English
Related papers

Related papers: Off-policy Evaluation in Infinite-Horizon Reinforc…

200 papers

We introduce a novel doubly-robust (DR) off-policy evaluation (OPE) estimator for Markov decision processes, DRUnknown, designed for situations where both the logging policy and the value function are unknown. The proposed estimator…

Machine Learning · Statistics 2024-04-03 Kyungbok Lee , Myunghee Cho Paik

The problem of on-line off-policy evaluation (OPE) has been actively studied in the last decade due to its importance both as a stand-alone problem and as a module in a policy improvement scheme. However, most Temporal Difference (TD) based…

Machine Learning · Statistics 2017-02-24 Assaf Hallak , Shie Mannor

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

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 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

Learning the value function of a given policy (target policy) from the data samples obtained from a different policy (behavior policy) is an important problem in Reinforcement Learning (RL). This problem is studied under the setting of…

Machine Learning · Computer Science 2019-11-14 Raghuram Bharadwaj Diddigi , Chandramouli Kamanchi , Shalabh Bhatnagar

We show that the popular reinforcement learning (RL) strategy of estimating the state-action value (Q-function) by minimizing the mean squared Bellman error leads to a regression problem with confounding, the inputs and output noise being…

Machine Learning · Computer Science 2022-12-01 Yutian Chen , Liyuan Xu , Caglar Gulcehre , Tom Le Paine , Arthur Gretton , Nando de Freitas , Arnaud Doucet

We consider off-policy evaluation (OPE) of deterministic target policies for reinforcement learning (RL) in environments with continuous action spaces. While it is common to use importance sampling for OPE, it suffers from high variance…

Machine Learning · Computer Science 2024-05-30 Haanvid Lee , Tri Wahyu Guntara , Jongmin Lee , Yung-Kyun Noh , Kee-Eung Kim

Off-Policy Evaluation (OPE) is employed to assess the potential impact of a hypothetical policy using logged contextual bandit feedback, which is crucial in areas such as personalized medicine and recommender systems, where online…

Machine Learning · Computer Science 2025-07-10 Yuqi Bai , Ziyu Zhao , Chenxin Lyu , Minqin Zhu , Kun Kuang

Off-policy prediction -- learning the value function for one policy from data generated while following another policy -- is one of the most challenging subproblems in reinforcement learning. This paper presents empirical results with…

Machine Learning · Computer Science 2021-06-15 Sina Ghiassian , Richard S. Sutton

We study the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of a policy from the data generated by another policy(ies). In particular, we focus on the doubly robust (DR)…

Artificial Intelligence · Computer Science 2018-05-25 Mehrdad Farajtabar , Yinlam Chow , Mohammad Ghavamzadeh

Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same time minimizing the deviation from the behavior policy so as to…

Machine Learning · Computer Science 2021-10-13 Ilya Kostrikov , Ashvin Nair , Sergey Levine

Offline reinforcement learning promises policy improvement from logged interaction data alone, yet state-of-the-art algorithms remain vulnerable to value over-estimation and to violations of domain knowledge such as monotonicity or…

Systems and Control · Electrical Eng. & Systems 2025-06-18 Ali Baheri

Matching users based on mutual preferences is a fundamental aspect of services driven by reciprocal recommendations, such as job search and dating applications. Although A/B tests remain the gold standard for evaluating new policies in…

Machine Learning · Computer Science 2025-07-21 Yudai Hayashi , Shuhei Goda , Yuta Saito

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

Infinite horizon off-policy policy evaluation is a highly challenging task due to the excessively large variance of typical importance sampling (IS) estimators. Recently, Liu et al. (2018a) proposed an approach that significantly reduces…

Machine Learning · Computer Science 2019-10-17 Ziyang Tang , Yihao Feng , Lihong Li , Dengyong Zhou , Qiang Liu

This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history…

Machine Learning · Computer Science 2020-02-25 Yaqi Duan , Mengdi Wang

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

Policy gradient methods are widely used for control in reinforcement learning, particularly for the continuous action setting. There have been a host of theoretically sound algorithms proposed for the on-policy setting, due to the existence…

Machine Learning · Computer Science 2019-06-21 Ehsan Imani , Eric Graves , Martha White

For the problem of task-agnostic reinforcement learning (RL), an agent first collects samples from an unknown environment without the supervision of reward signals, then is revealed with a reward and is asked to compute a corresponding…

Machine Learning · Computer Science 2022-03-16 Jingfeng Wu , Vladimir Braverman , Lin F. Yang