# Max K-armed bandit: On the ExtremeHunter algorithm and beyond

arXiv: https://arxiv.org/abs/1707.08820 · HTML: https://mlsanity.com/paper/1707.08820/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2017.

## Built on by (most cited first, 8 of 8)

- [On Regression in Extreme Regions](https://mlsanity.com/paper/2303.03084/) (2023)
- [Extreme Bandits using Robust Statistics](https://mlsanity.com/paper/2109.04433/) (2021)
- [Materials Discovery using Max K-Armed Bandit](https://mlsanity.com/paper/2212.08225/) (2022)
- [Efficient Algorithms for Extreme Bandits](https://mlsanity.com/paper/2203.10883/) (2022)
- [A Risk-Averse Framework for Non-Stationary Stochastic Multi-Armed Bandits](https://mlsanity.com/paper/2310.19821/) (2023)
- [Unified theory of upper confidence bound policies for bandit problems targeting total reward, maximal reward, and more](https://mlsanity.com/paper/2411.00339/) (2024)
- [Theoretical Foundations of max@k Reinforcement Learning](https://mlsanity.com/paper/2607.17823/) (2026)
- [Equal-Budget Monte Carlo Tree Search versus Randomized-Restart List Scheduling for DAG Workflows: A Controlled Equal-Budget Computational Study](https://mlsanity.com/paper/2610.12542/) (2026)

## Abstract (arXiv)

This paper is devoted to the study of the max K-armed bandit problem, which consists in sequentially allocating resources in order to detect extreme values. Our contribution is twofold. We first significantly refine the analysis of the ExtremeHunter algorithm carried out in Carpentier and Valko (2014), and next propose an alternative approach, showing that, remarkably, Extreme Bandits can be reduced to a classical version of the bandit problem to a certain extent. Beyond the formal analysis, these two approaches are compared through numerical experiments.