中文
相关论文

相关论文: Garbage In, Reward Out: Bootstrapping Exploration …

200 篇论文

We study the best-arm identification problem in linear bandit, where the rewards of the arms depend linearly on an unknown parameter $\theta^*$ and the objective is to return the arm with the largest reward. We characterize the complexity…

机器学习 · 计算机科学 2014-11-05 Marta Soare , Alessandro Lazaric , Rémi Munos

We study the problem of corralling stochastic bandit algorithms, that is combining multiple bandit algorithms designed for a stochastic environment, with the goal of devising a corralling algorithm that performs almost as well as the best…

机器学习 · 计算机科学 2021-03-02 Raman Arora , Teodor V. Marinov , Mehryar Mohri

We study the bandit problem where the underlying expected reward is a Bounded Mean Oscillation (BMO) function. BMO functions are allowed to be discontinuous and unbounded, and are useful in modeling signals with infinities in the do-main.…

机器学习 · 计算机科学 2020-07-20 Tianyu Wang , Cynthia Rudin

We study a variant of the bandit problem where side information in the form of bounds on the mean of each arm is provided. We prove that these translate to tighter estimates of subgaussian factors and develop novel algorithms that exploit…

机器学习 · 计算机科学 2024-10-29 Nihal Sharma , Soumya Basu , Karthikeyan Shanmugam , Sanjay Shakkottai

We investigate the problem of unconstrained combinatorial multi-armed bandits with full-bandit feedback and stochastic rewards for submodular maximization. Previous works investigate the same problem assuming a submodular and monotone…

机器学习 · 计算机科学 2023-02-03 Fares Fourati , Vaneet Aggarwal , Christopher John Quinn , Mohamed-Slim Alouini

We consider a non-stationary formulation of the stochastic multi-armed bandit where the rewards are no longer assumed to be identically distributed. For the best-arm identification task, we introduce a version of Successive Elimination…

人工智能 · 计算机科学 2016-09-09 Robin Allesiardo , Raphaël Féraud , Odalric-Ambrym Maillard

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…

机器学习 · 计算机科学 2025-09-03 Chanakya Varude , Jay Chaudhary , Siddharth Kaushik , Prasanna Chaporkar

In a multi-armed bandit (MAB) problem a gambler needs to choose at each round of play one of K arms, each characterized by an unknown reward distribution. Reward realizations are only observed when an arm is selected, and the gambler's…

机器学习 · 计算机科学 2019-06-11 Omar Besbes , Yonatan Gur , Assaf Zeevi

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…

机器学习 · 计算机科学 2026-02-16 Mridul Agarwal , Vaneet Aggarwal , Christopher J. Quinn , Abhishek Umrawal

Canonical algorithms for multi-armed bandits typically assume a stationary reward environment where the size of the action space (number of arms) is small. More recently developed methods typically relax only one of these assumptions:…

机器学习 · 计算机科学 2025-06-02 Derek Everett , Fred Lu , Edward Raff , Fernando Camacho , James Holt

Despite the great interest in the bandit problem, designing efficient algorithms for complex models remains challenging, as there is typically no analytical way to quantify uncertainty. In this paper, we propose Multiplier Bootstrap-based…

机器学习 · 计算机科学 2023-02-06 Runzhe Wan , Haoyu Wei , Branislav Kveton , Rui Song

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…

机器学习 · 计算机科学 2022-04-13 Evrard Garcelon , Vashist Avadhanula , Alessandro Lazaric , Matteo Pirotta

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…

量子物理 · 物理学 2023-02-02 Daochen Wang , Xuchen You , Tongyang Li , Andrew M. Childs

We consider the Max $K$-Armed Bandit problem, where a learning agent is faced with several stochastic arms, each a source of i.i.d. rewards of unknown distribution. At each time step the agent chooses an arm, and observes the reward of the…

机器学习 · 统计学 2015-12-25 Yahel David , Nahum Shimkin

We investigate a Bayesian $k$-armed bandit problem in the \emph{many-armed} regime, where $k \geq \sqrt{T}$ and $T$ represents the time horizon. Initially, and aligned with recent literature on many-armed bandit problems, we observe that…

机器学习 · 计算机科学 2024-03-21 Mohsen Bayati , Nima Hamidi , Ramesh Johari , Khashayar Khosravi

In this paper, we consider a bandit problem in which there are a number of groups each consisting of infinitely many arms. Whenever a new arm is requested from a given group, its mean reward is drawn from an unknown reservoir distribution…

机器学习 · 统计学 2023-02-02 Ivan Lau , Yan Hao Ling , Mayank Shrivastava , Jonathan Scarlett

We study \emph{multi-armed bandits} (MABs) augmented with \emph{best-action queries}, in which the learner may additionally query an oracle that reveals the best arm in the current round. This setting was recently characterized by Russo et…

机器学习 · 计算机科学 2026-05-12 Francesco Bacchiocchi , Matteo Castiglioni , Alberto Marchesi , Francesco Emanuele Stradi

The stochastic multi-armed bandit setting has been recently studied in the non-stationary regime, where the mean payoff of each action is a non-decreasing function of the number of rounds passed since it was last played. This model captures…

机器学习 · 计算机科学 2022-10-13 Orestis Papadigenopoulos , Constantine Caramanis , Sanjay Shakkottai

We study incentivized exploration for the multi-armed bandit (MAB) problem with non-stationary reward distributions, where players receive compensation for exploring arms other than the greedy choice and may provide biased feedback on the…

机器学习 · 计算机科学 2024-03-19 Sourav Chakraborty , Lijun Chen

We consider the Max $K$-Armed Bandit problem, where a learning agent is faced with several sources (arms) of items (rewards), and interested in finding the best item overall. At each time step the agent chooses an arm, and obtains a random…

机器学习 · 统计学 2015-08-25 Yahel David , Nahum Shimkin