English
Related papers

Related papers: The Ratio Index for Budgeted Learning, with Applic…

200 papers

The Multi-Armed Bandit problem provides a fundamental framework for analyzing the tension between exploration and exploitation in sequential learning. This paper explores Information Directed Sampling (IDS) policies, a class of heuristics…

Machine Learning · Computer Science 2025-12-24 Annika Hirling , Giorgio Nicoletti , Antonio Celani

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 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…

Machine Learning · Statistics 2017-03-30 Christopher R. Dance , Tomi Silander

We consider finite-horizon restless bandits with multiple pulls per period, which play an important role in recommender systems, active learning, revenue management, and many other areas. While an optimal policy can be computed, in…

Optimization and Control · Mathematics 2021-07-27 Xiangyu Zhang , Peter I. Frazier

Best-arm identification (BAI) in a fixed-budget setting is a bandit problem where the learning agent maximizes the probability of identifying the optimal (best) arm after a fixed number of observations. Most works on this topic study…

Machine Learning · Computer Science 2023-07-06 Mohammad Javad Azizi , Branislav Kveton , Mohammad Ghavamzadeh

We consider a resource-aware variant of the classical multi-armed bandit problem: In each round, the learner selects an arm and determines a resource limit. It then observes a corresponding (random) reward, provided the (random) amount of…

Machine Learning · Computer Science 2022-10-18 Viktor Bengs , Eyke Hüllermeier

Adaptive designs for multi-armed clinical trials have become increasingly popular recently in many areas of medical research because of their potential to shorten development times and to increase patient response. However, developing…

Applications · Statistics 2017-03-16 Adam Smith , Sofia S. Villar

Most bandit policies are designed to either minimize regret in any problem instance, making very few assumptions about the underlying environment, or in a Bayesian sense, assuming a prior distribution over environment parameters. The former…

Machine Learning · Computer Science 2021-01-07 Branislav Kveton , Martin Mladenov , Chih-Wei Hsu , Manzil Zaheer , Csaba Szepesvari , Craig Boutilier

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…

Machine Learning · Computer Science 2018-03-29 Yuval Dagan , Koby Crammer

Restless multi-armed bandits (RMABs) provide a scalable framework for sequential decision-making under uncertainty, but classical formulations assume binary actions and a single global budget. Real-world settings, such as healthcare, often…

Machine Learning · Computer Science 2025-10-28 Himadri S. Pandey , Kai Wang , Gian-Gabriel P. Garcia

We consider a policy gradient algorithm applied to a finite-arm bandit problem with Bernoulli rewards. We allow learning rates to depend on the current state of the algorithm, rather than use a deterministic time-decreasing learning rate.…

Machine Learning · Computer Science 2021-09-24 Denis Denisov , Neil Walton

We consider a class of restless multi-armed bandit problems (RMBP) that arises in dynamic multichannel access, user/server scheduling, and optimal activation in multi-agent systems. For this class of RMBP, we establish the indexability and…

Information Theory · Computer Science 2008-11-13 Keqin Liu , Qing Zhao

In the classical multi-armed bandit problem, instance-dependent algorithms attain improved performance on "easy" problems with a gap between the best and second-best arm. Are similar guarantees possible for contextual bandits? While…

Machine Learning · Computer Science 2020-10-08 Dylan J. Foster , Alexander Rakhlin , David Simchi-Levi , Yunzong Xu

Modern systems, such as digital platforms and service systems, increasingly rely on contextual bandits for online decision-making; however, their deployment can inadvertently create unfair exposure among arms, undermining long-term platform…

Machine Learning · Statistics 2026-02-05 Qingwen Zhang , Wenjia Wang

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…

Machine Learning · Computer Science 2021-11-08 Rianne de Heide , James Cheshire , Pierre Ménard , Alexandra Carpentier

A novel reinforcement learning algorithm is introduced for multiarmed restless bandits with average reward, using the paradigms of Q-learning and Whittle index. Specifically, we leverage the structure of the Whittle index policy to reduce…

Machine Learning · Computer Science 2021-09-22 Konstantin E. Avrachenkov , Vivek S. Borkar

In real-world machine learning applications, there is a cost associated with sampling of different features. Budgeted learning can be used to select which feature-values to acquire from each instance in a dataset, such that the best model…

Machine Learning · Computer Science 2019-03-14 Eran Fainman , Bracha Shapira , Lior Rokach , Yisroel Mirsky

We study the problem of learning 'good' interventions in a stochastic environment modeled by its underlying causal graph. Good interventions refer to interventions that maximize rewards. Specifically, we consider the setting of a…

Machine Learning · Computer Science 2024-01-17 Fateme Jamshidi , Jalal Etesami , Negar Kiyavash

This paper proposes near-optimal algorithms for the pure-exploration linear bandit problem in the fixed confidence and fixed budget settings. Leveraging ideas from the theory of suprema of empirical processes, we provide an algorithm whose…

Machine Learning · Computer Science 2020-06-23 Julian Katz-Samuels , Lalit Jain , Zohar Karnin , Kevin Jamieson

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