Towards Practical Theory: Bayesian Optimization and Optimal Exploration
Name
MIT-CSAIL-TR-2016-006.pdf
Size
2.49 MB
Format
Adobe PDF
Checksum (MD5)
ee8ef8aa2340d6009c9015a8f630105f
Download all files submitted through automated deposit
Author(s)
Kawaguchi, Kenji
Advisor(s)
Leslie Kaelbling
Date Issued
May 26, 2016
Series/Report no.
MIT-CSAIL-TR-2016-006
Abstract
This thesis discusses 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 PAC-RMDP, 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
SM thesis
Subjects
PAC-MDP
AI planning
Global optimization
Terms of Use
Creative Commons Attribution 4.0 International
Persistent DSpace Link
