CBT: Confidence Bound Target Algorithm

The Confidence Bound Target (CBT) algorithm is designed for infinite arms bandit problem. It is shown that CBT algorithm achieves the regret lower bound for general reward distributions. Reference: Hock Peng Chan and Shouri Hu (2018) <doi:10.48550/arXiv.1805.11793>.

Version: 1.0
Published: 2018-05-31
DOI: 10.32614/CRAN.package.CBT
Author: Hock Peng Chan and Shouri Hu
Maintainer: Shouri Hu <e0054325 at u.nus.edu>
License: GPL-2
NeedsCompilation: no
CRAN checks: CBT results

Documentation:

Reference manual: CBT.pdf

Downloads:

Package source: CBT_1.0.tar.gz
Windows binaries: r-devel: CBT_1.0.zip, r-release: CBT_1.0.zip, r-oldrel: CBT_1.0.zip
macOS binaries: r-release (arm64): CBT_1.0.tgz, r-oldrel (arm64): CBT_1.0.tgz, r-release (x86_64): CBT_1.0.tgz, r-oldrel (x86_64): CBT_1.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=CBT to link to this page.