Targeting a simple statistical bandit problem - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

Targeting a simple statistical bandit problem

Abstract

This manuscript deals with the estimation of the optimal rule and its mean reward in a simple bandit setting where, at each round, the player is given a context, chooses one of two actions based on the context and all past observations, and receives a reward corresponding to the action undertaken. The player focuses on the mean reward and tries to narrow her confidence interval for it, but it happens that she can also estimate her regret. Inference hinges on the targeted learning methodology. A simulation study illustrates the results of the manuscript.
Fichier principal
Vignette du fichier
bandits_HAL.pdf (364.15 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01359222 , version 1 (02-09-2016)

Identifiers

  • HAL Id : hal-01359222 , version 1

Cite

Antoine Chambaz, Wenjing Zheng. Targeting a simple statistical bandit problem. 2016. ⟨hal-01359222⟩

Relations

142 View
160 Download

Share

Gmail Facebook Twitter LinkedIn More