English
Related papers

Related papers: On Minimax Optimal Offline Policy Evaluation

200 papers

In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy.…

Machine Learning · Computer Science 2022-11-04 Jie Wang , Rui Gao , Hongyuan Zha

This paper introduces a new principled approach for off-policy learning in contextual bandits. Unlike previous work, our approach does not derive learning principles from intractable or loose bounds. We analyse the problem through the…

Machine Learning · Statistics 2023-05-30 Otmane Sakhi , Pierre Alquier , Nicolas Chopin

What is the most statistically efficient way to do off-policy evaluation and optimization with batch data from bandit feedback? For log data generated by contextual bandit algorithms, we consider offline estimators for the expected reward…

Machine Learning · Computer Science 2018-12-07 Yusuke Narita , Shota Yasui , Kohei Yata

An extension of the traditional two-armed bandit problem is considered, in which the decision maker has access to some side information before deciding which arm to pull. At each time t, before making a selection, the decision maker is able…

Information Theory · Computer Science 2007-07-16 Chih-Chun Wang , Sanjeev R. Kulkarni , H. Vincent Poor

Learning paradigms based purely on offline data as well as those based solely on sequential online learning have been well-studied in the literature. In this paper, we consider combining offline data with online learning, an area less…

Machine Learning · Computer Science 2023-06-16 Shubhada Agrawal , Sandeep Juneja , Karthikeyan Shanmugam , Arun Sai Suggala

Off-policy evaluation (OPE) and off-policy learning (OPL) are foundational for decision-making in offline contextual bandits. Recent advances in OPL primarily optimize OPE estimators with improved statistical properties, assuming that…

Machine Learning · Statistics 2025-09-04 Imad Aouali , Otmane Sakhi

We propose the first boosting algorithm for off-policy learning from logged bandit feedback. Unlike existing boosting methods for supervised learning, our algorithm directly optimizes an estimate of the policy's expected reward. We analyze…

Machine Learning · Computer Science 2023-05-03 Ben London , Levi Lu , Ted Sandler , Thorsten Joachims

This work investigates the offline formulation of the contextual bandit problem, where the goal is to leverage past interactions collected under a behavior policy to evaluate, select, and learn new, potentially better-performing, policies.…

Machine Learning · Statistics 2024-11-01 Otmane Sakhi , Imad Aouali , Pierre Alquier , Nicolas Chopin

We propose a new framework for designing estimators for off-policy evaluation in contextual bandits. Our approach is based on the asymptotically optimal doubly robust estimator, but we shrink the importance weights to minimize a bound on…

Machine Learning · Computer Science 2020-09-22 Yi Su , Maria Dimakopoulou , Akshay Krishnamurthy , Miroslav Dudík

We introduce the cram method as a general statistical framework for evaluating the final learned policy from a multi-armed contextual bandit algorithm, using the dataset generated by the same bandit algorithm. The proposed on-policy…

Machine Learning · Computer Science 2025-04-16 Zeyang Jia , Kosuke Imai , Michael Lingzhi Li

We propose a robust regression approach to off-policy evaluation (OPE) for contextual bandits. We frame OPE as a covariate-shift problem and leverage modern robust regression tools. Ours is a general approach that can be used to augment any…

Machine Learning · Computer Science 2019-11-19 Anqi Liu , Hao Liu , Anima Anandkumar , Yisong Yue

Estimation of importance sampling weights for off-policy evaluation of contextual bandits often results in imbalance - a mismatch between the desired and the actual distribution of state-action pairs after weighting. In this work we present…

Machine Learning · Computer Science 2020-03-06 Arjun Sondhi , David Arbour , Drew Dimmery

In the field of reinforcement learning, because of the high cost and risk of policy training in the real world, policies are trained in a simulation environment and transferred to the corresponding real-world environment. However, the…

Machine Learning · Computer Science 2023-01-12 Takumi Tanabe , Rei Sato , Kazuto Fukuchi , Jun Sakuma , Youhei Akimoto

We develop confidence bounds that hold uniformly over time for off-policy evaluation in the contextual bandit setting. These confidence sequences are based on recent ideas from martingale analysis and are non-asymptotic, non-parametric, and…

Machine Learning · Computer Science 2021-02-19 Nikos Karampatziakis , Paul Mineiro , Aaditya Ramdas

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

We study minimax methods for off-policy evaluation (OPE) using value functions and marginalized importance weights. Despite that they hold promises of overcoming the exponential variance in traditional importance sampling, several key…

Machine Learning · Computer Science 2020-11-06 Nan Jiang , Jiawei Huang

We study the offline contextual bandit problem, where we aim to acquire an optimal policy using observational data. However, this data usually contains two deficiencies: (i) some variables that confound actions are not observed, and (ii)…

Machine Learning · Computer Science 2023-03-21 Siyu Chen , Yitan Wang , Zhaoran Wang , Zhuoran Yang

This paper deals with optimal policy learning (OPL) with observational data, i.e. data-driven optimal decision-making, in multi-action (or multi-arm) settings, where a finite set of decision options is available. It is organized in three…

Machine Learning · Statistics 2024-04-01 Giovanni Cerulli

Off-policy evaluation provides an essential tool for evaluating the effects of different policies or treatments using only observed data. When applied to high-stakes scenarios such as medical diagnosis or financial decision-making, it is…

Machine Learning · Computer Science 2020-10-30 Ziyang Tang , Yihao Feng , Na Zhang , Jian Peng , Qiang Liu

We study off-policy evaluation and learning from sequential data in a structured class of Markov decision processes that arise from repeated interactions with an exogenous sequence of arrivals with contexts, which generate unknown…

Machine Learning · Computer Science 2021-10-20 Nathan Kallus , Angela Zhou