English
Related papers

Related papers: Off-policy Bandits with Deficient Support

200 papers

We consider off-policy evaluation in the contextual bandit setting for the purpose of obtaining a robust off-policy selection strategy, where the selection strategy is evaluated based on the value of the chosen policy in a set of proposal…

Machine Learning · Computer Science 2022-03-22 Ilja Kuzborskij , Claire Vernade , András György , Csaba Szepesvári

Off-policy evaluation methods are important in recommendation systems and search engines, where data collected under an existing logging policy is used to estimate the performance of a new proposed policy. A common approach to this problem…

Machine Learning · Computer Science 2023-01-04 Jaron J. R. Lee , David Arbour , Georgios Theocharous

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

Contextual bandits are widely-used in the study of learning-based control policies for finite action spaces. While the problem is well-studied for bandits with perfectly observed context vectors, little is known about the case of…

Machine Learning · Statistics 2022-02-03 Hongju Park , Mohamad Kazem Shirani Faradonbeh

Preference-based feedback is important for many applications where direct evaluation of a reward function is not feasible. A notable recent example arises in reinforcement learning from human feedback on large language models. For many of…

Machine Learning · Computer Science 2023-07-24 Viraj Mehta , Ojash Neopane , Vikramjeet Das , Sen Lin , Jeff Schneider , Willie Neiswanger

We present and prove properties of a new offline policy evaluator for an exploration learning setting which is superior to previous evaluators. In particular, it simultaneously and correctly incorporates techniques from importance…

Machine Learning · Computer Science 2012-10-19 Miroslav Dudik , Dumitru Erhan , John Langford , Lihong Li

The goal of off-policy evaluation (OPE) is to evaluate a new policy using historical data obtained via a behavior policy. However, because the contextual bandit algorithm updates the policy based on past observations, the samples are not…

Machine Learning · Computer Science 2020-10-27 Masahiro Kato , Yusuke Kaneko

Off-policy learning plays a pivotal role in optimizing and evaluating policies prior to the online deployment. However, during the real-time serving, we observe varieties of interventions and constraints that cause inconsistency between the…

Machine Learning · Computer Science 2022-03-01 Da Xu , Yuting Ye , Chuanwei Ruan , Bo Yang

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

Off-policy evaluation (OPE) is the problem of estimating the value of a target policy from samples obtained via different policies. Recently, applying OPE methods for bandit problems has garnered attention. For the theoretical guarantees of…

Machine Learning · Computer Science 2020-10-26 Masahiro Kato , Kenshi Abe , Kaito Ariu , Shota Yasui

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

Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to the inherent distributional shift and value function…

Machine Learning · Computer Science 2026-02-03 Arip Asadulaev , Maksim Bobrin , Salem Lahlou , Dmitry Dylov , Fakhri Karray , Martin Takac

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

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 study the Inverse Contextual Bandit (ICB) problem, in which a learner seeks to optimize a policy while an observer, who cannot access the learner's rewards and only observes actions, aims to recover the underlying problem parameters.…

Machine Learning · Computer Science 2026-03-05 Yuqi Kong , Xiao Zhang , Weiran Shen

This paper studies the evaluation of policies that recommend an ordered set of items (e.g., a ranking) based on some context---a common scenario in web search, ads, and recommendation. We build on techniques from combinatorial bandits to…

Machine Learning · Computer Science 2017-11-08 Adith Swaminathan , Akshay Krishnamurthy , Alekh Agarwal , Miroslav Dudík , John Langford , Damien Jose , Imed Zitouni

Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, particularly in the experience replay setting now commonly used with deep neural networks. Classically, off-policy estimation bias is…

Machine Learning · Computer Science 2021-12-24 Brett Daley , Christopher Amato

In the field of reinforcement learning there has been recent progress towards safety and high-confidence bounds on policy performance. However, to our knowledge, no practical methods exist for determining high-confidence policy performance…

Artificial Intelligence · Computer Science 2018-06-26 Daniel S. Brown , Scott Niekum

We consider local kernel metric learning for off-policy evaluation (OPE) of deterministic policies in contextual bandits with continuous action spaces. Our work is motivated by practical scenarios where the target policy needs to be…

Machine Learning · Computer Science 2022-12-29 Haanvid Lee , Jongmin Lee , Yunseon Choi , Wonseok Jeon , Byung-Jun Lee , Yung-Kyun Noh , Kee-Eung Kim

We study offline recommender learning from explicit rating feedback in the presence of selection bias. A current promising solution for the bias is the inverse propensity score (IPS) estimation. However, the performance of existing…

Machine Learning · Statistics 2022-04-22 Yuta Saito , Masahiro Nomura