← Search

Julien Seznec

2 accepted papers

2020

A single algorithm for both restless and rested rotting bandits

AISTATS 2020poster

In many application domains (e.g., recommender systems, intelligent tutoring systems), the rewards associated to the available actions tend to decrease over time. This decay is either caused by the actions executed in the past (e.g., a user may get bored when songs of the same genre are recommended…

2019

Rotting bandits are no harder than stochastic ones

AISTATS 2019poster

In stochastic multi-armed bandits, the reward distribution of each arm is assumed to be stationary. This assumption is often violated in practice (e.g., in recommendation systems), where the reward of an arm may change whenever is selected, i.e., rested bandit setting. In this paper, we consider the…

Cited by 73SourcePDFScholar