English
Related papers

Related papers: Pure exploration in multi-armed bandits with low r…

200 papers

The Competing Bandits framework is a recently emerging area that integrates multi-armed bandits in online learning with stable matching in game theory. While conventional models assume that all players and arms are constantly available, in…

Machine Learning · Computer Science 2026-03-23 Shinnosuke Uba , Yutaro Yamaguchi

We consider the bandit problem of selecting $K$ out of $N$ arms at each time step. The reward can be a non-linear function of the rewards of the selected individual arms. The direct use of a multi-armed bandit algorithm requires choosing…

Machine Learning · Computer Science 2026-02-16 Mridul Agarwal , Vaneet Aggarwal , Christopher J. Quinn , Abhishek Umrawal

We consider a multi-armed bandit setting where, at the beginning of each round, the learner receives noisy independent, and possibly biased, \emph{evaluations} of the true reward of each arm and it selects $K$ arms with the objective of…

Machine Learning · Computer Science 2022-04-13 Evrard Garcelon , Vashist Avadhanula , Alessandro Lazaric , Matteo Pirotta

In this paper, we introduce the notion of replicable policies in the context of stochastic bandits, one of the canonical problems in interactive learning. A policy in the bandit environment is called replicable if it pulls, with high…

Machine Learning · Computer Science 2023-02-16 Hossein Esfandiari , Alkis Kalavasis , Amin Karbasi , Andreas Krause , Vahab Mirrokni , Grigoris Velegkas

We consider the problem of best arm identification in a variant of multi-armed bandits called linked bandits. In a single interaction with linked bandits, multiple arms are played sequentially until one of them receives a positive reward.…

Machine Learning · Computer Science 2019-01-29 Anant Gupta

Preference-based Pure Exploration (PrePEx) aims to identify with a given confidence level the set of Pareto optimal arms in a vector-valued (aka multi-objective) bandit, where the reward vectors are ordered via a (given) preference cone…

Machine Learning · Computer Science 2025-08-25 Udvas Das , Apurv Shukla , Debabrota Basu

We study the Combinatorial Pure Exploration problem with Continuous and Separable reward functions (CPE-CS) in the stochastic multi-armed bandit setting. In a CPE-CS instance, we are given several stochastic arms with unknown distributions,…

Machine Learning · Computer Science 2018-05-07 Weiran Huang , Jungseul Ok , Liang Li , Wei Chen

Multi-player multi-armed bandit is an increasingly relevant decision-making problem, motivated by applications to cognitive radio systems. Most research for this problem focuses exclusively on the settings that players have \textit{full…

Machine Learning · Computer Science 2022-12-14 Guojun Xiong , Jian Li

In multi-armed bandits, the tasks of reward maximization and pure exploration are often at odds with each other. The former focuses on exploiting arms with the highest means, while the latter may require constant exploration across all…

Machine Learning · Computer Science 2024-10-22 Brian Cho , Dominik Meier , Kyra Gan , Nathan Kallus

We consider a bandit problem where the buget is smaller than the number of arms, which may be infinite. In this regime, the usual objective in the literature is to minimize simple regret. To analyze broad classes of distributions with…

Statistics Theory · Mathematics 2025-11-04 Emmanuel Pilliat

Motivated by a number of real-world applications from domains like healthcare and sustainable transportation, in this paper we study a scenario of repeated principal-agent games within a multi-armed bandit (MAB) framework, where: the…

Machine Learning · Computer Science 2023-05-09 Ilgin Dogan , Zuo-Jun Max Shen , Anil Aswani

In stochastic low-rank matrix bandit, the expected reward of an arm is equal to the inner product between its feature matrix and some unknown $d_1$ by $d_2$ low-rank parameter matrix $\Theta^*$ with rank $r \ll d_1\wedge d_2$. While all…

Machine Learning · Statistics 2024-04-30 Yue Kang , Cho-Jui Hsieh , Thomas C. M. Lee

The Greedy algorithm is the simplest heuristic in sequential decision problem that carelessly takes the locally optimal choice at each round, disregarding any advantages of exploring and/or information gathering. Theoretically, it is known…

Machine Learning · Computer Science 2021-01-05 Matthieu Jedor , Jonathan Louëdec , Vianney Perchet

Cascading bandits is a natural and popular model that frames the task of learning to rank from Bernoulli click feedback in a bandit setting. For the case of unstructured rewards, we prove matching upper and lower bounds for the…

Machine Learning · Computer Science 2022-10-11 Daniel Vial , Sujay Sanghavi , Sanjay Shakkottai , R. Srikant

We study the problem of exploration in Reinforcement Learning and present a novel model-free solution. We adopt an information-theoretical viewpoint and start from the instance-specific lower bound of the number of samples that have to be…

Machine Learning · Computer Science 2024-07-02 Alessio Russo , Alexandre Proutiere

We consider stochastic multi-armed bandit problems where the expected reward is a Lipschitz function of the arm, and where the set of arms is either discrete or continuous. For discrete Lipschitz bandits, we derive asymptotic problem…

Machine Learning · Computer Science 2014-05-20 Stefan Magureanu , Richard Combes , Alexandre Proutiere

This paper studies the Best-of-K Bandit game: At each time the player chooses a subset S among all N-choose-K possible options and observes reward max(X(i) : i in S) where X is a random vector drawn from a joint distribution. The objective…

Machine Learning · Computer Science 2016-03-22 Max Simchowitz , Kevin Jamieson , Benjamin Recht

In this paper, we consider the distributed stochastic multi-armed bandit problem, where a global arm set can be accessed by multiple players independently. The players are allowed to exchange their history of observations with each other at…

Machine Learning · Computer Science 2020-02-13 Shuang Liu , Cheng Chen , Zhihua Zhang

Causal knowledge about the relationships among decision variables and a reward variable in a bandit setting can accelerate the learning of an optimal decision. Current works often assume the causal graph is known, which may not always be…

Machine Learning · Statistics 2024-11-07 Muhammad Qasim Elahi , Mahsa Ghasemi , Murat Kocaoglu

Fast changing states or volatile environments pose a significant challenge to online optimization, which needs to perform rapid adaptation under limited observation. In this paper, we give query and regret optimal bandit algorithms under…

Machine Learning · Computer Science 2024-01-18 Zhou Lu , Qiuyi Zhang , Xinyi Chen , Fred Zhang , David Woodruff , Elad Hazan