English
Related papers

Related papers: Off-policy Confidence Sequences

200 papers

We study the problem of offline learning in automated decision systems under the contextual bandits model. We are given logged historical data consisting of contexts, (randomized) actions, and (nonnegative) rewards. A common goal is to…

Machine Learning · Computer Science 2019-01-16 Yifei Ma , Yu-Xiang Wang , Balakrishnan , Narayanaswamy

We study the problem of off-policy evaluation from batched contextual bandit data with multidimensional actions, often termed slates. The problem is common to recommender systems and user-interface optimization, and it is particularly…

Machine Learning · Computer Science 2021-11-04 Nikos Vlassis , Ashok Chandrashekar , Fernando Amat Gil , Nathan Kallus

Certifiable, adaptive uncertainty estimates for unknown quantities are an essential ingredient of sequential decision-making algorithms. Standard approaches rely on problem-dependent concentration results and are limited to a specific…

Machine Learning · Computer Science 2023-11-09 Nicolas Emmenegger , Mojmír Mutný , Andreas Krause

Batch policy optimization considers leveraging existing data for policy construction before interacting with an environment. Although interest in this problem has grown significantly in recent years, its theoretical foundations remain…

Machine Learning · Computer Science 2021-04-07 Chenjun Xiao , Yifan Wu , Tor Lattimore , Bo Dai , Jincheng Mei , Lihong Li , Csaba Szepesvari , Dale Schuurmans

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

We consider the linear contextual bandit problem with resource consumption, in addition to reward generation. In each round, the outcome of pulling an arm is a reward as well as a vector of resource consumptions. The expected values of…

Machine Learning · Computer Science 2016-07-12 Shipra Agrawal , Nikhil R. Devanur

Off-policy evaluation (OPE) attempts to predict the performance of counterfactual policies using log data from a different policy. We extend its applicability by developing an OPE method for a class of both full support and deficient…

Machine Learning · Computer Science 2022-12-06 Yusuke Narita , Kyohei Okumura , Akihiro Shimizu , Kohei Yata

This paper is devoted to regret lower bounds in the classical model of stochastic multi-armed bandit. A well-known result of Lai and Robbins, which has then been extended by Burnetas and Katehakis, has established the presence of a…

Machine Learning · Statistics 2011-12-19 Antoine Salomon , Jean-Yves Audibert , Issam El Alaoui

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

We provide the first oracle efficient sublinear regret algorithms for adversarial versions of the contextual bandit problem. In this problem, the learner repeatedly makes an action on the basis of a context and receives reward for the…

Machine Learning · Computer Science 2016-02-09 Vasilis Syrgkanis , Akshay Krishnamurthy , Robert E. Schapire

We investigate the feasibility of learning from a mix of both fully-labeled supervised data and contextual bandit data. We specifically consider settings in which the underlying learning signal may be different between these two data…

Machine Learning · Computer Science 2019-06-25 Chicheng Zhang , Alekh Agarwal , Hal Daumé , John Langford , Sahand N Negahban

Contextual bandit algorithms are increasingly replacing non-adaptive A/B tests in e-commerce, healthcare, and policymaking because they can both improve outcomes for study participants and increase the chance of identifying good or even…

Machine Learning · Statistics 2021-06-02 Aurélien Bibaut , Antoine Chambaz , Maria Dimakopoulou , Nathan Kallus , Mark van der Laan

The contextual bandit framework is widely used to solve sequential optimization problems where the reward of each decision depends on auxiliary context variables. In settings such as medicine, business, and engineering, the decision maker…

Machine Learning · Statistics 2025-03-17 Kevin Li , Eric Laber

In this paper we consider stochastic multiarmed bandit problems. Recently a policy, DMED, is proposed and proved to achieve the asymptotic bound for the model that each reward distribution is supported in a known bounded interval, e.g.…

Statistics Theory · Mathematics 2012-02-20 Junya Honda , Akimichi Takemura

Contextual bandits have become popular as they offer a middle ground between very simple approaches based on multi-armed bandits and very complex approaches using the full power of reinforcement learning. They have demonstrated success in…

Methodology · Statistics 2017-11-13 Kristjan Greenewald , Ambuj Tewari , Predrag Klasnja , Susan Murphy

Off-policy learning is a framework for optimizing policies without deploying them, using data collected by another policy. In recommender systems, this is especially challenging due to the imbalance in logged data: some items are…

Machine Learning · Computer Science 2024-10-23 Matej Cief , Branislav Kveton , Michal Kompan

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

We provide a sound and consistent foundation for the use of \emph{nonrandom} exploration data in "contextual bandit" or "partially labeled" settings where only the value of a chosen action is learned. The primary challenge in a variety of…

Machine Learning · Computer Science 2010-06-15 Alex Strehl , John Langford , Sham Kakade , Lihong Li

In statistical learning, algorithms for model selection allow the learner to adapt to the complexity of the best hypothesis class in a sequence. We ask whether similar guarantees are possible for contextual bandit learning.

Machine Learning · Computer Science 2020-06-22 Dylan J. Foster , Akshay Krishnamurthy , Haipeng Luo

Off-policy learning methods are intended to learn a policy from logged data, which includes context, action, and feedback (cost or reward) for each sample point. In this work, we build on the counterfactual risk minimization framework,…