English
Related papers

Related papers: PERRY: Policy Evaluation with Confidence Intervals…

200 papers

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

We offer a theoretical characterization of off-policy evaluation (OPE) in reinforcement learning using function approximation for marginal importance weights and $q$-functions when these are estimated using recent minimax methods. Under…

Machine Learning · Computer Science 2022-07-26 Masatoshi Uehara , Masaaki Imaizumi , Nan Jiang , Nathan Kallus , Wen Sun , Tengyang Xie

Decision makers often wish to use offline historical data to compare sequential-action policies at various world states. Importantly, computational tools should produce confidence values for such offline policy comparison (OPC) to account…

Machine Learning · Computer Science 2022-05-24 Anurag Koul , Mariano Phielipp , Alan Fern

To accumulate knowledge and improve its policy of behaviour, a reinforcement learning agent can learn `off-policy' about policies that differ from the policy used to generate its experience. This is important to learn counterfactuals, or…

Machine Learning · Computer Science 2022-02-03 Simon Schmitt , John Shawe-Taylor , Hado van Hasselt

Optimizing survival outcomes, such as patient survival or customer retention, is a critical objective in data-driven decision-making. Off-Policy Evaluation~(OPE) provides a powerful framework for assessing such decision-making policies…

Methodology · Statistics 2026-03-25 Kohsuke Kubota , Mitsuhiro Takahashi , Yuta Saito

Ranking interfaces are everywhere in online platforms. There is thus an ever growing interest in their Off-Policy Evaluation (OPE), aiming towards an accurate performance evaluation of ranking policies using logged data. A de-facto approach…

Machine Learning · Statistics 2023-06-28 Haruka Kiyohara , Masatoshi Uehara , Yusuke Narita , Nobuyuki Shimizu , Yasuo Yamamoto , Yuta Saito

Model-free reinforcement learning algorithms can compute policy gradients given sampled environment transitions, but require large amounts of data. In contrast, model-based methods can use the learned model to generate new data, but model…

Machine Learning · Computer Science 2022-03-04 Lukas P. Fröhlich , Maksym Lefarov , Melanie N. Zeilinger , Felix Berkenkamp

We develop a generic data-driven method for estimator selection in off-policy policy evaluation settings. We establish a strong performance guarantee for the method, showing that it is competitive with the oracle estimator, up to a constant…

Machine Learning · Computer Science 2020-08-25 Yi Su , Pavithra Srinath , Akshay Krishnamurthy

Off-Policy Evaluation (OPE) in contextual bandits is crucial for assessing new policies using existing data without costly experimentation. However, current OPE methods, such as Inverse Probability Weighting (IPW) and Doubly Robust (DR)…

Machine Learning · Statistics 2023-12-05 Muhammad Faaiz Taufiq , Arnaud Doucet , Rob Cornish , Jean-Francois Ton

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

Confidence estimation is crucial for reflecting the reliability of large language models (LLMs), particularly in the widely used closed-source models. Utilizing data augmentation for confidence estimation is viable, but discussions focus on…

Machine Learning · Computer Science 2025-06-16 Rui Wang , Renyu Zhu , Minmin Lin , Runze Wu , Tangjie Lv , Changjie Fan , Haobo Wang

Offline Reinforcement Learning (RL) learns optimal policies from fixed datasets, training a policy once and deploying it at inference time without further refinement. Inspired by model predictive control (MPC), we introduce an inference…

Machine Learning · Computer Science 2026-05-21 Rohan Deb , Stephen J. Wright , Arindam Banerjee

Policy evaluation estimates the performance of a policy by (1) collecting data from the environment and (2) processing raw data into a meaningful estimate. Due to the sequential nature of reinforcement learning, any improper data-collecting…

Machine Learning · Computer Science 2025-03-21 Shuze Daniel Liu , Claire Chen , Shangtong Zhang

This paper studies off-policy evaluation (OPE) in reinforcement learning with a focus on behavior policy estimation for importance sampling. Prior work has shown empirically that estimating a history-dependent behavior policy can lead to…

Machine Learning · Computer Science 2025-05-29 Hongyi Zhou , Josiah P. Hanna , Jin Zhu , Ying Yang , Chengchun Shi

How to select between policies and value functions produced by different training algorithms in offline reinforcement learning (RL) -- which is crucial for hyperpa-rameter tuning -- is an important open question. Existing approaches based…

Machine Learning · Computer Science 2021-11-04 Siyuan Zhang , Nan Jiang

Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy. In this paper, we study a subtle…

Machine Learning · Computer Science 2022-10-12 Rujie Zhong , Duohan Zhang , Lukas Schäfer , Stefano V. Albrecht , Josiah P. Hanna

Off-policy evaluation (OPE) aims to estimate the performance of hypothetical policies using data generated by a different policy. Because of its huge potential impact in practice, there has been growing research interest in this field.…

Machine Learning · Computer Science 2021-10-27 Yuta Saito , Shunsuke Aihara , Megumi Matsutani , Yusuke Narita

Off-Policy Evaluation (OPE) aims to assess the effectiveness of counterfactual policies using only offline logged data and is often used to identify the top-k promising policies for deployment in online A/B tests. Existing evaluation…

Machine Learning · Computer Science 2024-03-12 Haruka Kiyohara , Ren Kishimoto , Kosuke Kawakami , Ken Kobayashi , Kazuhide Nakata , Yuta Saito

Offline reinforcement learning (RL) addresses the problem of learning a performant policy from a fixed batch of data collected by following some behavior policy. Model-based approaches are particularly appealing in the offline setting since…

Machine Learning · Computer Science 2023-03-06 Jihwan Jeong , Xiaoyu Wang , Michael Gimelfarb , Hyunwoo Kim , Baher Abdulhai , Scott Sanner

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