English
Related papers

Related papers: An Asymptotically Optimal Policy for Finite Suppor…

200 papers

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

We study the best-arm identification problem in multi-armed bandits with stochastic, potentially private rewards, when the goal is to identify the arm with the highest quantile at a fixed, prescribed level. First, we propose a (non-private)…

Machine Learning · Statistics 2022-12-06 Kontantinos E. Nikolakakis , Dionysios S. Kalogerias , Or Sheffet , Anand D. Sarwate

Partial monitoring is a general model for sequential learning with limited feedback formalized as a game between two players. In this game, the learner chooses an action and at the same time the opponent chooses an outcome, then the learner…

Machine Learning · Statistics 2015-10-01 Junpei Komiyama , Junya Honda , Hiroshi Nakagawa

The Greedy algorithm is the simplest heuristic in sequential decision problem that carelessly takes the locally optimal choice at each round, disregarding any advantages of exploring and/or information gathering. Theoretically, it is known…

Machine Learning · Computer Science 2021-01-05 Matthieu Jedor , Jonathan Louëdec , Vianney Perchet

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

In light of the COVID-19 pandemic, it is an open challenge and critical practical problem to find a optimal way to dynamically prescribe the best policies that balance both the governmental resources and epidemic control in different…

Machine Learning · Computer Science 2022-04-28 Baihan Lin , Djallel Bouneffouf

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.…

Machine Learning · Statistics 2016-02-16 Yifan Wu , Roshan Shariff , Tor Lattimore , Csaba Szepesvári

We consider the discrete time infinite horizon average reward restless markovian bandit (RMAB) problem. We propose a \emph{model predictive control} based non-stationary policy with a rolling computational horizon $\tau$. At each time-slot,…

Optimization and Control · Mathematics 2025-06-06 Nicolas Gast , Dheeraj Narasimha

We address the problem of best arm identification (BAI) with a fixed budget for two-armed Gaussian bandits. In BAI, given multiple arms, we aim to find the best arm, an arm with the highest expected reward, through an adaptive experiment.…

Machine Learning · Computer Science 2024-03-19 Masahiro Kato

We consider the stochastic contextual bandit problem with additional regularization. The motivation comes from problems where the policy of the agent must be close to some baseline policy which is known to perform well on the task. To…

Machine Learning · Statistics 2019-06-06 Xavier Fontaine , Quentin Berthet , Vianney Perchet

We develop a frequentist decision-theoretic framework for selecting the best arm in one-shot, multi-arm randomized controlled trials (RCTs). Our approach characterizes the minimax-regret (MMR) optimal decision rule for any multivariate…

Econometrics · Economics 2025-10-21 Joonhwi Joo

We seek to take a different approach in deriving the optimal search policy for the repeated consumer search model found in Fishman and Rob (1995) with the main motivation of dropping the assumption of prior knowledge of the price…

Theoretical Economics · Economics 2020-12-24 Tung Yu Marco Chan

Multi-dueling bandits, where a learner selects $m \geq 2$ arms per round and observes only the winner, arise naturally in many applications including ranking and recommendation systems, yet a fundamental question has remained open: can a…

Machine Learning · Computer Science 2026-05-19 S Akash , Pratik Gajane , Jawar Singh

We study the asymptotic performance of the Thompson sampling algorithm in the batched multi-armed bandit setting where the time horizon $T$ is divided into batches, and the agent is not able to observe the rewards of her actions until the…

Machine Learning · Computer Science 2021-10-04 Cem Kalkanli , Ayfer Ozgur

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…

Data Structures and Algorithms · Computer Science 2008-09-30 Robert Kleinberg , Aleksandrs Slivkins , Eli Upfal

We study the off-policy evaluation problem---estimating the value of a target policy using data collected by another policy---under the contextual bandit model. We consider the general (agnostic) setting without access to a consistent model…

Machine Learning · Statistics 2017-11-15 Yu-Xiang Wang , Alekh Agarwal , Miroslav Dudik

We study the Improving Multi-Armed Bandit (IMAB) problem, where the reward obtained from an arm increases with the number of pulls it receives. This model provides an elegant abstraction for many real-world problems in domains such as…

Machine Learning · Computer Science 2022-08-22 Vishakha Patil , Vineet Nair , Ganesh Ghalme , Arindam Khan

Recently multi-armed bandit problem arises in many real-life scenarios where arms must be sampled in batches, due to limited time the agent can wait for the feedback. Such applications include biological experimentation and online…

Machine Learning · Statistics 2023-12-22 Shengyu Cao , Simai He , Ruoqing Jiang , Jin Xu , Hongsong Yuan

We study online learning in constrained Markov decision processes (CMDPs) in which rewards and constraints may be either stochastic or adversarial. In such settings, Stradi et al.(2024) proposed the first best-of-both-worlds algorithm able…

Machine Learning · Computer Science 2025-02-10 Francesco Emanuele Stradi , Anna Lunghi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

We give a complete characterization of the complexity of best-arm identification in one-parameter bandit problems. We prove a new, tight lower bound on the sample complexity. We propose the `Track-and-Stop' strategy, which we prove to be…

Statistics Theory · Mathematics 2016-06-02 Aurélien Garivier , Emilie Kaufmann