English
Related papers

Related papers: Optimal Exploration is no harder than Thompson Sam…

200 papers

This paper studies the fixed-confidence best arm identification (BAI) problem in the bandit framework in the canonical single-parameter exponential models. For this problem, many policies have been proposed, but most of them require solving…

Machine Learning · Statistics 2025-08-12 Jongyeong Lee , Junya Honda , Masashi Sugiyama

Thompson sampling (TS) is one of the most popular exploration techniques in reinforcement learning (RL). However, most TS algorithms with theoretical guarantees are difficult to implement and not generalizable to Deep RL. While the emerging…

Machine Learning · Computer Science 2024-06-19 Haque Ishfaq , Yixin Tan , Yu Yang , Qingfeng Lan , Jianfeng Lu , A. Rupam Mahmood , Doina Precup , Pan Xu

This paper introduces the framework of multi-armed sampling, which serves as the sampling counterpart to the optimization problem of multi-armed bandits. Our primary motivation is to rigorously examine the exploration-exploitation trade-off…

Machine Learning · Computer Science 2026-05-14 Mohammad Pedramfar , Siamak Ravanbakhsh

This paper considers the use of a simple posterior sampling algorithm to balance between exploration and exploitation when learning to optimize actions such as in multi-armed bandit problems. The algorithm, also known as Thompson Sampling,…

Machine Learning · Computer Science 2014-02-04 Daniel Russo , Benjamin Van Roy

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

The literature on bandit learning and regret analysis has focused on contexts where the goal is to converge on an optimal action in a manner that limits exploration costs. One shortcoming imposed by this orientation is that it does not…

Machine Learning · Computer Science 2017-05-01 Daniel Russo , David Tse , Benjamin Van Roy

We study the combinatorial pure exploration problem Best-Set in stochastic multi-armed bandits. In a Best-Set instance, we are given $n$ arms with unknown reward distributions, as well as a family $\mathcal{F}$ of feasible subsets over the…

Machine Learning · Computer Science 2017-06-06 Lijie Chen , Anupam Gupta , Jian Li , Mingda Qiao , Ruosong Wang

We propose a new strategy for best-arm identification with fixed confidence of Gaussian variables with bounded means and unit variance. This strategy, called Exploration-Biased Sampling, is not only asymptotically optimal: it is to the best…

Statistics Theory · Mathematics 2022-03-08 Antoine Barrier , Aurélien Garivier , Tomáš Kocák

In linear contextual bandits, the objective is to select actions that maximize cumulative rewards, modeled as a linear function with unknown parameters. Although Thompson Sampling performs well empirically, it does not achieve optimal…

Machine Learning · Statistics 2025-06-18 Wonyoung Kim

Thompson sampling is an efficient algorithm for sequential decision making, which exploits the posterior uncertainty to address the exploration-exploitation dilemma. There has been significant recent interest in integrating Bayesian neural…

Machine Learning · Statistics 2020-08-07 Zhendong Wang , Mingyuan Zhou

We study pure exploration with infinitely many bandit arms generated i.i.d. from an unknown distribution. Our goal is to efficiently select a single high quality arm whose average reward is, with probability $1-\delta$, within $\varepsilon$…

Machine Learning · Computer Science 2023-06-06 Xiao-Yue Gong , Mark Sellke

Thompson sampling for multi-armed bandit problems is known to enjoy favorable performance in both theory and practice. However, it suffers from a significant limitation computationally, arising from the need for samples from posterior…

Machine Learning · Computer Science 2020-06-19 Eric Mazumdar , Aldo Pacchiano , Yi-an Ma , Peter L. Bartlett , Michael I. Jordan

We study the regret of Thompson sampling (TS) algorithms for exponential family bandits, where the reward distribution is from a one-dimensional exponential family, which covers many common reward distributions including Bernoulli,…

Machine Learning · Statistics 2022-06-09 Tianyuan Jin , Pan Xu , Xiaokui Xiao , Anima Anandkumar

Thompson Sampling is one of the oldest heuristics for multi-armed bandit problems. It is a randomized algorithm based on Bayesian ideas, and has recently generated significant interest after several studies demonstrated it to have better…

Machine Learning · Computer Science 2014-02-04 Shipra Agrawal , Navin Goyal

Using bandit algorithms to conduct adaptive randomised experiments can minimise regret, but it poses major challenges for statistical inference (e.g., biased estimators, inflated type-I error and reduced power). Recent attempts to address…

Machine Learning · Statistics 2021-11-02 Nina Deliu , Joseph J. Williams , Sofia S. Villar

We consider a finite-horizon multi-armed bandit (MAB) problem in a Bayesian setting, for which we propose an information relaxation sampling framework. With this framework, we define an intuitive family of control policies that include…

Machine Learning · Computer Science 2021-06-17 Seungki Min , Costis Maglaras , Ciamac C. Moallemi

The question of the optimality of Thompson Sampling for solving the stochastic multi-armed bandit problem had been open since 1933. In this paper we answer it positively for the case of Bernoulli rewards by providing the first finite-time…

Machine Learning · Statistics 2012-07-20 Emilie Kaufmann , Nathaniel Korda , Rémi Munos

We consider the Multi-Armed Bandit (MAB) problem, where an agent sequentially chooses actions and observes rewards for the actions it took. While the majority of algorithms try to minimize the regret, i.e., the cumulative difference between…

Machine Learning · Computer Science 2021-09-14 Nadav Merlis , Shie Mannor

Thompson Sampling is one of the most effective methods for contextual bandits and has been generalized to posterior sampling for certain MDP settings. However, existing posterior sampling methods for reinforcement learning are limited by…

Machine Learning · Computer Science 2022-08-24 Christoph Dann , Mehryar Mohri , Tong Zhang , Julian Zimmert

We study a novel pure exploration problem: the $\epsilon$-Thresholding Bandit Problem (TBP) with fixed confidence in stochastic linear bandits. We prove a lower bound for the sample complexity and extend an algorithm designed for Best Arm…

Machine Learning · Statistics 2024-02-16 Eduardo Ochoa Rivera , Ambuj Tewari