<?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>2026-11-22T20:25:23Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/16908" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/16908</identifier><datestamp>2025-03-26T23:36:28Z</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">Orchard, Jeff</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author" authority="7ccb0d73-1e9d-48ef-b719-2df171fe0091" confidence="600">Van de Kleut, Alexander</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2021-04-27T14:13:41Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2021-04-27T14:13:41Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2021-04-27</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2021-04-16</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/10012/16908</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en">We are interested in training goal-conditioned reinforcement learning agents to reach arbitrary goals specified as images. In order to make our agent fully general, we provide the agent with only images of the environment and the goal image. Prior methods in goal-conditioned reinforcement learning from images use a learned lower-dimensional representation of images. These learned latent representations are not necessary to solve a variety of goal-conditioned tasks from images. We show that a goal-conditioned reinforcement learning policy can be successfully trained end-to-end from pixels by using simple reward functions. In contrast to prior work, we demonstrate that using negative raw pixel distance as a reward function is a strong baseline. We also show that using the negative Euclidian distance between feature vectors produced by a random convolutional neural network outperforms learned latent representations like convolutional variational autoencoders.</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="subject" lang="en">reinforcement learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">deep reinforcement learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">machine learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">ai</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">artificial intelligence</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">machine vision</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">computer vision</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">self-supervised</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">goal-conditioned</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">multi-goal</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">rl</dim:field>
   <dim:field mdschema="dc" element="title" lang="en">Learning-Free Methods for Goal Conditioned Reinforcement Learning from Images</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">David R. Cheriton School of Computer Science</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="discipline" lang="en">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" lang="en">Master of Mathematics</dim:field>
   <dim:field mdschema="uws-etd" element="embargo" qualifier="terms" lang="en">0</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="advisor">Orchard, Jeff</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>