中文
相关论文

相关论文: Dual-Mandate Patrols: Multi-Armed Bandits for Gree…

200 篇论文

Preventing poaching through ranger patrols protects endangered wildlife, directly contributing to the UN Sustainable Development Goal 15 of life on land. Combinatorial bandits have been used to allocate limited patrol resources, but…

人工智能 · 计算机科学 2022-05-12 Lily Xu , Arpita Biswas , Fei Fang , Milind Tambe

We study a novel multi-armed bandit problem that models the challenge faced by a company wishing to explore new strategies to maximize revenue whilst simultaneously maintaining their revenue above a fixed baseline, uniformly over time.…

机器学习 · 统计学 2016-02-16 Yifan Wu , Roshan Shariff , Tor Lattimore , Csaba Szepesvári

In a multi-armed bandit problem, an online algorithm chooses from a set of strategies in a sequence of trials so as to maximize the total payoff of the chosen strategies. While the performance of bandit algorithms with a small finite…

数据结构与算法 · 计算机科学 2008-09-30 Robert Kleinberg , Aleksandrs Slivkins , Eli Upfal

Canonical algorithms for multi-armed bandits typically assume a stationary reward environment where the size of the action space (number of arms) is small. More recently developed methods typically relax only one of these assumptions:…

机器学习 · 计算机科学 2025-06-02 Derek Everett , Fred Lu , Edward Raff , Fernando Camacho , James Holt

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

In a multi-armed bandit problem, an online algorithm chooses from a set of strategies in a sequence of trials so as to maximize the total payoff of the chosen strategies. While the performance of bandit algorithms with a small finite…

数据结构与算法 · 计算机科学 2019-04-16 Robert Kleinberg , Aleksandrs Slivkins , Eli Upfal

Sequential portfolio selection has attracted increasing interests in the machine learning and quantitative finance communities in recent years. As a mathematical framework for reinforcement learning policies, the stochastic multi-armed…

投资组合管理 · 定量金融 2017-09-14 Xiaoguang Huo , Feng Fu

We study the decentralized multi-player stochastic bandit problem over a continuous, Lipschitz-structured action space where hard collisions yield zero reward. Our objective is to design a communication-free policy that maximizes collective…

机器学习 · 计算机科学 2026-02-20 Sourav Chakraborty , Amit Kiran Rege , Claire Monteleoni , Lijun Chen

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

In this report, we survey Bayesian Optimization methods focussed on the Multi-Armed Bandit Problem. We take the help of the paper "Portfolio Allocation for Bayesian Optimization". We report a small literature survey on the acquisition…

机器学习 · 计算机科学 2020-12-16 Abhilash Nandy , Chandan Kumar , Deepak Mewada , Soumya Sharma

Lipschitz bandit is a variant of stochastic bandits that deals with a continuous arm set defined on a metric space, where the reward function is subject to a Lipschitz constraint. In this paper, we introduce a new problem of Lipschitz…

机器学习 · 计算机科学 2023-10-10 Yue Kang , Cho-Jui Hsieh , Thomas C. M. Lee

Multi-player multi-armed bandit is an increasingly relevant decision-making problem, motivated by applications to cognitive radio systems. Most research for this problem focuses exclusively on the settings that players have \textit{full…

机器学习 · 计算机科学 2022-12-14 Guojun Xiong , Jian Li

We unify two prominent lines of work on multi-armed bandits: bandits with knapsacks (BwK) and combinatorial semi-bandits. The former concerns limited "resources" consumed by the algorithm, e.g., limited supply in dynamic pricing. The latter…

机器学习 · 计算机科学 2018-02-22 Karthik Abinav Sankararaman , Aleksandrs Slivkins

We study for the first time, stochastic dueling bandits over continuous action spaces with Lipschitz structure, where feedback is purely comparative. While dueling bandits and Lipschitz bandits have been studied separately, their…

机器学习 · 计算机科学 2026-04-02 Mudit Sharma , Shweta Jain , Vaneet Aggarwal , Ganesh Ghalme

In this paper, we study the multi-armed bandit problem in the batched setting where the employed policy must split data into a small number of batches. While the minimax regret for the two-armed stochastic bandits has been completely…

机器学习 · 统计学 2019-10-29 Zijun Gao , Yanjun Han , Zhimei Ren , Zhengqing Zhou

Motivated by applications such as online labor markets we consider a variant of the stochastic multi-armed bandit problem where we have a collection of arms representing strategic agents with different performance characteristics. The…

计算机科学与博弈论 · 计算机科学 2025-03-11 Seyed A. Esmaeili , Suho Shin , Aleksandrs Slivkins

Communication networks shared by many users are a widespread challenge nowadays. In this paper we address several aspects of this challenge simultaneously: learning unknown stochastic network characteristics, sharing resources with other…

机器学习 · 计算机科学 2018-08-16 Orly Avner , Shie Mannor

We consider the two-armed bandit problem as applied to data processing if there are two alternative processing methods available with different a priori unknown efficiencies. One should determine the most effective method and provide its…

统计理论 · 数学 2017-04-13 Alexander V. Kolnogorov

In a typical stochastic multi-armed bandit problem, the objective is often to maximize the expected sum of rewards over some time horizon $T$. While the choice of a strategy that accomplishes that is optimal with no additional information,…

机器学习 · 计算机科学 2023-11-01 Reda Alami , Mohammed Mahfoud , Mastane Achab

Various approaches have emerged for multi-armed bandits in distributed systems. The multiplayer dueling bandit problem, common in scenarios with only preference-based information like human feedback, introduces challenges related to…

机器学习 · 计算机科学 2025-04-24 Or Raveh , Junya Honda , Masashi Sugiyama
‹ 上一页 1 2 3 10 下一页 ›