English
Related papers

Related papers: Batched bandit problems

200 papers

We present the first high-probability optimal regret bound for a policy optimization technique applied to the problem of stochastic contextual multi-armed bandit (CMAB) with general offline function approximation. Our algorithm is both…

Machine Learning · Computer Science 2026-02-17 Orin Levy , Yishay Mansour

We consider the problem of minimizing the regret in stochastic multi-armed bandit, when the measure of goodness of an arm is not the mean return, but some general function of the mean and the variance.We characterize the conditions under…

Machine Learning · Computer Science 2014-05-06 Alexander Zimin , Rasmus Ibsen-Jensen , Krishnendu Chatterjee

The batched multi-armed bandit (MAB) problem, in which rewards are collected in batches, is crucial for applications such as clinical trials. Existing research predominantly assumes light-tailed reward distributions, yet many real-world…

Machine Learning · Computer Science 2026-03-24 Yunwen Guo , Yunlun Shu , Gongyi Zhuo , Tianyu Wang

The Greedy algorithm is the simplest heuristic in sequential decision problem that carelessly takes the locally optimal choice at each round, disregarding any advantages of exploring and/or information gathering. Theoretically, it is known…

Machine Learning · Computer Science 2021-01-05 Matthieu Jedor , Jonathan Louëdec , Vianney Perchet

In the classical multi-armed bandit problem, d arms are available to the decision maker who pulls them sequentially in order to maximize his cumulative reward. Guarantees can be obtained on a relative quantity called regret, which scales…

Machine Learning · Computer Science 2017-06-06 Joon Kwon , Vianney Perchet , Claire Vernade

In many sequential decision-making problems, the individuals are split into several batches and the decision-maker is only allowed to change her policy at the end of batches. These batch problems have a large number of applications, ranging…

Machine Learning · Computer Science 2021-02-26 Quanquan Gu , Amin Karbasi , Khashayar Khosravi , Vahab Mirrokni , Dongruo Zhou

We consider a stochastic multi-armed bandit setting where reward must be actively queried for it to be observed. We provide tight lower and upper problem-dependent guarantees on both the regret and the number of queries. Interestingly, we…

Machine Learning · Computer Science 2022-10-28 Nadav Merlis , Yonathan Efroni , Shie Mannor

We study the stochastic multi-armed bandit problem in the case when the arm samples are dependent over time and generated from so-called weak $\cC$-mixing processes. We establish a $\cC-$Mix Improved UCB agorithm and provide both…

Machine Learning · Statistics 2019-06-26 Oleksandr Zadorozhnyi , Gilles Blanchard , Alexandra Carpentier

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 the optimal batch-regret tradeoff for batch linear contextual bandits. For any batch number $M$, number of actions $K$, time horizon $T$, and dimension $d$, we provide an algorithm and prove its regret guarantee, which, due to…

Machine Learning · Computer Science 2022-10-18 Zihan Zhang , Xiangyang Ji , Yuan Zhou

We consider a budget-constrained bandit problem where each arm pull incurs a random cost, and yields a random reward in return. The objective is to maximize the total expected reward under a budget constraint on the total cost. The model is…

Machine Learning · Computer Science 2020-03-03 Semih Cayci , Atilla Eryilmaz , R. Srikant

This paper studies the one-shot behavior of no-regret algorithms for stochastic bandits. Although many algorithms are known to be asymptotically optimal with respect to the expected regret, over a single run, their pseudo-regret seems to…

Machine Learning · Computer Science 2023-12-01 Victor Boone

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 consider the problem of sleeping bandits with stochastic action sets and adversarial rewards. In this setting, in contrast to most work in bandits, the actions may not be available at all times. For instance, some products…

Machine Learning · Computer Science 2020-08-11 Aadirupa Saha , Pierre Gaillard , Michal Valko

We introduce the factored bandits model, which is a framework for learning with limited (bandit) feedback, where actions can be decomposed into a Cartesian product of atomic actions. Factored bandits incorporate rank-1 bandits as a special…

Machine Learning · Computer Science 2018-10-30 Julian Zimmert , Yevgeny Seldin

We study the stochastic Multi-Armed Bandit (MAB) problem under worst-case regret and heavy-tailed reward distribution. We modify the minimax policy MOSS for the sub-Gaussian reward distribution by using saturated empirical mean to design a…

Machine Learning · Statistics 2020-11-19 Lai Wei , Vaibhav Srivastava

Stochastic linear bandits are a fundamental model for sequential decision making, where an agent selects a vector-valued action and receives a noisy reward with expected value given by an unknown linear function. Although well studied in…

Machine Learning · Computer Science 2025-06-23 Bruce Huang , Ruida Zhou , Lin F. Yang , Suhas Diggavi

We study an important variant of the stochastic multi-armed bandit (MAB) problem, which takes penalization into consideration. Instead of directly maximizing cumulative expected reward, we need to balance between the total reward and…

Machine Learning · Statistics 2022-11-16 Guanhua Fang , Ping Li , Gennady Samorodnitsky

We study a stochastic bandit algorithm motivated by retry-aware objectives that value the best outcome among multiple attempts, such as pass@$k$ and max@$k$. Given a posterior over arm values, ReMax chooses a sampling distribution that…

Machine Learning · Computer Science 2026-05-21 Bingkui Tong , Junpei Komiyama , Soichiro Nishimori , Paavo Parmas

Algorithms for hyperparameter optimization abound, all of which work well under different and often unverifiable assumptions. Motivated by the general challenge of sequentially choosing which algorithm to use, we study the more specific…

Machine Learning · Statistics 2016-04-12 Robert Nishihara , David Lopez-Paz , Léon Bottou