2026-09-19T16:24:41Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1218132026-06-16T18:53:44Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022
Joshua B. Tenenbaum.
Tsividis, Pedro A.
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences.
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
2019-07-18T20:31:54Z
2019-07-18T20:31:54Z
2019
2019
https://hdl.handle.net/1721.1/121813
1103712391
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Brain and Cognitive Sciences, 2019
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 123-130).
Humans are remarkable in their ability to rapidly learn complex tasks from little experience. Recent successes in Al have produced algorithms that can perform complex tasks well in environments whose simple dynamics are known in advance, as well as models that can learn to perform expertly in unknown environments after a great amount of experience. Despite this, no current AI models are able to learn sufficiently rich and general representations so as to support rapid, human-level learning on new, complex, tasks. This thesis examines some of the epistemic practices, representations, and algorithms that we believe underlie humans' ability to quickly learn about their world and to deploy that understanding to achieve their aims. In particular, the thesis examines humans' ability to effectively query their environment for information that helps distinguish between competing hypotheses (Chapter 2); children's ability to use higher-level amodal features of data to match causes and effects (Chapter 3); and adult human rapid-learning abilities in artificial video-game environments (Chapter 4). The thesis culminates by presenting and testing a model, inspired by human inductive biases and epistemic practices, that learns to perform complex video-game tasks at human levels with human-level amounts of experience (Chapter 5). The model is an instantiation of a more general approach, Theory-Based Reinforcement Learning, which we believe can underlie the development of human-level agents that may eventually learn and act adaptively in the real world.
by Pedro A. Tsividis.
Ph.D.
Ph.D. Massachusetts Institute of Technology, Department of Brain and Cognitive Sciences
130 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
Brain and Cognitive Sciences.
Theory-based learning in humans and machines
Thesis
application/pdf
2019-07-18T20:31:52Z
Publication
Doctoral
Brain
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="2c540af1-c118-46e4-a518-0ab44e92faa0">
<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>Theory-based learning in humans and machines</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2019</PublicationDate>
<Authors>
<Author>
<DisplayName>Tsividis, Pedro A.</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>Brain and Cognitive Sciences.</Keyword>
<Abstract>Humans are remarkable in their ability to rapidly learn complex tasks from little experience. Recent successes in Al have produced algorithms that can perform complex tasks well in environments whose simple dynamics are known in advance, as well as models that can learn to perform expertly in unknown environments after a great amount of experience. Despite this, no current AI models are able to learn sufficiently rich and general representations so as to support rapid, human-level learning on new, complex, tasks. This thesis examines some of the epistemic practices, representations, and algorithms that we believe underlie humans' ability to quickly learn about their world and to deploy that understanding to achieve their aims. In particular, the thesis examines humans' ability to effectively query their environment for information that helps distinguish between competing hypotheses (Chapter 2); children's ability to use higher-level amodal features of data to match causes and effects (Chapter 3); and adult human rapid-learning abilities in artificial video-game environments (Chapter 4). The thesis culminates by presenting and testing a model, inspired by human inductive biases and epistemic practices, that learns to perform complex video-game tasks at human levels with human-level amounts of experience (Chapter 5). The model is an instantiation of a more general approach, Theory-Based Reinforcement Learning, which we believe can underlie the development of human-level agents that may eventually learn and act adaptively in the real world.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>