Towards practical theory : Bayesian optimization and optimal exploration

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.

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2016

Author dc:creator

• Kawaguchi, Kenji, Ph. D. Massachusetts Institute of Technology

Advisor dc:contributor.advisor

• Leslie P. Kaelbling and Tomas Lozano-Perez.

• Electrical Engineering and Computer Science.

Statement dc:rights

• 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.

Licence dc:rights.uri

• http://dspace.mit.edu/handle/1721.1/7582

Language dc:language.iso

eng

Handle dc:identifier.uri

http://hdl.handle.net/1721.1/103670

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/103670