2026-09-19T06:32:27Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1134422026-06-06T00:55:38Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Leslie P. Kaelbling.
Shavit, Yonadav Goldwasser
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2018-02-08T15:57:54Z
2018-02-08T15:57:54Z
2017
2017
http://hdl.handle.net/1721.1/113442
1020173476
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 83-85).
To allow planning in novel environments that have not been mapped out by hand, we need ways of learning environment models. While conventional work has focused on video prediction as a means for environment learning, this work instead seeks to learn from much sparser signals, like the agent's reward. In Chapter 1, we establish a taxonomy of environments and the attributes that make them easier or harder to model through learning. In Chapter 2, we review prior work in the field of environment learning. In Chapter 3, we propose a model-learning architecture based purely on reward prediction, and analyze its performance on illustrative problems. Finally, in Chapter 4, we propose and evaluate a model-learning architecture that uses both reward and sparse "features" extracted from the environment.
by Yonadav Goldwasser Shavit.
M.Eng.
85 pages
eng
Massachusetts Institute of Technology
MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Learning environment simulators from sparse signals
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="bb239596-a691-4974-a725-62f03eca4b03">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Learning environment simulators from sparse signals</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2017</PublicationDate>
<Authors>
<Author>
<DisplayName>Shavit, Yonadav Goldwasser</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>To allow planning in novel environments that have not been mapped out by hand, we need ways of learning environment models. While conventional work has focused on video prediction as a means for environment learning, this work instead seeks to learn from much sparser signals, like the agent's reward. In Chapter 1, we establish a taxonomy of environments and the attributes that make them easier or harder to model through learning. In Chapter 2, we review prior work in the field of environment learning. In Chapter 3, we propose a model-learning architecture based purely on reward prediction, and analyze its performance on illustrative problems. Finally, in Chapter 4, we propose and evaluate a model-learning architecture that uses both reward and sparse "features" extracted from the environment.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>