Towards practical theory : Bayesian optimization and optimal exploration
Author(s)
Kawaguchi, Kenji, Ph. D. Massachusetts Institute of Technology
DownloadFull printable version (2.319Mb)
Alternative title
Bayesian optimization and optimal exploration
Other Contributors
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Advisor
Leslie P. Kaelbling and Tomas Lozano-Perez.
Terms of use
Metadata
Show full item recordAbstract
This thesis presents novel principles to improve the theoretical analyses of a class of methods, aiming to provide theoretically driven yet practically useful methods. The thesis focuses on a class of methods, called bound-based search, which includes several planning algorithms (e.g., the A* algorithm and the UCT algorithm), several optimization methods (e.g., Bayesian optimization and Lipschitz optimization), and some learning algorithms (e.g., PAC-MDP algorithms). For Bayesian optimization, this work solves an open problem and achieves an exponential convergence rate. For learning algorithms, this thesis proposes a new analysis framework, called PACRMDP, and improves the previous theoretical bounds. The PAC-RMDP framework also provides a unifying view of some previous near-Bayes optimal and PAC-MDP algorithms. All proposed algorithms derived on the basis of the new principles produced competitive results in our numerical experiments with standard benchmark tests.
Description
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016. 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 83-87).
Date issued
2016Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.