English
Related papers

Related papers: Pure Exploration with Infinite Answers

200 papers

We determine the sample complexity of pure exploration bandit problems with multiple good answers. We derive a lower bound using a new game equilibrium argument. We show how continuity and convexity properties of single-answer problems…

Machine Learning · Computer Science 2019-02-12 Rémy Degenne , Wouter M. Koolen

In pure exploration problems, a statistician sequentially collects information to answer a question about some stochastic and unknown environment. The probability of returning a wrong answer should not exceed a maximum risk parameter…

Machine Learning · Computer Science 2026-02-19 Riccardo Poiani , Martino Bernasconi , Andrea Celli

Pure exploration (aka active testing) is the fundamental task of sequentially gathering information to answer a query about a stochastic environment. Good algorithms make few mistakes and take few samples. Lower bounds (for multi-armed…

Machine Learning · Statistics 2019-06-26 Rémy Degenne , Wouter M. Koolen , Pierre Ménard

We study the sample complexity of pure exploration in an online learning problem with a feedback graph. This graph dictates the feedback available to the learner, covering scenarios between full-information, pure bandit feedback, and…

Machine Learning · Statistics 2025-03-12 Alessio Russo , Yichen Song , Aldo Pacchiano

Pure exploration in bandits formalises multiple real-world problems, such as tuning hyper-parameters or conducting user studies to test a set of items, where different safety, resource, and fairness constraints on the decision space…

Machine Learning · Computer Science 2026-02-05 Udvas Das , Debabrota Basu

In a fixed-confidence pure exploration problem in stochastic multi-armed bandits, an algorithm iteratively samples arms and should stop as early as possible and return the correct answer to a query about the arms distributions. We are…

Machine Learning · Computer Science 2025-02-04 Adrienne Tuynman , Rémy Degenne

Exploration in unknown environments is a fundamental problem in reinforcement learning and control. In this work, we study task-guided exploration and determine what precisely an agent must learn about their environment in order to complete…

Machine Learning · Computer Science 2021-07-13 Andrew Wagenmaker , Max Simchowitz , Kevin Jamieson

We introduce the model selection problem in pure exploration linear bandits, where the learner needs to adapt to the instance-dependent complexity measure of the smallest hypothesis class containing the true model. We design algorithms in…

Machine Learning · Statistics 2022-03-18 Yinglun Zhu , Julian Katz-Samuels , Robert Nowak

We study a specific \textit{combinatorial pure exploration stochastic bandit problem} where the learner aims at finding the set of arms whose means are above a given threshold, up to a given precision, and \textit{for a fixed time horizon}.…

Machine Learning · Statistics 2016-05-30 Andrea Locatelli , Maurilio Gutzeit , Alexandra Carpentier

We study the sample complexity of identifying the pure strategy Nash equilibrium (PSNE) in a two-player zero-sum matrix game with noise. Formally, we are given a stochastic model where any learner can sample an entry $(i,j)$ of the input…

Machine Learning · Computer Science 2023-11-29 Arnab Maiti , Ross Boczar , Kevin Jamieson , Lillian J. Ratliff

Bandit algorithms have garnered significant attention due to their practical applications in real-world scenarios. However, beyond simple settings such as multi-arm or linear bandits, optimal algorithms remain scarce. Notably, no optimal…

Machine Learning · Statistics 2025-02-10 Eduardo Ochoa Rivera , Ambuj Tewari

We study the greedy (exploitation-only) algorithm in bandit problems with a known reward structure. We allow arbitrary finite reward structures, while prior work focused on a few specific ones. We fully characterize when the greedy…

Machine Learning · Computer Science 2025-11-10 Aleksandrs Slivkins , Yunzong Xu , Shiliang Zuo

We study an infinite-horizon discrete-time optimal stopping problem under non-exponential discounting. A new method, which we call the iterative approach, is developed to find subgame perfect Nash equilibria. When the discount function…

Optimization and Control · Mathematics 2021-07-15 Yu-Jui Huang , Zhou Zhou

We consider a discounted infinite horizon optimal stopping problem. If the underlying distribution is known a priori, the solution of this problem is obtained via dynamic programming (DP) and is given by a well known threshold rule. When…

Machine Learning · Computer Science 2021-02-23 Daniel Russo , Assaf Zeevi , Tianyi Zhang

We consider the problem of pure exploration with subset-wise preference feedback, which contains $N$ arms with features. The learner is allowed to query subsets of size $K$ and receives feedback in the form of a noisy winner. The goal of…

Machine Learning · Computer Science 2021-04-13 Shubham Gupta , Aadirupa Saha , Sumeet Katariya

We investigate an active pure-exploration setting, that includes best-arm identification, in the context of linear stochastic bandits. While asymptotically optimal algorithms exist for standard multi-arm bandits, the existence of such…

Machine Learning · Statistics 2020-07-03 Rémy Degenne , Pierre Ménard , Xuedong Shang , Michal Valko

We study the problem of exploration in Reinforcement Learning and present a novel model-free solution. We adopt an information-theoretical viewpoint and start from the instance-specific lower bound of the number of samples that have to be…

Machine Learning · Computer Science 2024-07-02 Alessio Russo , Alexandre Proutiere

We address the problem of identifying the optimal policy with a fixed confidence level in a multi-armed bandit setup, when \emph{the arms are subject to linear constraints}. Unlike the standard best-arm identification problem which is well…

Machine Learning · Computer Science 2024-01-26 Emil Carlsson , Debabrota Basu , Fredrik D. Johansson , Devdatt Dubhashi

This paper explores continuous-time and state-space optimal stopping problems from a reinforcement learning perspective. We begin by formulating the stopping problem using randomized stopping times, where the decision maker's control is…

Optimization and Control · Mathematics 2026-03-12 Jodi Dianetti , Giorgio Ferrari , Renyuan Xu

Standard Markovian optimal stopping problems are consistent in the sense that the first entrance time into the stopping set is optimal for each initial state of the process. Clearly, the usual concept of optimality cannot in a…

Optimization and Control · Mathematics 2018-12-05 Sören Christensen , Kristoffer Lindensjö
‹ Prev 1 2 3 10 Next ›