<?xml version='1.0' encoding='UTF-8'?><?xml-stylesheet href='static/style.xsl' type='text/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>2026-11-22T10:23:31Z</responseDate><request verb="GetRecord" identifier="oai:ecommons.cornell.edu:1813/114489" metadataPrefix="dim">https://ecommons.cornell.edu/server/oai/request</request><GetRecord><record><header><identifier>oai:ecommons.cornell.edu:1813/114489</identifier><datestamp>2026-05-15T19:43:22Z</datestamp><setSpec>com_1813_35</setSpec><setSpec>col_1813_47</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author">Sreenivas, Dhruv</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="chair" lang="en_US">Sun, Wen</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember" lang="en_US">Kleinberg, Robert</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2024-04-05T18:36:33Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2024-04-05T18:36:33Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2023-08</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">ProQuest Submission ID: 11870</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">ProQuest Publication ID: 30573370</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/1813/114489</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="doi">https://doi.org/10.7298/hjpq-qh26</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="bibid">16219185</dim:field>
   <dim:field mdschema="dc" element="description" lang="en_US">40 pages</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Imitation learning is a promising paradigm to learn policies to solve a variety of tasks given some expert data. In particular, off-policy imitation learning is particularly nice for practitioners, as it in principle allows the policy to use previously collected data to improve, similar to standard value-based off-policy reinforcement learning algorithms such as Deep Q Learning and actor-critic methods. However, this is generally ill-defined, as the policy improvement operator can generally only in principle be applied to data collected by the most recent policy, making the algorithm on-policy. To mitigate this while still remaining off-policy, we design an actor-critic method where we treat the replay buffer as a collection of data from a set of weak learners. Our algorithm more appropriately weights each weak learner’s data when it comes to sampling for policy optimization, offering a principled way to mitigate the above distribution mismatch problem in the off-policy setting. We apply this technique to both state and vision-based tasks in the DeepMind Control Suite domain and see that our method does indeed improve learning in terms of sample efficiency.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Adversarial Learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Imitation Learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Reinforcement Learning</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">Principled Off-Policy Imitation Learning via Boosting</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">dissertation or thesis</dim:field>
   <dim:field mdschema="dc" element="relation" qualifier="localuri">https://newcatalog.library.cornell.edu/catalog/16219185</dim:field>
   <dim:field mdschema="dc" element="format" qualifier="mimetype">application/pdf</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="discipline">Computer Science</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="grantor">Cornell University</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="level">Master of Science</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="name">M.S., Computer Science</dim:field>
   <dim:field mdschema="dcterms" element="license">https://hdl.handle.net/1813/59810.2</dim:field>
   <dim:field mdschema="dspace" element="entity" qualifier="type">Publication</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="collection" authority="https://cornell-ecommons.eks.prod.4science.cloud/handle/1813/47" confidence="600">Cornell Theses and Dissertations</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="author">Sreenivas, Dhruv</dim:field>
   <dim:field mdschema="cris" element="virtualsource" qualifier="collection">5893a6ea-7af3-41d7-abc6-04bcd26ab5df</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="cerif" element="openaire" authority="" confidence="-1">&lt;Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="8a46b2da-c078-4c92-b3b2-1abe40e400ed">
	&lt;Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843&lt;/Type>
	&lt;Language>en&lt;/Language>
   	&lt;Title>Principled Off-Policy Imitation Learning via Boosting&lt;/Title>
   	&lt;PublishedIn>
    	&lt;Publication>
      	&lt;/Publication>
   	&lt;/PublishedIn>
   	&lt;PublicationDate>2023-08&lt;/PublicationDate>
   	&lt;DOI>https://doi.org/10.7298/hjpq-qh26&lt;/DOI>
   	&lt;Authors>
      	&lt;Author>
        	&lt;DisplayName>Sreenivas, Dhruv&lt;/DisplayName>
         	&lt;Affiliation>
         		&lt;OrgUnit>
         		&lt;/OrgUnit>
         	&lt;/Affiliation>
      	&lt;/Author>
	&lt;/Authors>
   	&lt;Editors>
	&lt;/Editors>
    &lt;Publishers>
        &lt;Publisher>
            &lt;OrgUnit />
        &lt;/Publisher>
    &lt;/Publishers>
    &lt;Keyword>Adversarial Learning&lt;/Keyword>
    &lt;Keyword>Imitation Learning&lt;/Keyword>
    &lt;Keyword>Reinforcement Learning&lt;/Keyword>
   	&lt;Abstract>Imitation learning is a promising paradigm to learn policies to solve a variety of tasks given some expert data. In particular, off-policy imitation learning is particularly nice for practitioners, as it in principle allows the policy to use previously collected data to improve, similar to standard value-based off-policy reinforcement learning algorithms such as Deep Q Learning and actor-critic methods. However, this is generally ill-defined, as the policy improvement operator can generally only in principle be applied to data collected by the most recent policy, making the algorithm on-policy. To mitigate this while still remaining off-policy, we design an actor-critic method where we treat the replay buffer as a collection of data from a set of weak learners. Our algorithm more appropriately weights each weak learner’s data when it comes to sampling for policy optimization, offering a principled way to mitigate the above distribution mismatch problem in the off-policy setting. We apply this technique to both state and vision-based tasks in the DeepMind Control Suite domain and see that our method does indeed improve learning in terms of sample efficiency.&lt;/Abstract>
	&lt;Access xmlns="http://purl.org/coar/access_right" 
    >
    &lt;/Access>
&lt;/Publication>
</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>