English
Related papers

Related papers: Asymptotically Optimal Problem-Dependent Bandit Po…

200 papers

We propose $\tt RandUCB$, a bandit strategy that builds on theoretically derived confidence intervals similar to upper confidence bound (UCB) algorithms, but akin to Thompson sampling (TS), it uses randomization to trade off exploration and…

Machine Learning · Computer Science 2020-03-24 Sharan Vaswani , Abbas Mehrabian , Audrey Durand , Branislav Kveton

We consider the problem of learning in single-player and multiplayer multiarmed bandit models. Bandit problems are classes of online learning problems that capture exploration versus exploitation tradeoffs. In a multiarmed bandit model,…

Machine Learning · Statistics 2016-12-02 Naumaan Nayyar , Dileep Kalathil , Rahul Jain

The Indexed Minimum Empirical Divergence (IMED) algorithm is a highly effective approach that offers a stronger theoretical guarantee of the asymptotic optimality compared to the Kullback--Leibler Upper Confidence Bound (KL-UCB) algorithm…

Machine Learning · Computer Science 2024-05-27 Jie Bian , Vincent Y. F. Tan

We study the distribution of regret in stochastic multi-armed bandits and episodic reinforcement learning through a unified framework. We formalize a distributional regret bound as a probabilistic guarantee that holds uniformly over all…

Machine Learning · Computer Science 2026-05-08 Harin Lee , Min-hwan Oh

We study the $K$-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms. We introduce a tight asymptotic regret lower bound that is based…

Machine Learning · Statistics 2015-06-30 Junpei Komiyama , Junya Honda , Hisashi Kashima , Hiroshi Nakagawa

Optimal regret bounds for Multi-Armed Bandit problems are now well documented. They can be classified into two categories based on the growth rate with respect to the time horizon $T$: (i) small, distribution-dependent, bounds of order of…

Data Structures and Algorithms · Computer Science 2017-04-12 Arthur Flajolet , Patrick Jaillet

We study the nonstationary stochastic Multi-Armed Bandit (MAB) problem in which the distribution of rewards associated with each arm are assumed to be time-varying and the total variation in the expected rewards is subject to a variation…

Machine Learning · Computer Science 2021-01-25 Lai Wei , Vaibhav Srivastava

Motivated by wireless networks where interference or channel state estimates provide partial insight into throughput, we study a variant of the classical stochastic multi-armed bandit problem in which the learner has limited access to…

Machine Learning · Computer Science 2026-03-03 Arun Verma , Manjesh Kumar Hanawal , Arun Rajkumar

We consider a multi-hypothesis testing problem involving a K-armed bandit. Each arm's signal follows a distribution from a vector exponential family. The actual parameters of the arms are unknown to the decision maker. The decision maker…

Information Theory · Computer Science 2022-06-13 Gayathri R Prabhu , Srikrishna Bhashyam , Aditya Gopalan , Rajesh Sundaresan

Multi-armed bandit (MAB) processes constitute a foundational subclass of reinforcement learning problems and represent a central topic in statistical decision theory, but are limited to simultaneous adaptive allocation and sequential test,…

Methodology · Statistics 2026-02-27 Li Yang , Xiaodong Yan , Dandan Jiang

We consider stochastic bandit problems with $K$ arms, each associated with a bounded distribution supported on the range $[m,M]$. We do not assume that the range $[m,M]$ is known and show that there is a cost for learning this range.…

Statistics Theory · Mathematics 2022-06-16 Hédi Hadiji , Gilles Stoltz

We consider a variant of the multi-armed bandit model, which we call multi-armed bandit problem with known trend, where the gambler knows the shape of the reward function of each arm but not its distribution. This new problem is motivated…

Machine Learning · Computer Science 2017-05-15 Djallel Bouneffouf , Raphaël Feraud

We study the non-stationary stochastic multi-armed bandit problem, where the reward statistics of each arm may change several times during the course of learning. The performance of a learning algorithm is evaluated in terms of their…

Machine Learning · Computer Science 2022-03-09 Yasin Abbasi-Yadkori , Andras Gyorgy , Nevena Lazic

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…

Artificial Intelligence · Computer Science 2016-09-09 Robin Allesiardo , Raphaël Féraud , Odalric-Ambrym Maillard

We study the problem of $K$-armed dueling bandit for both stochastic and adversarial environments, where the goal of the learner is to aggregate information through relative preferences of pair of decisions points queried in an online…

Machine Learning · Computer Science 2022-02-15 Aadirupa Saha , Pierre Gaillard

In performative prediction, the deployment of a predictive model triggers a shift in the data distribution. As these shifts are typically unknown ahead of time, the learner needs to deploy a model to get feedback about the distribution it…

Machine Learning · Computer Science 2022-07-19 Meena Jagadeesan , Tijana Zrnic , Celestine Mendler-Dünner

Multi-armed bandit problems are the predominant theoretical model of exploration-exploitation tradeoffs in learning, and they have countless applications ranging from medical trials, to communication networks, to Web search and advertising.…

Data Structures and Algorithms · Computer Science 2017-09-06 Ashwinkumar Badanidiyuru , Robert Kleinberg , Aleksandrs Slivkins

We study an extension of the classic stochastic multi-armed bandit problem which involves multiple plays and Markovian rewards in the rested bandits setting. In order to tackle this problem we consider an adaptive allocation rule which at…

Statistics Theory · Mathematics 2020-07-15 Vrettos Moulos

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…

Machine Learning · Computer Science 2026-02-16 Mridul Agarwal , Vaneet Aggarwal , Christopher J. Quinn , Abhishek Umrawal

Classic contextual bandit algorithms for linear models, such as LinUCB, assume that the reward distribution for an arm is modeled by a stationary linear regression. When the linear regression model is non-stationary over time, the regret of…

Machine Learning · Statistics 2020-02-14 Qin Ding , Cho-Jui Hsieh , James Sharpnack