中文
相关论文

相关论文: Restless Bandits with Many Arms: Beating the Centr…

200 篇论文

Restless multi-armed bandits (RMABs) extend multi-armed bandits to allow for stateful arms, where the state of each arm evolves restlessly with different transitions depending on whether that arm is pulled. Solving RMABs requires…

机器学习 · 计算机科学 2023-11-21 Kai Wang , Lily Xu , Aparna Taneja , Milind Tambe

The Whittle index, which characterizes optimal policies for controlling certain single restless bandit projects (a Markov decision process with two actions: active and passive) is the basis for a widely used heuristic index policy for the…

最优化与控制 · 数学 2021-05-06 José Niño-Mora

We develop asymptotically optimal policies for the multi armed bandit (MAB), problem, under a cost constraint. This model is applicable in situations where each sample (or activation) from a population (bandit) incurs a known bandit…

机器学习 · 统计学 2015-12-18 Apostolos N. Burnetas , Odysseas Kanavetas , Michael N. Katehakis

We provide a framework to analyse control policies for the restless Markovian bandit model, under both finite and infinite time horizon. We show that when the population of arms goes to infinity, the value of the optimal control policy…

最优化与控制 · 数学 2023-12-25 Nicolas Gast , Bruno Gaujal , Chen Yan

In the classic multi-armed bandits problem, the goal is to have a policy for dynamically operating arms that each yield stochastic rewards with unknown means. The key metric of interest is regret, defined as the gap between the expected…

最优化与控制 · 数学 2010-11-23 Yi Gai , Bhaskar Krishnamachari , Rahul Jain

This paper considers the multi-armed bandit problem with multiple simultaneous arm pulls. We develop a new `irrevocable' heuristic for this problem. In particular, we do not allow recourse to arms that were pulled at some point in the past…

最优化与控制 · 数学 2008-06-26 Vivek Farias , Ritesh Madan

We study a resource allocation problem with varying requests, and with resources of limited capacity shared by multiple requests. It is modeled as a set of heterogeneous Restless Multi-Armed Bandit Problems (RMABPs) connected by constraints…

最优化与控制 · 数学 2020-03-30 Jing Fu , Bill Moran , Peter G. Taylor

We study the problem of planning restless multi-armed bandits (RMABs) with multiple actions. This is a popular model for multi-agent systems with applications like multi-channel communication, monitoring and machine maintenance tasks, and…

多智能体系统 · 计算机科学 2023-03-01 Abheek Ghosh , Dheeraj Nagaraj , Manish Jain , Milind Tambe

We consider a general infinite horizon Heterogeneous Restless multi-armed Bandit (RMAB). Heterogeneity is a fundamental problem for many real-world systems largely because it resists many concentration arguments. In this paper, we assume…

最优化与控制 · 数学 2025-11-12 Dheeraj Narasimha , Nicolas Gast

We consider the problem of maximizing the expected average reward obtained over an infinite time horizon by $n$ weakly coupled Markov decision processes. Our setup is a substantial generalization of the multi-armed restless bandit problem…

最优化与控制 · 数学 2026-04-01 Diego Goldsztajn , Konstantin Avrachenkov

We study a sequential resource allocation problem between a fixed number of arms. On each iteration the algorithm distributes a resource among the arms in order to maximize the expected success rate. Allocating more of the resource to a…

机器学习 · 计算机科学 2018-03-29 Yuval Dagan , Koby Crammer

We study stochastic linear optimization problem with bandit feedback. The set of arms take values in an $N$-dimensional space and belong to a bounded polyhedron described by finitely many linear inequalities. We provide a lower bound for…

机器学习 · 计算机科学 2015-09-29 Manjesh K. Hanawal , Amir Leshem , Venkatesh Saligrama

The trade-off between the cost of acquiring and processing data, and uncertainty due to a lack of data is fundamental in machine learning. A basic instance of this trade-off is the problem of deciding when to make noisy and costly…

机器学习 · 统计学 2017-03-30 Christopher R. Dance , Tomi Silander

We study the Lagrangian Index Policy (LIP) for restless multi-armed bandits with long-run average reward. In particular, we compare the performance of LIP with the performance of the Whittle Index Policy (WIP), both heuristic policies known…

机器学习 · 计算机科学 2026-01-01 Konstantin Avrachenkov , Vivek S. Borkar , Pratik Shah

We consider the problem of learning the optimal threshold policy for control problems. Threshold policies make control decisions by evaluating whether an element of the system state exceeds a certain threshold, whose value is determined by…

机器学习 · 计算机科学 2022-09-30 Khaled Nakhleh , I-Hong Hou

The Whittle index, which characterizes optimal policies for controlling certain single restless bandit projects (a Markov decision process with two actions: active and passive) is the basis for a widely used heuristic index policy for the…

最优化与控制 · 数学 2021-05-05 José Niño-Mora

We study a generalization of the multi-armed bandit problem with multiple plays where there is a cost associated with pulling each arm and the agent has a budget at each time that dictates how much she can expect to spend. We derive an…

机器学习 · 统计学 2019-09-13 Alexander Luedtke , Emilie Kaufmann , Antoine Chambaz

The Whittle index for restless bandits (two-action semi-Markov decision processes) provides an intuitively appealing optimal policy for controlling a single generic project that can be active (engaged) or passive (rested) at each decision…

最优化与控制 · 数学 2026-01-22 José Niño-Mora

We consider a stochastic bandit problem with a possibly infinite number of arms. We write $p^*$ for the proportion of optimal arms and $\Delta$ for the minimal mean-gap between optimal and sub-optimal arms. We characterize the optimal…

机器学习 · 计算机科学 2021-11-08 Rianne de Heide , James Cheshire , Pierre Ménard , Alexandra Carpentier

This paper studies a class of constrained restless multi-armed bandits (CRMAB). The constraints are in the form of time varying set of actions (set of available arms). This variation can be either stochastic or semi-deterministic. Given a…

系统与控制 · 计算机科学 2021-09-07 Kesav Kaza , Rahul Meshram , Varun Mehta , S. N. Merchant