English
Related papers

Related papers: Confident Off-Policy Evaluation and Selection thro…

200 papers

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

This paper is concerned with constructing a confidence interval for a target policy's value offline based on a pre-collected observational data in infinite horizon settings. Most of the existing works assume no unmeasured variables exist…

Machine Learning · Statistics 2022-11-07 Chengchun Shi , Jin Zhu , Ye Shen , Shikai Luo , Hongtu Zhu , Rui Song

This study addresses the problem of off-policy evaluation (OPE) from dependent samples obtained via the bandit algorithm. The goal of OPE is to evaluate a new policy using historical data obtained from behavior policies generated by the…

Machine Learning · Statistics 2020-06-15 Masahiro Kato

We study risk-aware offline policy learning, aiming to learn a decision rule from logged data that is optimal under general risk criteria. This problem is crucial in high-stakes domains where online interaction is infeasible and adverse…

Machine Learning · Statistics 2026-05-18 Yilong Wan , Yuqiang Li , Xianyi Wu

We study the problem of estimating the expected reward of the optimal policy in the stochastic disjoint linear bandit setting. We prove that for certain settings it is possible to obtain an accurate estimate of the optimal policy value even…

Machine Learning · Computer Science 2019-12-17 Weihao Kong , Gregory Valiant , Emma Brunskill

Off-policy evaluation is critical in a number of applications where new policies need to be evaluated offline before online deployment. Most existing methods focus on the expected return, define the target parameter through averaging and…

Machine Learning · Statistics 2023-02-10 Yingying Zhang , Chengchun Shi , Shikai Luo

Off-policy evaluation and learning in contextual bandits use logged interaction data to estimate and optimize the value of a target policy. Most existing methods require sufficient action overlap between the logging and target policies, and…

Machine Learning · Statistics 2026-02-03 Shu Tamano

We study the problem of off-policy evaluation in the multi-armed bandit model with bounded rewards, and develop minimax rate-optimal procedures under three settings. First, when the behavior policy is known, we show that the Switch…

Machine Learning · Statistics 2021-01-20 Cong Ma , Banghua Zhu , Jiantao Jiao , Martin J. Wainwright

Offline reinforcement learning, wherein one uses off-policy data logged by a fixed behavior policy to evaluate and learn new policies, is crucial in applications where experimentation is limited such as medicine. We study the estimation of…

Machine Learning · Computer Science 2020-06-09 Nathan Kallus , Masatoshi Uehara

We consider off-policy evaluation and optimization with continuous action spaces. We focus on observational data where the data collection policy is unknown and needs to be estimated. We take a semi-parametric approach where the value…

Econometrics · Economics 2019-07-23 Mert Demirer , Vasilis Syrgkanis , Greg Lewis , Victor Chernozhukov

Off-policy learning (OPL) aims at finding improved policies from logged bandit data, often by minimizing the inverse propensity scoring (IPS) estimator of the risk. In this work, we investigate a smooth regularization for IPS, for which we…

Machine Learning · Computer Science 2023-06-06 Imad Aouali , Victor-Emmanuel Brunel , David Rohde , Anna Korba

In this work, we consider the off-policy policy evaluation problem for contextual bandits and finite horizon reinforcement learning in the nonstationary setting. Reusing old data is critical for policy evaluation, but existing estimators…

Machine Learning · Computer Science 2023-02-24 Vincent Liu , Yash Chandak , Philip Thomas , Martha White

Off-policy evaluation (OPE) is the problem of estimating the value of a target policy using historical data collected under a different logging policy. OPE methods typically assume overlap between the target and logging policy, enabling…

Methodology · Statistics 2024-03-12 Samir Khan , Martin Saveski , Johan Ugander

We consider the problem of learning personalized decision policies from observational bandit feedback data across multiple heterogeneous data sources. In our approach, we introduce a novel regret analysis that establishes finite-sample…

Machine Learning · Computer Science 2024-10-14 Aldo Gael Carranza , Susan Athey

Off-policy learning is a framework for evaluating and optimizing policies without deploying them, from data collected by another policy. Real-world environments are typically non-stationary and the offline learned policies should adapt to…

Machine Learning · Computer Science 2021-04-06 Joey Hong , Branislav Kveton , Manzil Zaheer , Yinlam Chow , Amr Ahmed

We provide theoretical investigations into off-policy evaluation in reinforcement learning using function approximators for (marginalized) importance weights and value functions. Our contributions include: (1) A new estimator, MWL, that…

Machine Learning · Computer Science 2020-10-08 Masatoshi Uehara , Jiawei Huang , Nan Jiang

Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates are performed on data collected by older policies. This…

Machine Learning · Computer Science 2026-05-28 Otmane Sakhi , Aleksei Arzhantsev , Imad Aouali , Flavian Vasile

In many domains, the exploration process of reinforcement learning will be too costly as it requires trying out suboptimal policies, resulting in a need for off-policy evaluation, in which a target policy is evaluated based on data…

Machine Learning · Computer Science 2024-05-07 David M. Bossens , Philip S. Thomas

Offline contextual bandits allow one to learn policies from historical/offline data without requiring online interaction. However, offline policy optimization that maximizes overall expected rewards can unintentionally amplify the reward…

Machine Learning · Computer Science 2026-01-07 Yihong Guo , Junjie Luo , Guodong Gao , Ritu Agarwal , Anqi Liu

Off-policy evaluation learns a target policy's value with a historical dataset generated by a different behavior policy. In addition to a point estimate, many applications would benefit significantly from having a confidence interval (CI)…

Machine Learning · Statistics 2021-06-09 Chengchun Shi , Runzhe Wan , Victor Chernozhukov , Rui Song