policy iteration compared&#xd;
to standard Monte Carlo (MC). We extend this work by investigating the application of these numerical&#xd;
methods to model-free reinforcement learning algorithms in portfolio optimization, which are of&#xd;
interest because they do not rely on complex model assumptions that pose difficulties to other&#xd;
analytical methods. We find that RQMC significantly outperforms MC under all conditions for&#xd;
policy evaluation and that Array-RQMC outperforms both MC and RQMC in policy iteration with&#xd;
a strategic choice of the reordering function.</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="relation" qualifier="uri" lang="en">https://colab.research.google.com/drive/1DOA2VRYGWWR1hC713l6sIY57tK2gDx0H?usp=sharing</dim:field>
   <dim:field mdschema="dc" element="relation" qualifier="uri" lang="en">https://colab.research.google.com/drive/1mwA9wtUAPZoIUfWnlirZ5_TmVbZlWZi8?usp=sharing</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">reinforcement learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">numerical methods</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">quasi-Monte Carlo</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">portfolio optimization</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">continuous control</dim:field>
   <dim:field mdschema="dc" element="title" lang="en">Optimization of Policy Evaluation and Policy Improvement Methods in Portfolio Optimization using Quasi-Monte Carlo Methods</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">Statistics and Actuarial Science</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="discipline" lang="en">Quantitative Finance</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 Quantitative Finance</dim:field>
   <dim:field mdschema="uws-etd" element="embargo" qualifier="terms" lang="en">0</dim:field>
   <dim:field mdschema="uws" element="comment" qualifier="hidden" lang="en">The two links provide access to the Google Colab notebooks with the code used for policy iteration and evaluation.</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="advisor">Lemieux, Christiane</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="affiliation1" lang="en">Faculty of Mathematics</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>