English
Related papers

Related papers: Clus-UCB: A Near-Optimal Algorithm for Clustered B…

200 papers

We study dueling bandits with weak utility-based regret when preferences over arms have a total order and carry observable feature vectors. The order is assumed to be determined by these feature vectors, an unknown preference vector, and a…

Machine Learning · Computer Science 2017-06-16 Bangrui Chen , Peter I. Frazier

Identifying the best arm of a multi-armed bandit is a central problem in bandit optimization. We study a quantum computational version of this problem with coherent oracle access to states encoding the reward probabilities of each arm as…

Quantum Physics · Physics 2023-02-02 Daochen Wang , Xuchen You , Tongyang Li , Andrew M. Childs

Much of the literature on optimal design of bandit algorithms is based on minimization of expected regret. It is well known that designs that are optimal over certain exponential families can achieve expected regret that grows…

Machine Learning · Computer Science 2024-11-14 Lin Fan , Peter W. Glynn

Motivated by economic applications such as recommender systems, we study the behavior of stochastic bandits algorithms under \emph{strategic behavior} conducted by rational actors, i.e., the arms. Each arm is a \emph{self-interested}…

Machine Learning · Computer Science 2020-11-16 Zhe Feng , David C. Parkes , Haifeng Xu

We study the piecewise stationary combinatorial semi-bandit problem with causally related rewards. In our nonstationary environment, variations in the base arms' distributions, causal relationships between rewards, or both, change the…

Machine Learning · Computer Science 2023-07-27 Behzad Nourani-Koliji , Steven Bilaj , Amir Rezaei Balef , Setareh Maghsudi

We consider the problem of latent bandits with cluster structure where there are multiple users, each with an associated multi-armed bandit problem. These users are grouped into \emph{latent} clusters such that the mean reward vectors of…

Machine Learning · Computer Science 2023-07-12 Soumyabrata Pal , Arun Sai Suggala , Karthikeyan Shanmugam , Prateek Jain

We generalize the multiple-play multi-armed bandits (MP-MAB) problem with a shareable arm setting, in which several plays can share the same arm. Furthermore, each shareable arm has a finite reward capacity and a ''per-load'' reward…

Machine Learning · Computer Science 2022-06-20 Xuchuang Wang , Hong Xie , John C. S. Lui

We study the tail behavior of regret in stochastic multi-armed bandits for algorithms that are asymptotically optimal in expectation. While minimizing expected regret is the classical objective, recent work shows that even such algorithms…

Information Theory · Computer Science 2026-04-17 Subhodip Panda , Shubhada Agrawal

This paper proposes a variant of multiple-play stochastic bandits tailored to resource allocation problems arising from LLM applications, edge intelligence, etc. The model is composed of $M$ arms and $K$ plays. Each arm has a stochastic…

Artificial Intelligence · Computer Science 2025-12-29 Hong Xie , Haoran Gu , Yanying Huang , Tao Tan , Defu Lian

We consider the upper confidence bound strategy for Gaussian multi-armed bandits with known control horizon sizes $N$ and build its limiting description with a system of stochastic differential equations and ordinary differential equations.…

Machine Learning · Computer Science 2023-05-12 Sergey Garbar

This paper investigates stochastic and adversarial combinatorial multi-armed bandit problems. In the stochastic setting under semi-bandit feedback, we derive a problem-specific regret lower bound, and discuss its scaling with the dimension…

Machine Learning · Computer Science 2015-11-09 Richard Combes , M. Sadegh Talebi , Alexandre Proutiere , Marc Lelarge

The Rising Multi-Armed Bandit (RMAB) framework models environments where expected rewards of arms increase with plays, which models practical scenarios where performance of each option improves with the repeated usage, such as in robotics…

Machine Learning · Computer Science 2026-02-16 Seockbean Song , Chenyu Gan , Youngsik Yoon , Siwei Wang , Wei Chen , Jungseul Ok

We consider the correlated multiarmed bandit (MAB) problem in which the rewards associated with each arm are modeled by a multivariate Gaussian random variable, and we investigate the influence of the assumptions in the Bayesian prior on…

Optimization and Control · Mathematics 2015-07-09 Vaibhav Srivastava , Paul Reverdy , Naomi Ehrich Leonard

Strategic behavior against sequential learning methods, such as "click framing" in real recommendation systems, have been widely observed. Motivated by such behavior we study the problem of combinatorial multi-armed bandits (CMAB) under…

Machine Learning · Computer Science 2021-11-22 Jing Dong , Ke Li , Shuai Li , Baoxiang Wang

In multi-armed bandit problems, the typical goal is to identify the arm with the highest reward. This paper explores a threshold-based bandit problem, aiming to select an arm based on its relation to a prescribed threshold \(\tau \). We…

Machine Learning · Computer Science 2025-09-03 Chanakya Varude , Jay Chaudhary , Siddharth Kaushik , Prasanna Chaporkar

Stochastic bandit algorithms are usually analyzed under a mean-reward criterion, yet many problems favor arms with strong upper-tail performance, which we study herein. For a fixed miscoverage level \(\alpha\), the natural upper-tail target…

Machine Learning · Computer Science 2026-05-11 Chengyu Du , Mengfan Xu

This paper studies a class of constrained restless multi-armed bandits (CRMAB). The constraints are in the form of time varying set of actions (set of available arms). This variation can be either stochastic or semi-deterministic. Given a…

Systems and Control · Computer Science 2021-09-07 Kesav Kaza , Rahul Meshram , Varun Mehta , S. N. Merchant

I introduce and analyse an anytime version of the Optimally Confident UCB (OCUCB) algorithm designed for minimising the cumulative regret in finite-armed stochastic bandits with subgaussian noise. The new algorithm is simple, intuitive (in…

Machine Learning · Computer Science 2016-05-09 Tor Lattimore

The upper confidence bound (UCB) policy is recognized as an order-optimal solution for the classical total-reward bandit problem. While similar UCB-based approaches have been applied to the max bandit problem, which aims to maximize the…

Machine Learning · Statistics 2024-11-04 Nobuaki Kikkawa , Hiroshi Ohno

In many fields such as digital marketing, healthcare, finance, and robotics, it is common to have a well-tested and reliable baseline policy running in production (e.g., a recommender system). Nonetheless, the baseline policy is often…

Machine Learning · Computer Science 2020-02-11 Evrard Garcelon , Mohammad Ghavamzadeh , Alessandro Lazaric , Matteo Pirotta