English
Related papers

Related papers: Thompson Sampling for (Combinatorial) Pure Explora…

200 papers

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

I study adversarial attacks against stochastic bandit algorithms. At each round, the learner chooses an arm, and a stochastic reward is generated. The adversary strategically adds corruption to the reward, and the learner is only able to…

Machine Learning · Computer Science 2024-03-18 Shiliang Zuo

We consider stochastic multi-armed bandit problems with complex actions over a set of basic arms, where the decision maker plays a complex action rather than a basic arm in each round. The reward of the complex action is some function of…

Machine Learning · Statistics 2013-11-05 Aditya Gopalan , Shie Mannor , Yishay Mansour

We study Thompson sampling (TS) in online decision making, where the uncertain environment is sampled from a mixture distribution. This is relevant in multi-task learning, where a learning agent faces different classes of problems. We…

Machine Learning · Computer Science 2022-03-08 Joey Hong , Branislav Kveton , Manzil Zaheer , Mohammad Ghavamzadeh , Craig Boutilier

We investigate experiments that are designed to select a treatment arm for population deployment. Multi-armed bandit algorithms can enhance efficiency by dynamically allocating measurement effort towards higher performing arms based on…

Machine Learning · Computer Science 2023-08-29 Chao Qin , Daniel Russo

Safe exploration remains a fundamental challenge in reinforcement learning (RL), limiting the deployment of RL agents in the real world. We propose Sampling-Based Safe Reinforcement Learning (SBSRL), a model-based RL algorithm that…

Machine Learning · Computer Science 2026-05-20 Luca Vignola , Bruce D. Lee , Manish Prajapat , Manuel Wendl , Melanie Zeilinger , Andreas Krause , Yarden As

A key challenge to deploying reinforcement learning in practice is avoiding excessive (harmful) exploration in individual episodes. We propose a natural constraint on exploration -- \textit{uniformly} outperforming a conservative policy…

Machine Learning · Computer Science 2023-02-27 Wanqiao Xu , Jason Yecheng Ma , Kan Xu , Hamsa Bastani , Osbert Bastani

Thompson Sampling has been demonstrated in many complex bandit models, however the theoretical guarantees available for the parametric multi-armed bandit are still limited to the Bernoulli case. Here we extend them by proving asymptotic…

Machine Learning · Statistics 2013-07-15 Nathaniel Korda , Emilie Kaufmann , Remi Munos

In this paper, we consider the low rank structure of the reward sequence of the pure exploration problems. Firstly, we propose the separated setting in pure exploration problem, where the exploration strategy cannot receive the feedback of…

Machine Learning · Computer Science 2023-06-29 Yaxiong Liu , Atsuyoshi Nakamura , Kohei Hatano , Eiji Takimoto

The pure-exploration problem in stochastic multi-armed bandits aims to find one or more arms with the largest (or near largest) means. Examples include finding an {\epsilon}-good arm, best-arm identification, top-k arm identification, and…

Machine Learning · Statistics 2020-09-14 Blake Mason , Lalit Jain , Ardhendu Tripathy , Robert Nowak

In this paper, we discuss the asymptotic behavior of the Upper Confidence Bound (UCB) algorithm in the context of multiarmed bandit problems and discuss its implication in downstream inferential tasks. While inferential tasks become…

Machine Learning · Statistics 2024-08-09 Koulik Khamaru , Cun-Hui Zhang

Thompson Sampling is a well established approach to bandit and reinforcement learning problems. However its use in continuum armed bandit problems has received relatively little attention. We provide the first bounds on the regret of…

Machine Learning · Computer Science 2020-02-27 James A. Grant , David S. Leslie

We consider online sequential decision problems where an agent must balance exploration and exploitation. We derive a set of Bayesian `optimistic' policies which, in the stochastic multi-armed bandit case, includes the Thompson sampling…

Machine Learning · Statistics 2021-11-01 Brendan O'Donoghue , Tor Lattimore

We study, to the best of our knowledge, the first Bayesian algorithm for unimodal Multi-Armed Bandit (MAB) problems with graph structure. In this setting, each arm corresponds to a node of a graph and each edge provides a relationship,…

Machine Learning · Computer Science 2016-11-23 Stefano Paladino , Francesco Trovò , Marcello Restelli , Nicola Gatti

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

When two players are engaged in a repeated game with unknown payoff matrices, they may use single-agent multi-armed bandit algorithms to choose the actions independent of each other. We show that when the players use Thompson sampling, the…

Computer Science and Game Theory · Computer Science 2025-09-30 Yi Xiong , Ningyuan Chen , Xuefeng Gao

Thompson Sampling, one of the oldest heuristics for solving multi-armed bandits, has recently been shown to demonstrate state-of-the-art performance. The empirical success has led to great interests in theoretical understanding of this…

Machine Learning · Computer Science 2013-10-29 Lihong Li

The regret lower bound of Lai and Robbins (1985), the gold standard for checking optimality of bandit algorithms, considers arm size fixed as sample size goes to infinity. We show that when arm size increases polynomially with sample size,…

Statistics Theory · Mathematics 2019-09-06 Hock Peng Chan , Shouri Hu

We design and analyse variations of the classical Thompson sampling (TS) procedure for Bayesian optimisation (BO) in settings where function evaluations are expensive, but can be performed in parallel. Our theoretical analysis shows that a…

Machine Learning · Statistics 2017-05-26 Kirthevasan Kandasamy , Akshay Krishnamurthy , Jeff Schneider , Barnabas Poczos

This paper introduces a general multi-agent bandit model in which each agent is facing a finite set of arms and may communicate with other agents through a central controller in order to identify, in pure exploration, or play, in regret…

Machine Learning · Computer Science 2022-10-31 Clémence Réda , Sattar Vakili , Emilie Kaufmann