2026-09-19T19:06:26Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/178242022-01-13T07:55:03Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Bruce M. Blumberg.
Lyons, Derek Eugen
Massachusetts Institute of Technology. Dept. of Architecture. Program in Media Arts and Sciences.
Program in Media Arts and Sciences (Massachusetts Institute of Technology)
2005-06-02T18:49:06Z
2005-06-02T18:49:06Z
2004
2004
http://hdl.handle.net/1721.1/17824
56564997
Thesis (S.M.)--Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2004.
Page 205 blank.
Includes bibliographical references (p. [197]-204).
Cognitive development is one of nature's most important mechanisms for creating robustly adaptive intelligent creatures. From felids to oscines, developing animals are capable of learning in adverse environments with a reliability that often outpaces the current state-of-the-art in artificial intelligence (AI) The purpose of this thesis, therefore, is to examine how insights from cognitive development might be applied to the design of AI architectures. Starting with a targeted review of the ethological literature, I identify the key computational lessons of development, the fundamental conceptual insights that suggest intriguing new strategies for behavioral organization. These insights are then employed in the design of a developmental behavior architecture in which a hierarchical motivation-based behavior system is coupled to a distributed set of domain-specific learning tools. The architecture is deployed in a synthetic character (Hektor the mouse) whose challenge is to learn to play a competitive card matching game successfully against a human user. Evaluation of Hektor's performance on this task, at both qualitative and quantitative levels of description, reveal that the developmental architecture is capable of surmounting complex learning objectives in a novel and efficient manner. I conclude that the architecture presented here represents a valuable starting point for further consideration of developmental design principles.
by Derek Eugen Lyons.
S.M.
205 p.
7564590 bytes
7589626 bytes
application/pdf
application/pdf
eng
Massachusetts Institute of Technology
M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.
http://dspace.mit.edu/handle/1721.1/7582
Architecture. Program in Media Arts and Sciences.
Growing up virtual : the computational lessons of development
Thesis
application/pdf
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="69cedd67-5d00-4a17-9eec-f8aef09c7750">
<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>Growing up virtual : the computational lessons of development</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2004</PublicationDate>
<Authors>
<Author>
<DisplayName>Lyons, Derek Eugen</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>Architecture. Program in Media Arts and Sciences.</Keyword>
<Abstract>Cognitive development is one of nature's most important mechanisms for creating robustly adaptive intelligent creatures. From felids to oscines, developing animals are capable of learning in adverse environments with a reliability that often outpaces the current state-of-the-art in artificial intelligence (AI) The purpose of this thesis, therefore, is to examine how insights from cognitive development might be applied to the design of AI architectures. Starting with a targeted review of the ethological literature, I identify the key computational lessons of development, the fundamental conceptual insights that suggest intriguing new strategies for behavioral organization. These insights are then employed in the design of a developmental behavior architecture in which a hierarchical motivation-based behavior system is coupled to a distributed set of domain-specific learning tools. The architecture is deployed in a synthetic character (Hektor the mouse) whose challenge is to learn to play a competitive card matching game successfully against a human user. Evaluation of Hektor's performance on this task, at both qualitative and quantitative levels of description, reveal that the developmental architecture is capable of surmounting complex learning objectives in a novel and efficient manner. I conclude that the architecture presented here represents a valuable starting point for further consideration of developmental design principles.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>