knitr::opts_chunk$set( collapse = TRUE, comment = "#>", fig.path = "README-" )
The goal of banditr is to manage multi-armed bandit experiments. The package supports Linear Upper Confidence Bound (LinUCB), and Thompson sampling algorithms. It allows storing the resulting objects in a database management system (DBMS). Currently, the package supports one DBMS: Microsoft SQL Server, through the RODBC
package.
You can install banditr from github with:
# uncomment the following line if the package devtools is not installed # install.packages("devtools") devtools::install_github("rferrali/banditr")
A tutorial is available here. It is also available as a vigentte in the package. To access the vignette, make sure to compile it as you install the package, and use:
# devtools::install_github("rferrali/banditr", build_vignettes = TRUE) library(banditr) vignette("introduction", "banditr")
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.