<?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>2026-11-22T19:59:11Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/15872" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/15872</identifier><datestamp>2025-03-26T23:33:31Z</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">Law, Edith</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author" authority="16bdb4e0-96e2-4a19-b1c7-18d696b4a2b8" confidence="600">Vandenhof, Colin</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2020-05-15T19:43:16Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2020-05-15T19:43:16Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2020-05-15</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2020-04-16</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/10012/15872</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en">Reinforcement learning (RL) is a powerful tool for developing&#xd;
intelligent agents, and the use of neural networks makes RL techniques more&#xd;
scalable to challenging real-world applications, from task-oriented dialogue&#xd;
systems to autonomous driving. However, one of the major bottlenecks to the&#xd;
adoption of RL is efficiency, as it often takes many time steps to learn an&#xd;
acceptable policy. To address this problem, we investigate the idea of&#xd;
allowing the agent to ask for advice from a teacher. We formalize this&#xd;
concept in a framework called ask-for-help RL, which entails augmenting a&#xd;
Markov decision process with a teacher-query action that can be taken at a&#xd;
fixed cost in any state. In this task, the agent faces a dilemma between&#xd;
exploration, exploitation, and teacher-querying. To make this trade-off, we&#xd;
propose an action selection strategy that is rooted in the classical notion&#xd;
of value-of-information, and suggest a practical implementation that is based&#xd;
on deep Q-learning. This algorithm, called VOE/Q, can jointly decide between&#xd;
taking a particular environment action or querying the teacher, and is&#xd;
sensitive to the query cost. We then perform experiments in two domains: a&#xd;
maze navigation task and the Atari game Freeway. When the teacher is&#xd;
excluded, the algorithm shows substantial gains over many other exploration&#xd;
strategies from the literature. With the teacher included, we again find that&#xd;
the algorithm outperforms baselines. By taking advantage of the teacher,&#xd;
higher cumulative reward can be achieved than with standard RL alone.&#xd;
Together, our results point to a promising approach to both RL and&#xd;
ask-for-help RL.</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">apprenticeship learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">imitation learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">learning from demonstration</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">human-in-the-loop</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">interactive 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">active learning</dim:field>
   <dim:field mdschema="dc" element="subject" qualifier="lcsh" lang="en">Reinforcement learning</dim:field>
   <dim:field mdschema="dc" element="subject" qualifier="lcsh" lang="en">Active learning</dim:field>
   <dim:field mdschema="dc" element="title" lang="en">Asking for Help with a Cost in Reinforcement Learning</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" element="contributor" qualifier="advisor">Law, Edith</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>