中文
相关论文

相关论文: Quick-Draw Bandits: Quickly Optimizing in Nonstati…

200 篇论文

Non-stationary multi-armed bandits enable agents to adapt to changing environments by incorporating mechanisms to detect and respond to shifts in reward distributions, making them well-suited for dynamic settings. However, existing…

机器学习 · 计算机科学 2025-09-19 Shaoang Li , Jian Li

We consider a contextual version of multi-armed bandit problem with global knapsack constraints. In each round, the outcome of pulling an arm is a scalar reward and a resource consumption vector, both dependent on the context, and the…

机器学习 · 计算机科学 2016-07-12 Shipra Agrawal , Nikhil R. Devanur , Lihong Li

We study the problem of non-stationary Lipschitz bandits, where the number of actions is infinite and the reward function, satisfying a Lipschitz assumption, can change arbitrarily over time. We design an algorithm that adaptively tracks…

机器学习 · 统计学 2025-10-23 Nicolas Nguyen , Solenne Gaucher , Claire Vernade

Stochastic Lipschitz bandit algorithms balance exploration and exploitation, and have been used for a variety of important task domains. In this paper, we present a framework for Lipschitz bandit methods that adaptively learns partitions of…

机器学习 · 统计学 2021-01-25 Tianyu Wang , Weicheng Ye , Dawei Geng , Cynthia Rudin

Multi-armed bandit algorithms have become a reference solution for handling the explore/exploit dilemma in recommender systems, and many other important real-world problems, such as display advertisement. However, such algorithms usually…

机器学习 · 计算机科学 2018-05-25 Qingyun Wu , Naveen Iyer , Hongning Wang

We study the non-stationary stochastic multi-armed bandit problem, where the reward statistics of each arm may change several times during the course of learning. The performance of a learning algorithm is evaluated in terms of their…

机器学习 · 计算机科学 2022-03-09 Yasin Abbasi-Yadkori , Andras Gyorgy , Nevena Lazic

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)…

机器学习 · 计算机科学 2025-08-28 Sourav Chakraborty , Amit Kiran Rege , Claire Monteleoni , Lijun Chen

We study the multi-armed bandit problem where the rewards are realizations of general non-stationary stochastic processes, a setting that generalizes many existing lines of work and analyses. In particular, we present a theoretical analysis…

机器学习 · 计算机科学 2020-09-04 Corinna Cortes , Giulia DeSalvo , Vitaly Kuznetsov , Mehryar Mohri , Scott Yang

Multi-armed bandit models have proven to be useful in modeling many real world problems in the areas of control and sequential decision making with partial information. However, in many scenarios, such as those prevalent in healthcare and…

最优化与控制 · 数学 2024-08-27 Qinyang He , Yonatan Mintz

Online decision-making can be formulated as the popular stochastic multi-armed bandit problem where a learner makes decisions (or takes actions) to maximize cumulative rewards collected from an unknown environment. This paper proposes to…

系统与控制 · 电气工程与系统科学 2025-11-26 Jonathan Gornet , Mehdi Hosseinzadeh , Bruno Sinopoli

Decision-making under uncertainty is a fundamental problem encountered frequently and can be formulated as a stochastic multi-armed bandit problem. In the problem, the learner interacts with an environment by choosing an action at each…

机器学习 · 统计学 2024-05-24 Jonathan Gornet , Bruno Sinopoli

We consider the stochastic bandit problem with a continuous set of arms, with the expected reward function over the arms assumed to be fixed but unknown. We provide two new Gaussian process-based algorithms for continuous bandit…

机器学习 · 计算机科学 2017-05-18 Sayak Ray Chowdhury , Aditya Gopalan

Lipschitz bandits is a prominent version of multi-armed bandits that studies large, structured action spaces such as the $[0,1]$ interval, where similar actions are guaranteed to have similar rewards. A central theme here is the adaptive…

机器学习 · 计算机科学 2025-06-13 Chara Podimata , Aleksandrs Slivkins

We consider the setting of stochastic bandit problems with a continuum of arms. We first point out that the strategies considered so far in the literature only provided theoretical guarantees of the form: given some tuning parameters, the…

统计理论 · 数学 2011-07-18 Sébastien Bubeck , Gilles Stoltz , Jia Yuan Yu

We study the recovering bandits problem, a variant of the stochastic multi-armed bandit problem where the expected reward of each arm varies according to some unknown function of the time since the arm was last played. While being a natural…

机器学习 · 统计学 2019-11-01 Ciara Pike-Burke , Steffen Grünewälder

We consider a generalization of stochastic bandits where the set of arms, $\cX$, is allowed to be a generic measurable space and the mean-payoff function is "locally Lipschitz" with respect to a dissimilarity function that is known to the…

机器学习 · 计算机科学 2011-04-15 Sébastien Bubeck , Rémi Munos , Gilles Stoltz , Csaba Szepesvari

Motivated by modern applications, such as online advertisement and recommender systems, we study the top-$k$ extreme contextual bandits problem, where the total number of arms can be enormous, and the learner is allowed to select $k$ arms…

Motivated by emerging applications such as live-streaming e-commerce, promotions and recommendations, we introduce and solve a general class of non-stationary multi-armed bandit problems that have the following two features: (i) the…

机器学习 · 统计学 2021-12-23 David Simchi-Levi , Zeyu Zheng , Feng Zhu

Most contextual bandit algorithms minimize regret against the best fixed policy, a questionable benchmark for non-stationary environments that are ubiquitous in applications. In this work, we develop several efficient contextual bandit…

机器学习 · 计算机科学 2019-04-05 Haipeng Luo , Chen-Yu Wei , Alekh Agarwal , John Langford

We consider the stochastic linear (multi-armed) contextual bandit problem with the possibility of hidden simple multi-armed bandit structure in which the rewards are independent of the contextual information. Algorithms that are designed…

机器学习 · 统计学 2020-10-07 Niladri S. Chatterji , Vidya Muthukumar , Peter L. Bartlett
‹ 上一页 1 2 3 10 下一页 ›