2026-09-18T18:39:06Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/918832026-06-06T00:55:55Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Leslie Kaelbling and Tomás Lozano-Pérez. Zewdie, Dawit (Dawit Habtamu) Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2014-11-24T18:42:25Z 2014-11-24T18:42:25Z 2014 2014 http://hdl.handle.net/1721.1/91883 894499580 Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2014. Cataloged from PDF version of thesis. Includes bibliographical references (pages 71-73). Recent years have seen a surge of interest in non-parametric reinforcement learning. There are now practical non-parametric algorithms that use kernel regression to approximate value functions. The correctness guarantees of kernel regression require that the underlying value function be smooth. Most problems of interest do not satisfy this requirement in their native space, but can be represented in such a way that they do. In this thesis, we show that the ideal representation is one that maps points directly to their values. Existing representation discovery algorithms that have been used in parametric reinforcement learning settings do not, in general, produce such a representation. We go on to present Fit-Improving Iterative Representation Adjustment (FIIRA), a novel framework for function approximation and representation discovery, which interleaves steps of value estimation and representation adjustment to increase the expressive power of a given regression scheme. We then show that FIIRA creates representations that correlate highly with value, giving kernel regression the power to represent discontinuous functions. Finally, we extend kernel-based reinforcement learning to use FIIRA and show that this results in performance improvements on three benchmark problems: Mountain-Car, Acrobot, and PinBall. by Dawit Zewdie. M.Eng. 73 pages 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 Electrical Engineering and Computer Science. Representation discovery in non-parametric reinforcement learning Thesis application/pdf false Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="d459ba1c-453e-48a2-90ab-31fa6aebf392"> <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>Representation discovery in non-parametric reinforcement learning</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2014</PublicationDate> <Authors> <Author> <DisplayName>Zewdie, Dawit (Dawit Habtamu)</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>Recent years have seen a surge of interest in non-parametric reinforcement learning. There are now practical non-parametric algorithms that use kernel regression to approximate value functions. The correctness guarantees of kernel regression require that the underlying value function be smooth. Most problems of interest do not satisfy this requirement in their native space, but can be represented in such a way that they do. In this thesis, we show that the ideal representation is one that maps points directly to their values. Existing representation discovery algorithms that have been used in parametric reinforcement learning settings do not, in general, produce such a representation. We go on to present Fit-Improving Iterative Representation Adjustment (FIIRA), a novel framework for function approximation and representation discovery, which interleaves steps of value estimation and representation adjustment to increase the expressive power of a given regression scheme. We then show that FIIRA creates representations that correlate highly with value, giving kernel regression the power to represent discontinuous functions. Finally, we extend kernel-based reinforcement learning to use FIIRA and show that this results in performance improvements on three benchmark problems: Mountain-Car, Acrobot, and PinBall.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>