Sub-sampling for Efficient Non-Parametric Bandit Exploration - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

Sub-sampling for Efficient Non-Parametric Bandit Exploration

Abstract

In this paper we propose the first multi-armed bandit algorithm based on re-sampling that achieves asymptotically optimal regret simultaneously for different families of arms (namely Bernoulli, Gaussian and Poisson distributions). Unlike Thompson Sampling which requires to specify a different prior to be optimal in each case, our proposal RB-SDA does not need any distribution-dependent tuning. RB-SDA belongs to the family of Sub-sampling Duelling Algorithms (SDA) which combines the sub-sampling idea first used by the BESA [1] and SSMC [2] algorithms with different sub-sampling schemes. In particular, RB-SDA uses Random Block sampling. We perform an experimental study assessing the flexibility and robustness of this promising novel approach for exploration in bandit models.
Fichier principal
Vignette du fichier
sda_hal.pdf (551 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02977552 , version 1 (26-10-2020)

Identifiers

Cite

Dorian Baudry, Emilie Kaufmann, Odalric-Ambrym Maillard. Sub-sampling for Efficient Non-Parametric Bandit Exploration. NeurIPS 2020, Dec 2020, Vancouver, Canada. ⟨hal-02977552⟩
344 View
185 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More