English
Related papers

Related papers: Kernel Metric Learning for In-Sample Off-Policy Ev…

200 papers

Off-Policy Evaluation (OPE) is an important practical problem in algorithmic ranking systems, where the goal is to estimate the expected performance of a new ranking policy using only offline logged data collected under a different, logging…

We consider off-policy evaluation (OPE) in continuous treatment settings, such as personalized dose-finding. In OPE, one aims to estimate the mean outcome under a new treatment decision rule using historical data generated by a different…

Machine Learning · Statistics 2021-11-08 Hengrui Cai , Chengchun Shi , Rui Song , Wenbin Lu

Compared to on-policy counterparts, off-policy model-free deep reinforcement learning can improve data efficiency by repeatedly using the previously gathered data. However, off-policy learning becomes challenging when the discrepancy…

Machine Learning · Computer Science 2023-09-27 Baturay Saglam , Dogan C. Cicek , Furkan B. Mutlu , Suleyman S. Kozat

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

Offline policy evaluation (OPE) allows us to evaluate and estimate a new sequential decision-making policy's performance by leveraging historical interaction data collected from other policies. Evaluating a new policy online without a…

Machine Learning · Computer Science 2024-11-04 Allen Nie , Yash Chandak , Christina J. Yuan , Anirudhan Badrinath , Yannis Flet-Berliac , Emma Brunskil

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

Reinforcement learning (RL) has the potential to transform real-world decision-making systems by enabling autonomous agents to learn from experience. Deploying RL in real-world settings, especially in the context of human-robot interaction,…

Machine Learning · Computer Science 2026-02-04 Saurav Singh , Rodney Sanchez , Alexander Ororbia , Jamison Heard

Offline reinforcement learning (RL) aims to learn a policy that maximizes the expected return using a given static dataset of transitions. However, offline RL faces the distribution shift problem. The policy constraint offline RL method is…

Machine Learning · Computer Science 2025-12-24 Yuanhao Chen , Qi Liu , Pengbin Chen , Zhongjian Qiao , Yanjie Li

Off-policy evaluation (OPE) in reinforcement learning is notoriously difficult in long- and infinite-horizon settings due to diminishing overlap between behavior and target policies. In this paper, we study the role of Markovian and…

Machine Learning · Statistics 2023-01-18 Nathan Kallus , Masatoshi Uehara

Reinforcement learning (RL) approaches for Large Language Models (LLMs) frequently use on-policy algorithms, such as PPO or GRPO. However, policy lag from distributed training architectures and differences between the training and inference…

Machine Learning · Computer Science 2026-03-03 Daniel Ritter , Owen Oertell , Bradley Guo , Jonathan Chang , Kianté Brantley , Wen Sun

Off-policy learning is a framework for optimizing policies without deploying them, using data collected by another policy. In recommender systems, this is especially challenging due to the imbalance in logged data: some items are…

Machine Learning · Computer Science 2024-10-23 Matej Cief , Branislav Kveton , Michal Kompan

Many advances that have improved the robustness and efficiency of deep reinforcement learning (RL) algorithms can, in one way or another, be understood as introducing additional objectives or constraints in the policy optimization step.…

We study off-policy evaluation (OPE) of contextual bandit policies for large discrete action spaces where conventional importance-weighting approaches suffer from excessive variance. To circumvent this variance issue, we propose a new…

Machine Learning · Statistics 2023-06-12 Yuta Saito , Qingyang Ren , Thorsten Joachims

Off-policy updates are inevitable in reinforcement learning (RL) for large language models (LLMs) due to rollout staleness from asynchronous training and mismatches between training and inference engines. Naive importance sampling gives an…

Machine Learning · Computer Science 2026-05-11 Guobin Shen , Chenxiao Zhao , Xiang Cheng , Lei Huang , Xing Yu

Off-policy evaluation (OPE) in reinforcement learning is an important problem in settings where experimentation is limited, such as education and healthcare. But, in these very same settings, observed actions are often confounded by…

Machine Learning · Computer Science 2020-07-29 Andrew Bennett , Nathan Kallus , Lihong Li , Ali Mousavi

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

Training agents via off-policy deep reinforcement learning (RL) requires a large memory, named replay memory, that stores past experiences used for learning. These experiences are sampled, uniformly or non-uniformly, to create the batches…

Machine Learning · Computer Science 2022-12-27 Bumgeun Park , Taeyoung Kim , Woohyeon Moon , Luiz Felipe Vecchietti , Dongsoo Har

Off-policy evaluation (OPE) in reinforcement learning allows one to evaluate novel decision policies without needing to conduct exploration, which is often costly or otherwise infeasible. We consider for the first time the semiparametric…

Machine Learning · Computer Science 2020-06-08 Nathan Kallus , Masatoshi Uehara

We consider evaluating and training a new policy for the evaluation data by using the historical data obtained from a different policy. The goal of off-policy evaluation (OPE) is to estimate the expected reward of a new policy over the…

Machine Learning · Statistics 2020-10-19 Masahiro Kato , Masatoshi Uehara , Shota Yasui

Policy gradient methods are widely adopted reinforcement learning algorithms for tasks with continuous action spaces. These methods succeeded in many application domains, however, because of their notorious sample inefficiency their use…

Machine Learning · Statistics 2024-02-20 Davide Mambelli , Stephan Bongers , Onno Zoeter , Matthijs T. J. Spaan , Frans A. Oliehoek