English
Related papers

Related papers: Learning Action Embeddings for Off-Policy Evaluati…

200 papers

We investigate off-policy evaluation (OPE), a central and fundamental problem in reinforcement learning (RL), in the challenging setting of Partially Observable Markov Decision Processes (POMDPs) with large observation spaces. Recent works…

Machine Learning · Computer Science 2025-03-04 Yuheng Zhang , Nan Jiang

Off-policy learning and evaluation leverage logged bandit feedback datasets, which contain context, action, propensity score, and feedback for each data point. These scenarios face significant challenges due to high variance and poor…

Machine Learning · Computer Science 2025-06-10 Armin Behnamnia , Gholamali Aminian , Alireza Aghaei , Chengchun Shi , Vincent Y. F. Tan , Hamid R. Rabiee

Off-policy Evaluation (OPE) methods are crucial tools for evaluating policies in high-stakes domains such as healthcare, where direct deployment is often infeasible, unethical, or expensive. When deployment environments are expected to…

Machine Learning · Computer Science 2022-09-20 Harvineet Singh , Shalmali Joshi , Finale Doshi-Velez , Himabindu Lakkaraju

This work studies the statistical limits of uniform convergence for offline policy evaluation (OPE) problems with model-based methods (for episodic MDP) and provides a unified framework towards optimal learning for several well-motivated…

Machine Learning · Computer Science 2021-06-25 Ming Yin , Yu-Xiang Wang

We consider the off-policy evaluation (OPE) problem in contextual bandits, where the goal is to estimate the value of a target policy using the data collected by a logging policy. Most popular approaches to the OPE are variants of the…

Machine Learning · Statistics 2024-08-20 Sutanoy Dasgupta , Yabo Niu , Kishan Panaganti , Dileep Kalathil , Debdeep Pati , Bani Mallick

Importance sampling (IS) is often used to perform off-policy policy evaluation but is prone to several issues, especially when the behavior policy is unknown and must be estimated from data. Significant differences between the target and…

Machine Learning · Computer Science 2021-11-23 Anton Matsson , Fredrik D. Johansson

Off-policy evaluation (OPE) is the task of estimating the expected reward of a given policy based on offline data previously collected under different policies. Therefore, OPE is a key step in applying reinforcement learning to real-world…

Machine Learning · Computer Science 2021-03-11 Yihao Feng , Ziyang Tang , Na Zhang , Qiang Liu

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

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

In reinforcement learning, distributional off-policy evaluation (OPE) focuses on estimating the return distribution of a target policy using offline data collected under a different policy. This work focuses on extending the widely used…

Machine Learning · Statistics 2025-10-21 Sungee Hong , Jiayi Wang , Zhengling Qi , Raymond K. W. Wong

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

We study off-policy evaluation (OPE) from multiple logging policies, each generating a dataset of fixed size, i.e., stratified sampling. Previous work noted that in this setting the ordering of the variances of different importance sampling…

Machine Learning · Computer Science 2020-10-22 Nathan Kallus , Yuta Saito , Masatoshi Uehara

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

In real-world recommender systems and search engines, optimizing ranking decisions to present a ranked list of relevant items is critical. Off-policy evaluation (OPE) for ranking policies is thus gaining a growing interest because it…

Machine Learning · Statistics 2022-02-04 Haruka Kiyohara , Yuta Saito , Tatsuya Matsuhiro , Yusuke Narita , Nobuyuki Shimizu , Yasuo Yamamoto

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

Off-policy evaluation (OPE) constructs confidence intervals for the value of a target policy using data generated under a different behavior policy. Most existing inference methods focus on fixed target policies and may fail when the target…

Statistics Theory · Mathematics 2026-01-21 Haoyu Wei

In this work, we propose marginalized operators, a new class of off-policy evaluation operators for reinforcement learning. Marginalized operators strictly generalize generic multi-step operators, such as Retrace, as special cases.…

Machine Learning · Computer Science 2022-03-31 Yunhao Tang , Mark Rowland , Rémi Munos , Michal Valko

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 learning optimal policies from a logged dataset, i.e., offline RL, with function approximation. Despite the efforts devoted, existing algorithms with theoretic finite-sample guarantees typically assume exploratory data coverage or…

Machine Learning · Computer Science 2023-05-25 Chenjie Mao

Offline reinforcement learning algorithms often require careful hyperparameter tuning. Before deployment, we need to select amongst a set of candidate policies. However, there is limited understanding about the fundamental limits of this…

Machine Learning · Computer Science 2026-02-17 Vincent Liu , Prabhat Nagarajan , Andrew Patterson , Martha White