English
Related papers

Related papers: Off-Policy Evaluation via Adaptive Weighting with …

200 papers

Contextual bandits are widely used in industrial personalization systems. These online learning frameworks learn a treatment assignment policy in the presence of treatment effects that vary with the observed contextual features of the…

Machine Learning · Computer Science 2022-05-11 Claudia Roberts , Maria Dimakopoulou , Qifeng Qiao , Ashok Chandrashekhar , Tony Jebara

We consider estimation of a linear functional of the treatment effect using adaptively collected data. This task finds a variety of applications including the off-policy evaluation (\textsf{OPE}) in contextual bandits, and estimation of the…

Machine Learning · Statistics 2024-11-21 Jeonghwan Lee , Cong Ma

Addressing such diverse ends as safety alignment with human preferences, and the efficiency of learning, a growing line of reinforcement learning research focuses on risk functionals that depend on the entire distribution of returns. Recent…

Machine Learning · Computer Science 2022-09-22 Audrey Huang , Liu Leqi , Zachary Chase Lipton , Kamyar Azizzadenesheli

In many real-world reinforcement learning applications, access to the environment is limited to a fixed dataset, instead of direct (online) interaction with the environment. When using this data for either evaluation or training of a new…

Machine Learning · Computer Science 2019-11-06 Ofir Nachum , Yinlam Chow , Bo Dai , Lihong Li

Policy gradient methods in reinforcement learning update policy parameters by taking steps in the direction of an estimated gradient of policy value. In this paper, we consider the statistically efficient estimation of policy gradients from…

Machine Learning · Statistics 2020-02-21 Nathan Kallus , Masatoshi Uehara

Contextual bandits are canonical models for sequential decision-making under uncertainty in environments with time-varying components. In this setting, the expected reward of each bandit arm consists of the inner product of an unknown…

Machine Learning · Statistics 2022-05-27 Hongju Park , Mohamad Kazem Shirani Faradonbeh

Doubly robust (DR) estimators guard against model misspecification but remain sensitive to weak covariate overlap. We show that trimming propensity scores reduces variance but eliminates double robustness. We introduce DR estimators that…

Econometrics · Economics 2026-04-17 Yukun Ma , Pedro H. C. Sant'Anna , Yuya Sasaki , Takuya Ura

Empirical risk minimization (ERM) is the workhorse of machine learning, whether for classification and regression or for off-policy policy learning, but its model-agnostic guarantees can fail when we use adaptively collected data, such as…

Machine Learning · Statistics 2021-06-04 Aurélien Bibaut , Antoine Chambaz , Maria Dimakopoulou , Nathan Kallus , Mark van der Laan

Bandits with covariates, a.k.a. contextual bandits, address situations where optimal actions (or arms) at a given time $t$, depend on a context $x_t$, e.g., a new patient's medical history, a consumer's past purchases. While it is…

Machine Learning · Statistics 2021-02-23 Joseph Suk , Samory Kpotufe

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

Doubly robust (DR) estimation is a crucial technique in causal inference and missing data problems. We propose a novel Propensity score Augmentved Doubly robust (PAD) estimator to enhance the commonly used DR estimator for average treatment…

Methodology · Statistics 2023-04-18 Liangbo Lyu , Molei Liu

We study policy evaluation of offline contextual bandits subject to unobserved confounders. Sensitivity analysis methods are commonly used to estimate the policy value under the worst-case confounding over a given uncertainty set. However,…

Machine Learning · Statistics 2026-01-13 Kei Ishikawa , Niao He , Takafumi Kanamori

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

High-quality data plays a central role in ensuring the accuracy of policy evaluation. This paper initiates the study of efficient and safe data collection for bandit policy evaluation. We formulate the problem and investigate its several…

Machine Learning · Computer Science 2022-06-22 Runzhe Wan , Branislav Kveton , Rui Song

Contextual bandit algorithms are essential for solving real-world decision making problems. In practice, collecting a contextual bandit's feedback from different domains may involve different costs. For example, measuring drug reaction from…

Machine Learning · Computer Science 2025-04-08 Ziyan Wang , Xiaoming Huo , Hao Wang

We investigate experiments that are designed to select a treatment arm for population deployment. Multi-armed bandit algorithms can enhance efficiency by dynamically allocating measurement effort towards higher performing arms based on…

Machine Learning · Computer Science 2023-08-29 Chao Qin , Daniel Russo

Doubly robust methods hold considerable promise for off-policy evaluation in Markov decision processes (MDPs) under sequential ignorability: They have been shown to converge as $1/\sqrt{T}$ with the horizon $T$, to be statistically…

Machine Learning · Statistics 2025-09-30 Mohammad Mehrabi , Stefan Wager

This paper studies bandit problems where an agent has access to offline data that might be utilized to potentially improve the estimation of each arm's reward distribution. A major obstacle in this setting is the existence of compound…

Machine Learning · Computer Science 2023-12-21 Wen Huang , Xintao Wu

We introduce a novel doubly-robust (DR) off-policy evaluation (OPE) estimator for Markov decision processes, DRUnknown, designed for situations where both the logging policy and the value function are unknown. The proposed estimator…

Machine Learning · Statistics 2024-04-03 Kyungbok Lee , Myunghee Cho Paik

To take sample biases and skewness in the observations into account, practitioners frequently weight their observations according to some marginal distribution. The present paper demonstrates that such weighting can indeed improve the…

Methodology · Statistics 2018-11-05 Tobias Niebuhr , Mathias Trabs