Skip to yearly menu bar Skip to main content


Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards

Kyungjae Lee · Hongjun Yang · Sungbin Lim · Songhwai Oh

Poster Session 4 #1276

Abstract: In this paper, we consider stochastic multi-armed bandits (MABs) with heavy-tailed rewards, whose p-th moment is bounded by a constant nu_p for 1

Chat is not available.