A single algorithm for both restless and rested rotting bandits - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

A single algorithm for both restless and rested rotting bandits

Pierre Menard
  • Function : Author
Michal Valko


In many application domains (e.g., recommender systems, intelligent tutoring systems), the rewards associated to the 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get bored when songs of the same genre are recommended over and over) or by an external factor (e.g., content becomes outdated). These two situations can be modeled as specific instances of the rested and restless bandit settings, where arms are rotting (i.e., their value decrease over time). These problems were thought to be significantly different, since Levine et al. (2017) showed that state-of-the-art algorithms for restless bandit perform poorly in the rested rotting setting. In this paper, we introduce a novel algorithm, Rotting Adaptive Window UCB (RAW-UCB), that achieves near-optimal regret in both rotting rested and restless bandit, without any prior knowledge of the setting (rested or restless) and the type of non-stationarity (e.g., piece-wise constant, bounded variation). This is in striking contrast with previous negative results showing that no algorithm can achieve similar results as soon as rewards are allowed to increase. We confirm our theoretical findings on a number of synthetic and datasetbased experiments.
Fichier principal
Vignette du fichier
seznec2020single.pdf (28.34 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03287835 , version 1 (15-07-2021)


  • HAL Id : hal-03287835 , version 1


Julien Seznec, Pierre Menard, Alessandro Lazaric, Michal Valko. A single algorithm for both restless and rested rotting bandits. International Conference on Artificial Intelligence and Statistics, Aug 2020, Palermo / Virtual, Italy. ⟨hal-03287835⟩
46 View
20 Download


Gmail Facebook Twitter LinkedIn More