English
Related papers

Related papers: Faster Q-Learning Algorithms for Restless Bandits

200 papers

We present a two-armed bandit model of decision making under uncertainty where the expected return to investing in the "risky arm" increases when choosing that arm and decreases when choosing the "safe" arm. These dynamics are natural in…

Optimization and Control · Mathematics 2017-03-22 Roland Fryer , Philipp Harms

We study the asymptotic optimal control of multi-class restless bandits. A restless bandit is a controllable stochastic process whose state evolution depends on whether or not the bandit is made active. Since finding the optimal control is…

Probability · Mathematics 2016-09-05 I. M. Verloop

Restless multi-arm bandits (RMABs), a class of resource allocation problems with broad application in areas such as healthcare, online advertising, and anti-poaching, have recently been studied from a multi-agent reinforcement learning…

Machine Learning · Computer Science 2024-01-31 Yunfan Zhao , Nikhil Behari , Edward Hughes , Edwin Zhang , Dheeraj Nagaraj , Karl Tuyls , Aparna Taneja , Milind Tambe

A general framework of personalized federated multi-armed bandits (PF-MAB) is proposed, which is a new bandit paradigm analogous to the federated learning (FL) framework in supervised learning and enjoys the features of FL with…

Machine Learning · Computer Science 2021-02-26 Chengshuai Shi , Cong Shen , Jing Yang

Fast changing states or volatile environments pose a significant challenge to online optimization, which needs to perform rapid adaptation under limited observation. In this paper, we give query and regret optimal bandit algorithms under…

Machine Learning · Computer Science 2024-01-18 Zhou Lu , Qiuyi Zhang , Xinyi Chen , Fred Zhang , David Woodruff , Elad Hazan

The contextual multi-armed bandit (MAB) problem is crucial in sequential decision-making. A line of research, known as online clustering of bandits, extends contextual MAB by grouping similar users into clusters, utilizing shared features…

Machine Learning · Computer Science 2025-01-03 Zhuohua Li , Maoli Liu , Xiangxiang Dai , John C. S. Lui

Reinforcement Learning (RL) has achieved tremendous success in recent years. However, the classical foundations of RL do not account for the risk sensitivity of the objective function, which is critical in various fields, including…

Machine Learning · Computer Science 2025-11-14 Mohammad Alipour-Vaezi , Huaiyang Zhong , Kwok-Leung Tsui , Sajad Khodadadian

The paper proposes a novel upper confidence bound (UCB) procedure for identifying the arm with the largest mean in a multi-armed bandit game in the fixed confidence setting using a small number of total samples. The procedure cannot be…

Machine Learning · Statistics 2013-12-30 Kevin Jamieson , Matthew Malloy , Robert Nowak , Sébastien Bubeck

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…

Machine Learning · Computer Science 2026-01-01 Konstantin Avrachenkov , Vivek S. Borkar , Pratik Shah

We provide a simple method to combine stochastic bandit algorithms. Our approach is based on a "meta-UCB" procedure that treats each of $N$ individual bandit algorithms as arms in a higher-level $N$-armed bandit problem that we solve with a…

Machine Learning · Computer Science 2020-12-25 Ashok Cutkosky , Abhimanyu Das , Manish Purohit

We consider the problem of controlling an unknown stochastic linear system with quadratic costs - called the adaptive LQ control problem. We re-examine an approach called ''Reward Biased Maximum Likelihood Estimate'' (RBMLE) that was…

Optimization and Control · Mathematics 2023-03-27 Akshay Mete , Rahul Singh , P. R. Kumar

We show how an ensemble of $Q^*$-functions can be leveraged for more effective exploration in deep reinforcement learning. We build on well established algorithms from the bandit setting, and adapt them to the $Q$-learning setting. We…

Machine Learning · Computer Science 2017-11-09 Richard Y. Chen , Szymon Sidor , Pieter Abbeel , John Schulman

Public health practitioners often have the goal of monitoring patients and maximizing patients' time spent in "favorable" or healthy states while being constrained to using limited resources. Restless multi-armed bandits (RMAB) are an…

Machine Learning · Computer Science 2024-12-12 Gauri Jain , Pradeep Varakantham , Haifeng Xu , Aparna Taneja , Prashant Doshi , Milind Tambe

We present a novel machine learning framework for the optimal control of fluid restless multi-armed bandit problems (FRMABPs) with state equations that are either affine or quadratic in the state variables. By establishing fundamental…

Machine Learning · Computer Science 2026-05-08 Dimitris Bertsimas , Cheol Woo Kim , José Niño-Mora

We study adversarial attacks that manipulate the reward signals to control the actions chosen by a stochastic multi-armed bandit algorithm. We propose the first attack against two popular bandit algorithms: $\epsilon$-greedy and UCB,…

Machine Learning · Computer Science 2018-10-30 Kwang-Sung Jun , Lihong Li , Yuzhe Ma , Xiaojin Zhu

We consider restless multi-armed bandit (RMAB) with a finite horizon and multiple pulls per period. Leveraging the Lagrangian relaxation, we approximate the problem with a collection of single arm problems. We then propose an index-based…

Optimization and Control · Mathematics 2017-07-04 Weici Hu , Peter Frazier

Most algorithms for the multi-armed bandit problem in reinforcement learning aimed to maximize the expected reward, which are thus useful in searching the optimized candidate with the highest reward (function value) for diverse applications…

Machine Learning · Computer Science 2022-01-03 Bin Chong , Yingguang Yang , Zi-Le Wang , Hang Xing , Zhirong Liu

We consider the problem of finitely parameterized multi-armed bandits where the model of the underlying stochastic environment can be characterized based on a common unknown parameter. The true parameter is unknown to the learning agent.…

Machine Learning · Computer Science 2020-11-10 Kishan Panaganti , Dileep Kalathil

Bandit algorithms have various application in safety-critical systems, where it is important to respect the system constraints that rely on the bandit's unknown parameters at every round. In this paper, we formulate a linear stochastic…

Machine Learning · Computer Science 2019-08-19 Sanae Amani , Mahnoosh Alizadeh , Christos Thrampoulidis

Existing risk-aware multi-armed bandit models typically focus on risk measures of individual options such as variance. As a result, they cannot be directly applied to important real-world online decision making problems with correlated…

Machine Learning · Computer Science 2023-05-12 Yihan Du , Siwei Wang , Zhixuan Fang , Longbo Huang