Multi-armed bandits

Solving Pure Exploration Problems with the Top Two Approach
In pure exploration problems for stochastic multi-armed bandits, the objective is to answer inquiries regarding a set of unknown …
PDF Cite Slides Video
Differentially Private Best-Arm Identification
Best Arm Identification (BAI) problems are progressively used for data-sensitive applications, such as designing adaptive clinical …
PDF Cite Code Slides
An Anytime Algorithm for Good Arm Identification
In good arm identification (GAI), the goal is to identify one arm whose average performance exceeds a given threshold, referred to as …
PDF Cite
An ε-Best-Arm Identification Algorithm for Fixed-Confidence and Beyond
We propose EB-TCε, a novel sampling rule for ε-best arm identification in stochastic bandits. It is the first instance of Top Two …
PDF Cite Code Poster Slides Video
On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence
Best Arm Identification (BAI) problems are progressively used for data-sensitive applications, such as designing adaptive clinical …
PDF Cite Code Poster Slides Video
Non-Asymptotic Analysis of a UCB-based Top Two Algorithm
A Top Two sampling rule for bandit identification is a method which selects the next arm to sample from among two candidate arms, a …
PDF Cite Code Poster Slides Video
Dealing with Unknown Variances in Best-Arm Identification
The problem of identifying the best arm among a collection of items having Gaussian rewards distribution is well understood when the …
PDF Cite Slides Video
Top Two Algorithms Revisited
Top Two algorithms arose as an adaptation of Thompson sampling to best arm identification in multi-armed bandit models (Russo, 2016), …
PDF Cite Code Poster Slides Video