<?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>2026-11-22T17:14:47Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/21202" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/21202</identifier><datestamp>2025-03-26T23:31:24Z</datestamp><setSpec>com_10012_9924</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9930</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">Wan, Justin</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Wang, Lufan</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2024-11-26T20:37:37Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2024-11-26T20:37:37Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2024-11-26</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2024-11-21</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/10012/21202</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract">This thesis explores the application of reinforcement learning (RL) to address two impor-
tant financial problems: risk management and optimal trade execution.
In risk management, we aim to balance returns with associated risks. To achieve this,
we propose an enhanced RL model that integrates a dynamic Conditional Value at Risk
(CVaR) measure. By leveraging distorted probability measures, CVaR allows the RL agent
to emphasize worst-case scenarios, ensuring that potential losses are accounted for while
optimizing long-term returns. Our method substantially reduces the model’s training time
by efficiently reusing computation results, significantly lowering computational overhead.
Furthermore, it optimizes the balance between exploration and exploitation. This approach
leads to more robust decision-making in uncertain environments and a better overall return.
For optimal trade execution, we formulate a flexible RL-based framework capable of
dynamically adjusting to changing market conditions. Our model not only replicates the
results of Almgren-Chriss model in linear environments but also demonstrates superior
performance in more complex, nonlinear scenarios where traditional methods like Almgren-
Chriss face challenges.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en</dim:field>
   <dim:field mdschema="dc" element="publisher" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="dc" element="title">Reinforcement Learning for Solving Financial Problems</dim:field>
   <dim:field mdschema="dc" element="type">Master Thesis</dim:field>
   <dim:field mdschema="dc" element="pending">false</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="department">David R. Cheriton School of Computer Science</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="discipline">Computer Science</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">Master of Mathematics</dim:field>
   <dim:field mdschema="uws-etd" element="embargo" qualifier="terms">0</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="advisor">Wan, Justin</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="affiliation1">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>