English
Related papers

Related papers: Perturbed-History Exploration in Stochastic Multi-…

200 papers

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…

Machine Learning · Computer Science 2024-03-19 Sourav Chakraborty , Lijun Chen

We propose feature perturbation, a simple yet effective exploration strategy for contextual bandits that injects randomness directly into feature inputs, instead of randomizing unknown parameters or adding noise to rewards. Remarkably, this…

Machine Learning · Computer Science 2025-10-27 Seouh-won Yi , Min-hwan Oh

We study incentivized exploration in multi-armed bandit (MAB) settings with infinitely many arms modeled as elements in continuous metric spaces. Unlike classical bandit models, we consider scenarios where the decision-maker (principal)…

Machine Learning · Computer Science 2025-08-28 Sourav Chakraborty , Amit Kiran Rege , Claire Monteleoni , Lijun Chen

We study how the regret guarantees of nonstochastic multi-armed bandits can be improved, if the effective range of the losses in each round is small (e.g. the maximal difference between two losses in a given round). Despite a recent…

Machine Learning · Computer Science 2020-01-03 Nicolò Cesa-Bianchi , Ohad Shamir

The objective of canonical multi-armed bandits is to identify and repeatedly select an arm with the largest reward, often in the form of the expected value of the arm's probability distribution. Such a utilitarian perspective and focus on…

Machine Learning · Statistics 2025-05-01 Meltem Tatlı , Arpan Mukherjee , Prashanth L. A. , Karthikeyan Shanmugam , Ali Tajer

Multi-armed bandit problems are the most basic examples of sequential decision problems with an exploration-exploitation trade-off. This is the balance between staying with the option that gave highest payoffs in the past and exploring new…

Machine Learning · Computer Science 2012-11-06 Sébastien Bubeck , Nicolò Cesa-Bianchi

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 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

We present a new bandit algorithm, SAO (Stochastic and Adversarial Optimal), whose regret is, essentially, optimal both for adversarial rewards and for stochastic rewards. Specifically, SAO combines the square-root worst-case regret of Exp3…

Machine Learning · Computer Science 2012-02-22 Sebastien Bubeck , Aleksandrs Slivkins

We study a multi-armed bandit problem in a dynamic environment where arm rewards evolve in a correlated fashion according to a Markov chain. Different than much of the work on related problems, in our formulation a learning algorithm does…

Machine Learning · Computer Science 2019-03-05 Tanner Fiez , Shreyas Sekar , Lillian J. Ratliff

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

Reward-biased maximum likelihood estimation (RBMLE) is a classic principle in the adaptive control literature for tackling explore-exploit trade-offs. This paper studies the stochastic contextual bandit problem with general bounded reward…

Machine Learning · Computer Science 2022-05-31 Yu-Heng Hung , Ping-Chun Hsieh

Multi-armed bandits (MAB) are commonly used in sequential online decision-making when the reward of each decision is an unknown random variable. In practice however, the typical goal of maximizing total reward may be less important than…

Machine Learning · Computer Science 2025-12-22 Ishank Juneja , Carlee Joe-Wong , Osman Yağan

We study a generalization of the multi-armed bandit problem with multiple plays where there is a cost associated with pulling each arm and the agent has a budget at each time that dictates how much she can expect to spend. We derive an…

Machine Learning · Statistics 2019-09-13 Alexander Luedtke , Emilie Kaufmann , Antoine Chambaz

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

Psychological research shows that enjoyment of many goods is subject to satiation, with short-term satisfaction declining after repeated exposures to the same item. Nevertheless, proposed algorithms for powering recommender systems seldom…

Machine Learning · Computer Science 2021-10-28 Liu Leqi , Fatma Kilinc-Karzan , Zachary C. Lipton , Alan L. Montgomery

This paper is in the field of stochastic Multi-Armed Bandits (MABs), i.e., those sequential selection techniques able to learn online using only the feedback given by the chosen option (a.k.a. arm). We study a particular case of the rested…

Machine Learning · Computer Science 2022-12-08 Alberto Maria Metelli , Francesco Trovò , Matteo Pirola , Marcello Restelli

We consider a contextual bandit problem with $S$ contexts and $K$ actions. In each round $t=1,2,\dots$, the learner observes a random context and chooses an action based on its past experience. The learner then observes a random reward…

Machine Learning · Computer Science 2023-11-29 Chung-Wei Lee , Qinghua Liu , Yasin Abbasi-Yadkori , Chi Jin , Tor Lattimore , Csaba Szepesvári

We study a variant of the stochastic $K$-armed bandit problem, which we call "bandits with delayed, aggregated anonymous feedback". In this problem, when the player pulls an arm, a reward is generated, however it is not immediately…

Machine Learning · Statistics 2018-06-14 Ciara Pike-Burke , Shipra Agrawal , Csaba Szepesvari , Steffen Grunewalder

Efficiently trading off exploration and exploitation is one of the key challenges in online Reinforcement Learning (RL). Most works achieve this by carefully estimating the model uncertainty and following the so-called optimistic model.…

Machine Learning · Computer Science 2024-09-16 Asaf Cassel , Orin Levy , Yishay Mansour