English
Related papers

Related papers: Thompson Sampling: An Asymptotically Optimal Finit…

200 papers

The PhD thesis of Maillard (2013) presents a rather obscure algorithm for the $K$-armed bandit problem. This less-known algorithm, which we call Maillard sampling (MS), computes the probability of choosing each arm in a \textit{closed…

Machine Learning · Statistics 2022-03-08 Jie Bian , Kwang-Sung Jun

This paper presents a class of Dynamic Multi-Armed Bandit problems where the reward can be modeled as the noisy output of a time varying linear stochastic dynamic system that satisfies some boundedness constraints. The class allows many…

Machine Learning · Computer Science 2017-10-10 T. W. U. Madhushani , D. H. S. Maithripala , N. E. Leonard

We address the problem of regret minimization in logistic contextual bandits, where a learner decides among sequential actions or arms given their respective contexts to maximize binary rewards. Using a fast inference procedure with…

Machine Learning · Statistics 2018-05-22 Bianca Dumitrascu , Karen Feng , Barbara E Engelhardt

This note introduce three Bayesian style Multi-armed bandit algorithms: Information-directed sampling, Thompson Sampling and Generalized Thompson Sampling. The goal is to give an intuitive explanation for these three algorithms and their…

Machine Learning · Computer Science 2015-03-25 Li Zhou

Non-stationary multi-armed bandit (NS-MAB) problems have recently received significant attention. NS-MAB are typically modelled in two scenarios: abruptly changing, where reward distributions remain constant for a certain period and change…

Machine Learning · Computer Science 2023-05-23 Han Qi , Yue Wang , Li Zhu

We study the benefits of sparsity in nonparametric contextual bandit problems, in which the set of candidate features is countably or uncountably infinite. Our contribution is two-fold. First, using a novel reduction to sequences of…

Machine Learning · Statistics 2026-01-16 Hamish Flynn , Julia Olkhovskaya , Paul Rognon-Vael

Adaptive sampling schemes are well known to create complex dependence that may invalidate conventional inference methods. A recent line of work shows that this need not be the case for UCB-type algorithms in multi-armed bandits. A central…

Statistics Theory · Mathematics 2026-01-30 Qiyang Han

We here adopt Bayesian nonparametric mixture models to extend multi-armed bandits in general, and Thompson sampling in particular, to scenarios where there is reward model uncertainty. In the stochastic multi-armed bandit, the reward for…

Machine Learning · Statistics 2022-08-26 Iñigo Urteaga , Chris H. Wiggins

We study, to the best of our knowledge, the first Bayesian algorithm for unimodal Multi-Armed Bandit (MAB) problems with graph structure. In this setting, each arm corresponds to a node of a graph and each edge provides a relationship,…

Machine Learning · Computer Science 2016-11-23 Stefano Paladino , Francesco Trovò , Marcello Restelli , Nicola Gatti

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

In fixed budget bandit identification, an algorithm sequentially observes samples from several distributions up to a given final time. It then answers a query about the set of distributions. A good algorithm will have a small probability of…

Machine Learning · Statistics 2023-07-03 Rémy Degenne

Learning the minimum/maximum mean among a finite set of distributions is a fundamental sub-task in planning, game tree search and reinforcement learning. We formalize this learning task as the problem of sequentially testing how the minimum…

Machine Learning · Statistics 2018-06-05 Emilie Kaufmann , Wouter Koolen , Aurelien Garivier

We propose the kl-UCB ++ algorithm for regret minimization in stochastic bandit models with exponential families of distributions. We prove that it is simultaneously asymptotically optimal (in the sense of Lai and Robbins' lower bound) and…

Machine Learning · Statistics 2017-09-21 Pierre Ménard , Aurélien Garivier

The staggering feats of AI systems have brought to attention the topic of AI Alignment: aligning a "superintelligent" AI agent's actions with humanity's interests. Many existing frameworks/algorithms in alignment study the problem on a…

Machine Learning · Computer Science 2024-10-22 Hong Jun Jeon , Benjamin Van Roy

The multi-armed bandit (MAB) problem is a classic example of the exploration-exploitation dilemma. It is concerned with maximising the total rewards for a gambler by sequentially pulling an arm from a multi-armed slot machine where each arm…

Machine Learning · Statistics 2018-05-16 Xue Lu , Niall Adams , Nikolas Kantas

As the cornerstone of modern portfolio theory, Markowitz's mean-variance optimization is considered a major model adopted in portfolio management. However, due to the difficulty of estimating its parameters, it cannot be applied to all…

Machine Learning · Computer Science 2019-11-15 Mengying Zhu , Xiaolin Zheng , Yan Wang , Yuyuan Li , Qianqiao Liang

Recent advances in deep reinforcement learning have made significant strides in performance on applications such as Go and Atari games. However, developing practical methods to balance exploration and exploitation in complex domains remains…

Machine Learning · Statistics 2018-02-27 Carlos Riquelme , George Tucker , Jasper Snoek

We study the problem of stochastic contextual bandits in the agnostic setting, where the goal is to compete with the best policy in a given class without assuming realizability or imposing model restrictions on losses or rewards. In this…

Machine Learning · Statistics 2026-04-06 Samuel Girard , Aurelien Bibaut , Arthur Gretton , Nathan Kallus , Houssam Zenati

We explore a stochastic contextual linear bandit problem where the agent observes a noisy, corrupted version of the true context through a noise channel with an unknown noise parameter. Our objective is to design an action policy that can…

Machine Learning · Computer Science 2024-03-26 Sharu Theresa Jose , Shana Moothedath

We study $K$-armed bandit problems where the reward distributions of the arms are all supported on the $[0,1]$ interval. It has been a challenge to design regret-efficient randomized exploration algorithms in this setting. Maillard sampling…

Machine Learning · Computer Science 2024-04-15 Hao Qin , Kwang-Sung Jun , Chicheng Zhang