English
Related papers

Related papers: SPEED: Experimental Design for Policy Evaluation i…

200 papers

We consider the scheduling problem concerning N projects. Each project evolves as a multi-state Markov process. At each time instant, one project is scheduled to work, and some reward depending on the state of the chosen project is…

Optimization and Control · Mathematics 2016-02-02 Kehao Wang

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

In many bandit problems, the maximal reward achievable by a policy is often unknown in advance. We consider the problem of estimating the optimal policy value in the sublinear data regime before the optimal policy is even learnable. We…

Machine Learning · Computer Science 2023-02-21 Jonathan N. Lee , Weihao Kong , Aldo Pacchiano , Vidya Muthukumar , Emma Brunskill

In this paper we propose a novel experimental design-based algorithm to minimize regret in online stochastic linear and combinatorial bandits. While existing literature tends to focus on optimism-based algorithms--which have been shown to…

Machine Learning · Computer Science 2021-03-02 Andrew Wagenmaker , Julian Katz-Samuels , Kevin Jamieson

Stochastic linear bandits are a fundamental model for sequential decision making, where an agent selects a vector-valued action and receives a noisy reward with expected value given by an unknown linear function. Although well studied in…

Machine Learning · Computer Science 2025-06-23 Bruce Huang , Ruida Zhou , Lin F. Yang , Suhas Diggavi

In this paper, we introduce the notion of replicable policies in the context of stochastic bandits, one of the canonical problems in interactive learning. A policy in the bandit environment is called replicable if it pulls, with high…

Machine Learning · Computer Science 2023-02-16 Hossein Esfandiari , Alkis Kalavasis , Amin Karbasi , Andreas Krause , Vahab Mirrokni , Grigoris Velegkas

Policy regret is a well established notion of measuring the performance of an online learning algorithm against an adaptive adversary. We study restrictions on the adversary that enable efficient minimization of the \emph{complete policy…

Machine Learning · Statistics 2022-04-26 Dhruv Malik , Yuanzhi Li , Aarti Singh

Performance of machine learning algorithms depends critically on identifying a good set of hyperparameters. While recent approaches use Bayesian optimization to adaptively select configurations, we focus on speeding up random search through…

Machine Learning · Computer Science 2018-06-20 Lisha Li , Kevin Jamieson , Giulia DeSalvo , Afshin Rostamizadeh , Ameet Talwalkar

We propose online algorithms for sequential learning in the contextual multi-armed bandit setting. Our approach is to partition the context space and then optimally combine all of the possible mappings between the partition regions and the…

Machine Learning · Computer Science 2017-12-11 Mohammadreza Mohaghegh Neyshabouri , Kaan Gokcesu , Huseyin Ozkan , Suleyman S. Kozat

Contextual multi-armed bandits are a popular choice to model sequential decision-making. E.g., in a healthcare application we may perform various tests to asses a patient condition (exploration) and then decide on the best treatment to give…

Machine Learning · Computer Science 2025-04-08 Mirco Mutti , Jeongyeol Kwon , Shie Mannor , Aviv Tamar

We study finite-armed semiparametric bandits, where each arm's reward combines a linear component with an unknown, potentially adversarial shift. This model strictly generalizes classical linear bandits and reflects complexities common in…

Machine Learning · Statistics 2025-06-18 Seok-Jin Kim , Gi-Soo Kim , Min-hwan Oh

The multi-armed bandit problem is a core framework for sequential decision-making under uncertainty, but classical algorithms often fail in environments with hidden, time-varying states that confound reward estimation and optimal action…

Machine Learning · Computer Science 2026-02-19 Jikai Jin , Kenneth Hung , Sanath Kumar Krishnamurthy , Baoyi Shi , Congshan Zhang

Motivated by the importance of explainability in modern machine learning, we design bandit algorithms that are efficient and interpretable. A bandit algorithm is interpretable if it explores with the objective of reducing uncertainty in the…

Machine Learning · Computer Science 2024-02-12 Subhojyoti Mukherjee , Ruihao Zhu , Branislav Kveton

Canonical algorithms for multi-armed bandits typically assume a stationary reward environment where the size of the action space (number of arms) is small. More recently developed methods typically relax only one of these assumptions:…

Machine Learning · Computer Science 2025-06-02 Derek Everett , Fred Lu , Edward Raff , Fernando Camacho , James Holt

In the stochastic bandit problem, the goal is to maximize an unknown function via a sequence of noisy evaluations. Typically, the observation noise is assumed to be independent of the evaluation point and to satisfy a tail bound uniformly…

Machine Learning · Statistics 2018-04-20 Johannes Kirschner , Andreas Krause

We study two model selection settings in stochastic linear bandits (LB). In the first setting, which we refer to as feature selection, the expected reward of the LB problem is in the linear span of at least one of $M$ feature maps (models).…

Machine Learning · Computer Science 2022-06-20 Ahmadreza Moradipari , Berkay Turan , Yasin Abbasi-Yadkori , Mahnoosh Alizadeh , Mohammad Ghavamzadeh

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

Partial monitoring is an expressive framework for sequential decision-making with an abundance of applications, including graph-structured and dueling bandits, dynamic pricing and transductive feedback models. We survey and extend recent…

Machine Learning · Computer Science 2023-11-15 Johannes Kirschner , Tor Lattimore , Andreas Krause

We study contextual bandits in the stochastic i.i.d.\ setting, where a learner observes contexts drawn from an unknown distribution, selects actions from a finite set $A$, and aims to identify an approximately optimal policy from a given…

Machine Learning · Computer Science 2026-05-29 Liad Erez , Fan Chen , Alon Cohen , Tomer Koren , Yishay Mansour , Shay Moran , Alexander Rakhlin

Given n experiment subjects with potentially heterogeneous covariates and two possible treatments, namely active treatment and control, this paper addresses the fundamental question of determining the optimal accuracy in estimating the…

Machine Learning · Statistics 2024-11-13 Jiachun Li , David Simchi-Levi , Yunxiao Zhao