English
Related papers

Related papers: Restless Bandits with Average Reward: Breaking the…

200 papers

In the classic Bayesian restless multi-armed bandit (RMAB) problem, there are $N$ arms, with rewards on all arms evolving at each time as Markov chains with known parameters. A player seeks to activate $K \geq 1$ arms at each time in order…

Optimization and Control · Mathematics 2011-12-25 Wenhan Dai , Yi Gai , Bhaskar Krishnamachari , Qing Zhao

In many real-world applications, multiple agents seek to learn how to perform highly related yet slightly different tasks in an online bandit learning protocol. We formulate this problem as the $\epsilon$-multi-player multi-armed bandit…

Machine Learning · Computer Science 2021-07-21 Zhi Wang , Chicheng Zhang , Manish Kumar Singh , Laurel D. Riek , Kamalika Chaudhuri

We study pure exploration with infinitely many bandit arms generated i.i.d. from an unknown distribution. Our goal is to efficiently select a single high quality arm whose average reward is, with probability $1-\delta$, within $\varepsilon$…

Machine Learning · Computer Science 2023-06-06 Xiao-Yue Gong , Mark Sellke

For the model of constrained multi-armed bandit, we show that by construction there exists an index-based deterministic asymptotically optimal algorithm. The optimality is achieved by the convergence of the probability of choosing an…

Optimization and Control · Mathematics 2020-07-30 Hyeong Soo Chang

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…

Machine Learning · Computer Science 2020-09-04 Corinna Cortes , Giulia DeSalvo , Vitaly Kuznetsov , Mehryar Mohri , Scott Yang

We consider a restless multi-armed bandit (RMAB) in which there are two types of arms, say A and B. Each arm can be in one of two states, say $0$ or $1.$ Playing a type A arm brings it to state $0$ with probability one and not playing it…

Systems and Control · Computer Science 2017-04-11 Rahul Meshram , Aditya Gopalan , D. Manjunath

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…

Multiagent Systems · Computer Science 2023-03-01 Abheek Ghosh , Dheeraj Nagaraj , Manish Jain , Milind Tambe

We consider a multi-armed bandit problem in a setting where each arm produces a noisy reward realization which depends on an observable random covariate. As opposed to the traditional static multi-armed bandit problem, this setting allows…

Statistics Theory · Mathematics 2013-05-27 Vianney Perchet , Philippe Rigollet

In this paper, we study the multi-objective bandits (MOB) problem, where a learner repeatedly selects one arm to play and then receives a reward vector consisting of multiple objectives. MOB has found many real-world applications as varied…

Machine Learning · Computer Science 2019-05-31 Shiyin Lu , Guanghui Wang , Yao Hu , Lijun Zhang

We consider a variant of the classic multi-armed bandit problem where the expected reward of each arm is a function of an unknown parameter. The arms are divided into different groups, each of which has a common parameter. Therefore, when…

Machine Learning · Computer Science 2018-02-23 Zhiyang Wang , Ruida Zhou , Cong Shen

In this study, we consider the infinitely many-armed bandit problems in a rested rotting setting, where the mean reward of an arm may decrease with each pull, while otherwise, it remains unchanged. We explore two scenarios regarding the…

Machine Learning · Computer Science 2025-06-03 Jung-hun Kim , Milan Vojnovic , Se-Young Yun

In the classic Bayesian restless multi-armed bandit (RMAB) problem, there are $N$ arms, with rewards on all arms evolving at each time as Markov chains with known parameters. A player seeks to activate $K \geq 1$ arms at each time in order…

Optimization and Control · Mathematics 2010-11-23 Wenhan Dai , Yi Gai , Bhaskar Krishnamachari , Qing Zhao

We consider a general multi-armed bandit problem with correlated (and simple contextual and restless) elements, as a relaxed control problem. By introducing an entropy regularisation, we obtain a smooth asymptotic approximation to the value…

Optimization and Control · Mathematics 2022-09-07 Samuel N. Cohen , Tanut Treetanthiploet

This paper presents a systematic study on gap-dependent sample complexity in offline reinforcement learning. Prior work showed when the density ratio between an optimal policy and the behavior policy is upper bounded (the optimal policy…

Machine Learning · Computer Science 2022-08-05 Xinqi Wang , Qiwen Cui , Simon S. Du

In $\mathcal{X}$-armed bandit problem an agent sequentially interacts with environment which yields a reward based on the vector input the agent provides. The agent's goal is to maximise the sum of these rewards across some number of time…

Machine Learning · Statistics 2021-01-19 Valeriy Avanesov

We study a finite-horizon restless multi-armed bandit problem with multiple actions, dubbed R(MA)^2B. The state of each arm evolves according to a controlled Markov decision process (MDP), and the reward of pulling an arm depends on both…

Machine Learning · Computer Science 2022-03-25 Guojun Xiong , Jian Li , Rahul Singh

The classical multi-armed bandit (MAB) problem involves a learner and a collection of K independent arms, each with its own ex ante unknown independent reward distribution. At each one of a finite number of rounds, the learner selects one…

Optimization and Control · Mathematics 2024-05-07 Hongda Hu , Arthur Charpentier , Mario Ghossoub , Alexander Schied

Multi-armed bandit (MAB) processes constitute a foundational subclass of reinforcement learning problems and represent a central topic in statistical decision theory, but are limited to simultaneous adaptive allocation and sequential test,…

Methodology · Statistics 2026-02-27 Li Yang , Xiaodong Yan , Dandan Jiang

Contextual bandits are canonical models for sequential decision-making under uncertainty in environments with time-varying components. In this setting, the expected reward of each bandit arm consists of the inner product of an unknown…

Machine Learning · Statistics 2022-05-27 Hongju Park , Mohamad Kazem Shirani Faradonbeh

This paper considers the efficient exact computation of the counterpart of the Gittins index for a finite-horizon discrete-state bandit, which measures for each initial state the average productivity, given by the maximum ratio of expected…

Optimization and Control · Mathematics 2022-07-29 José Niño-Mora