English
Related papers

Related papers: Improved Algorithms for Conservative Exploration i…

200 papers

This paper presents a finite-time analysis of the KL-UCB algorithm, an online, horizon-free index policy for stochastic bandit problems. We prove two distinct results: first, for arbitrary bounded rewards, the KL-UCB algorithm satisfies a…

Statistics Theory · Mathematics 2013-08-30 Aurélien Garivier , Olivier Cappé

We consider the bandit-based framework for diversity-preserving recommendations introduced by Celis et al. (2019), who approached it in the case of a polytope mainly by a reduction to the setting of linear bandits. We design a UCB algorithm…

Machine Learning · Statistics 2024-07-25 Hédi Hadiji , Sébastien Gerchinovitz , Jean-Michel Loubes , Gilles Stoltz

We study linear contextual bandits with access to a large, confounded, offline dataset that was sampled from some fixed policy. We show that this problem is closely related to a variant of the bandit problem with side information. We…

Machine Learning · Computer Science 2021-08-11 Guy Tennenholtz , Uri Shalit , Shie Mannor , Yonathan Efroni

The multi-armed bandit (MAB) problem is a foundational framework in sequential decision-making under uncertainty, extensively studied for its applications in areas such as clinical trials, online advertising, and resource allocation.…

Machine Learning · Computer Science 2024-10-28 Ali Baheri

We consider the classic online learning and stochastic multi-armed bandit (MAB) problems, when at each step, the online policy can probe and find out which of a small number ($k$) of choices has better reward (or loss) before making its…

Data Structures and Algorithms · Computer Science 2022-11-08 Aditya Bhaskara , Sreenivas Gollapudi , Sungjin Im , Kostas Kollias , Kamesh Munagala

Upper Confidence Bound (UCB) algorithms are a widely-used class of sequential algorithms for the $K$-armed bandit problem. Despite extensive research over the past decades aimed at understanding their asymptotic and (near) minimax…

Statistics Theory · Mathematics 2024-12-10 Qiyang Han , Koulik Khamaru , Cun-Hui Zhang

The linear contextual bandit literature is mostly focused on the design of efficient learning algorithms for a given representation. However, a contextual bandit problem may admit multiple linear representations, each one with different…

Machine Learning · Computer Science 2021-04-09 Matteo Papini , Andrea Tirinzoni , Marcello Restelli , Alessandro Lazaric , Matteo Pirotta

Multi-armed bandit models have proven to be useful in modeling many real world problems in the areas of control and sequential decision making with partial information. However, in many scenarios, such as those prevalent in healthcare and…

Optimization and Control · Mathematics 2024-08-27 Qinyang He , Yonatan Mintz

We study the online restless bandit problem, where the state of each arm evolves according to a Markov chain, and the reward of pulling an arm depends on both the pulled arm and the current state of the corresponding Markov chain. In this…

Machine Learning · Computer Science 2020-11-09 Siwei Wang , Longbo Huang , John C. S. Lui

We study a finite-horizon restless multi-armed bandit problem with multiple actions, dubbed R(MA)^2B. The state of each arm evolves according to a controlled Markov decision process (MDP), and the reward of pulling an arm depends on both…

Machine Learning · Computer Science 2022-03-25 Guojun Xiong , Jian Li , Rahul Singh

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

We study the linear contextual bandit problem with finite action sets. When the problem dimension is $d$, the time horizon is $T$, and there are $n \leq 2^{d/2}$ candidate actions per time period, we (1) show that the minimax expected…

Machine Learning · Statistics 2020-08-20 Yingkai Li , Yining Wang , Yuan Zhou

In many modern applications, a system must dynamically choose between several adaptive learning algorithms that are trained online. Examples include model selection in streaming environments, switching between trading strategies in finance,…

Machine Learning · Computer Science 2026-01-19 Ilgam Latypov , Alexandra Suvorikova , Alexey Kroshnin , Alexander Gasnikov , Yuriy Dorn

Traditional online learning models are typically initialized from scratch. By contrast, contemporary real-world applications often have access to historical datasets that can potentially enhanced the online learning processes. We study how…

Machine Learning · Computer Science 2025-12-19 Wang Chi Cheung , Lixing Lyu

I present the first algorithm for stochastic finite-armed bandits that simultaneously enjoys order-optimal problem-dependent regret and worst-case regret. Besides the theoretical results, the new algorithm is simple, efficient and…

Machine Learning · Computer Science 2016-02-25 Tor Lattimore

We consider the problem of finitely parameterized multi-armed bandits where the model of the underlying stochastic environment can be characterized based on a common unknown parameter. The true parameter is unknown to the learning agent.…

Machine Learning · Computer Science 2020-11-10 Kishan Panaganti , Dileep Kalathil

We study a stochastic multi-armed bandit problem where an agent is granted a free exploration budget before regret accumulates, a setting not captured by the classic regret minimization or pure exploration paradigms. The goal is to design…

Machine Learning · Computer Science 2026-05-26 Yunlong Hou , Zixin Zhong , Vincent Y. F. Tan

We consider what we call the offline-to-online learning setting, focusing on stochastic finite-armed bandit problems. In offline-to-online learning, a learner starts with offline data collected from interactions with an unknown environment…

Machine Learning · Computer Science 2025-03-11 Flore Sentenac , Ilbin Lee , Csaba Szepesvari

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

This paper considers the use of a simple posterior sampling algorithm to balance between exploration and exploitation when learning to optimize actions such as in multi-armed bandit problems. The algorithm, also known as Thompson Sampling,…

Machine Learning · Computer Science 2014-02-04 Daniel Russo , Benjamin Van Roy