English
Related papers

Related papers: A Sensing Policy Based on Confidence Bounds and a …

200 papers

We consider a linear stochastic bandit problem where the dimension $K$ of the unknown parameter $\theta$ is larger than the sampling budget $n$. In such cases, it is in general impossible to derive sub-linear regret bounds since usual…

Statistics Theory · Mathematics 2012-05-23 Alexandra Carpentier , Rémi Munos

We study nonparametric contextual bandits under batch constraints, where the expected reward for each action is modeled as a smooth function of covariates, and the policy updates are made at the end of each batch of observations. We…

Statistics Theory · Mathematics 2025-10-06 Rong Jiang , Cong Ma

Information-directed sampling (IDS) is a powerful framework for solving bandit problems which has shown strong results in both Bayesian and frequentist settings. However, frequentist IDS, like many other bandit algorithms, requires that one…

Machine Learning · Statistics 2025-03-10 Piotr M. Suder , Eric Laber

Contextual multi-armed bandit algorithms are widely used in sequential decision tasks such as news article recommendation systems, web page ad placement algorithms, and mobile health. Most of the existing algorithms have regret proportional…

Machine Learning · Statistics 2020-02-14 Gi-Soo Kim , Myunghee Cho Paik

We study the problem of information sharing and cooperation in Multi-Player Multi-Armed bandits. We propose the first algorithm that achieves logarithmic regret for this problem when the collision reward is unknown. Our results are based on…

Machine Learning · Computer Science 2022-10-04 Aldo Pacchiano , Peter Bartlett , Michael I. Jordan

We study a decentralized cooperative stochastic multi-armed bandit problem with $K$ arms on a network of $N$ agents. In our model, the reward distribution of each arm is the same for each agent and rewards are drawn independently across…

Machine Learning · Computer Science 2019-10-25 David Martínez-Rubio , Varun Kanade , Patrick Rebeschini

We study the problem of online learning in adversarial bandit problems under a partial observability model called off-policy feedback. In this sequential decision making problem, the learner cannot directly observe its rewards, but instead…

Machine Learning · Computer Science 2022-07-20 Germano Gabbianelli , Matteo Papini , Gergely Neu

The multi-armed bandit (MAB) model is one of the most classical models to study decision-making in an uncertain environment. In this model, a player chooses one of $K$ possible arms of a bandit machine to play at each time step, where the…

Machine Learning · Computer Science 2023-06-13 Bo Li , Chi Ho Yeung

We consider a variant of the traditional multi-armed bandit problem in which each arm is only able to provide one-bit feedback during each pull based on its past history of rewards. Our main result is the following: given an upper…

Machine Learning · Computer Science 2020-12-08 Daniel Vial , Sanjay Shakkottai , R. Srikant

We introduce the "inverse bandit" problem of estimating the rewards of a multi-armed bandit instance from observing the learning process of a low-regret demonstrator. Existing approaches to the related problem of inverse reinforcement…

Machine Learning · Statistics 2022-02-23 Wenshuo Guo , Kumar Krishna Agrawal , Aditya Grover , Vidya Muthukumar , Ashwin Pananjady

Contextual bandit algorithms have become widely used for recommendation in online systems (e.g. marketplaces, music streaming, news), where they now wield substantial influence on which items get exposed to the users. This raises questions…

Machine Learning · Computer Science 2021-09-14 Lequn Wang , Yiwei Bai , Wen Sun , Thorsten Joachims

The Combinatorial Multi-Armed Bandit problem is a sequential decision-making problem in which an agent selects a set of arms on each round, observes feedback for each of these arms and aims to maximize a known reward function of the arms it…

Machine Learning · Computer Science 2020-07-17 Nadav Merlis , Shie Mannor

Finding an optimal sensing policy for a particular access policy and sensing scheme is a laborious combinatorial problem that requires the system model parameters to be known. In practise the parameters or the model itself may not be…

Machine Learning · Computer Science 2012-09-11 Jan Oksanen , Jarmo Lundén , Visa Koivunen

We study the stochastic combinatorial semi-bandit problem with unrestricted feedback delays under merit-based fairness constraints. This is motivated by applications such as crowdsourcing, and online advertising, where immediate feedback is…

Machine Learning · Computer Science 2024-07-30 Ziqun Chen , Kechao Cai , Zhuoyue Chen , Jinbei Zhang , John C. S. Lui

We consider a remote contextual multi-armed bandit (CMAB) problem, in which the decision-maker observes the context and the reward, but must communicate the actions to be taken by the agents over a rate-limited communication channel. This…

Information Theory · Computer Science 2022-02-11 Francesco Pase , Deniz Gunduz , Michele Zorzi

Multi-arm bandits are gaining popularity as they enable real-world sequential decision-making across application areas, including clinical trials, recommender systems, and online decision-making. Consequently, there is an increased desire…

Methodology · Statistics 2023-03-01 Dae Woong Ham , Iavor Bojinov , Michael Lindon , Martin Tingley

The stochastic multi-armed bandit model is a simple abstraction that has proven useful in many different contexts in statistics and machine learning. Whereas the achievable limit in terms of regret minimization is now well known, our aim is…

Machine Learning · Statistics 2016-11-15 Emilie Kaufmann , Olivier Cappé , Aurélien Garivier

The multi-armed bandit problems have been studied mainly under the measure of expected total reward accrued over a horizon of length $T$. In this paper, we address the issue of risk in multi-armed bandit problems and develop parallel…

Machine Learning · Computer Science 2017-08-16 Sattar Vakili , Qing Zhao

We consider a stochastic bandit problem with countably many arms that belong to a finite set of types, each characterized by a unique mean reward. In addition, there is a fixed distribution over types which sets the proportion of each type…

Machine Learning · Computer Science 2021-05-25 Anand Kalvit , Assaf Zeevi

In this paper, we study the problem of optimal data collection for policy evaluation in linear bandits. In policy evaluation, we are given a target policy and asked to estimate the expected reward it will obtain when executed in a…

Machine Learning · Statistics 2024-03-04 Subhojyoti Mukherjee , Qiaomin Xie , Josiah Hanna , Robert Nowak