English
Related papers

Related papers: Thompson sampling: Precise arm-pull dynamics and a…

200 papers

We characterize a joint CLT of the number of pulls and the sample mean reward of the arms in a stochastic two-armed bandit environment under UCB algorithms. Several implications of this result are in place: (1) a nonstandard CLT of the…

Machine Learning · Statistics 2025-03-10 Yilun Chen , Jiaqi Lu

Existing methods of combinatorial pure exploration mainly focus on the UCB approach. To make the algorithm efficient, they usually use the sum of upper confidence bounds within arm set $S$ to represent the upper confidence bound of $S$,…

Machine Learning · Computer Science 2022-06-22 Siwei Wang , Jun Zhu

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

Stochastic linear bandits are a natural and simple generalisation of finite-armed bandits with numerous practical applications. Current approaches focus on generalising existing techniques for finite-armed bandits, notably the optimism…

Machine Learning · Statistics 2016-10-17 Tor Lattimore , Csaba Szepesvari

While experimental design often focuses on selecting the single best alternative from a finite set (e.g., in ranking and selection or best-arm identification), many pure-exploration problems pursue richer goals. Given a specific goal,…

Machine Learning · Statistics 2025-05-28 Chao Qin , Wei You

In many biomedical, science, and engineering problems, one must sequentially decide which action to take next so as to maximize rewards. One general class of algorithms for optimizing interactions with the world, while simultaneously…

Machine Learning · Statistics 2021-05-05 Iñigo Urteaga , Chris H. Wiggins

We consider the development of adaptive, instance-dependent algorithms for interactive decision making (bandits, reinforcement learning, and beyond) that, rather than only performing well in the worst case, adapt to favorable properties of…

Machine Learning · Computer Science 2023-04-26 Andrew Wagenmaker , Dylan J. Foster

We consider the multi armed bandit problem in non-stationary environments. Based on the Bayesian method, we propose a variant of Thompson Sampling which can be used in both rested and restless bandit scenarios. Applying discounting to the…

Machine Learning · Statistics 2017-08-01 Vishnu Raj , Sheetal Kalyani

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

Given a finite set of unknown distributions or arms that can be sampled, we consider the problem of identifying the one with the maximum mean using a $\delta$-correct algorithm (an adaptive, sequential algorithm that restricts the…

Machine Learning · Computer Science 2023-11-27 Shubhada Agrawal , Sandeep Juneja , Peter Glynn

We study the problem of best-arm identification with fixed confidence in stochastic linear bandits. The objective is to identify the best arm with a given level of certainty while minimizing the sampling budget. We devise a simple algorithm…

Machine Learning · Statistics 2020-06-30 Yassir Jedra , Alexandre Proutiere

This paper unifies the design and the analysis of risk-averse Thompson sampling algorithms for the multi-armed bandit problem for a class of risk functionals $\rho$ that are continuous and dominant. We prove generalised concentration bounds…

Machine Learning · Computer Science 2022-04-19 Joel Q. L. Chang , Vincent Y. F. Tan

We study the real-valued combinatorial pure exploration of the multi-armed bandit (R-CPE-MAB) problem. In R-CPE-MAB, a player is given $d$ stochastic arms, and the reward of each arm $s\in\{1, \ldots, d\}$ follows an unknown distribution…

Machine Learning · Computer Science 2023-11-16 Shintaro Nakamura , Masashi Sugiyama

Multi-arm bandit experimental designs are increasingly being adopted over standard randomized trials due to their potential to improve outcomes for study participants, enable faster identification of the best-performing options, and/or…

Methodology · Statistics 2025-06-04 Brian M Cho , Aurélien Bibaut , Nathan Kallus

Dynamic decision-making under model uncertainty is central to many economic environments, yet existing bandit and reinforcement learning algorithms rely on the assumption of correct model specification. This paper studies the behavior and…

Theoretical Economics · Economics 2026-02-20 Xinyu Dai , Daniel Chen , Yian Qian

Motion planning under differential constraints is a classic problem in robotics. To date, the state of the art is represented by sampling-based techniques, with the Rapidly-exploring Random Tree algorithm as a leading example. Yet, the…

Robotics · Computer Science 2015-03-03 Edward Schmerling , Lucas Janson , Marco Pavone

We study the problem of finding the optimal dosage in early stage clinical trials through the multi-armed bandit lens. We advocate the use of the Thompson Sampling principle, a flexible algorithm that can accommodate different types of…

Machine Learning · Statistics 2020-04-09 Maryam Aziz , Emilie Kaufmann , Marie-Karelle Riviere

Thompson sampling provides a solution to bandit problems in which new observations are allocated to arms with the posterior probability that an arm is optimal. While sometimes easy to implement and asymptotically optimal, Thompson sampling…

Machine Learning · Computer Science 2014-10-16 Dean Eckles , Maurits Kaptein

For the model of constrained multi-armed bandit, we show that by construction there exists an index-based deterministic asymptotically optimal algorithm. The optimality is achieved by the convergence of the probability of choosing an…

Optimization and Control · Mathematics 2020-07-30 Hyeong Soo Chang

We adopt an optimal-control framework for addressing the undiscounted infinite-horizon discrete-time restless $N$-armed bandit problem. Unlike most studies that rely on constructing policies based on the relaxed single-armed Markov Decision…

Optimization and Control · Mathematics 2024-03-19 Chen YAN