English
Related papers

Related papers: Leveraging Factored Action Spaces for Off-Policy E…

200 papers

When observed decisions depend only on observed features, off-policy policy evaluation (OPE) methods for sequential decision making problems can estimate the performance of evaluation policies before deploying them. This assumption is…

Machine Learning · Statistics 2020-03-13 Hongseok Namkoong , Ramtin Keramati , Steve Yadlowsky , Emma Brunskill

We consider off-policy evaluation (OPE) in Partially Observable Markov Decision Processes, where the evaluation policy depends only on observable variables but the behavior policy depends on latent states (Tennenholtz et al. (2020a)). Prior…

Machine Learning · Computer Science 2021-09-23 Yash Nair , Nan Jiang

We study off-policy evaluation (OPE) in the problem of slate contextual bandits where a policy selects multi-dimensional actions known as slates. This problem is widespread in recommender systems, search engines, marketing, to medical…

Machine Learning · Statistics 2024-02-20 Haruka Kiyohara , Masahiro Nomura , Yuta Saito

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

Bootstrapping provides a flexible and effective approach for assessing the quality of batch reinforcement learning, yet its theoretical property is less understood. In this paper, we study the use of bootstrapping in off-policy evaluation…

Machine Learning · Statistics 2022-05-24 Botao Hao , Xiang Ji , Yaqi Duan , Hao Lu , Csaba Szepesvári , Mengdi Wang

We consider the problem of off-policy evaluation in Markov decision processes. Off-policy evaluation is the task of evaluating the expected return of one policy with data generated by a different, behavior policy. Importance sampling is a…

Machine Learning · Computer Science 2019-05-13 Josiah P. Hanna , Scott Niekum , Peter Stone

Off-policy evaluation (OPE) estimates the value of a target treatment policy (e.g., a recommender system) using data collected by a different logging policy. It enables high-stakes experimentation without live deployment, yet in practice…

Machine Learning · Statistics 2026-05-18 Connor Douglas , Joel Persson , Foster Provost

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

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

In this work, we consider the problem of estimating a behaviour policy for use in Off-Policy Policy Evaluation (OPE) when the true behaviour policy is unknown. Via a series of empirical studies, we demonstrate how accurate OPE is strongly…

Machine Learning · Computer Science 2018-07-11 Aniruddh Raghu , Omer Gottesman , Yao Liu , Matthieu Komorowski , Aldo Faisal , Finale Doshi-Velez , Emma Brunskill

When learning policies for real-world domains, two important questions arise: (i) how to efficiently use pre-collected off-policy, non-optimal behavior data; and (ii) how to mediate among different competing objectives and constraints. We…

Machine Learning · Computer Science 2019-03-22 Hoang M. Le , Cameron Voloshin , Yisong Yue

When decision-makers can directly intervene, policy evaluation algorithms give valid causal estimates. In off-policy evaluation (OPE), there may exist unobserved variables that both impact the dynamics and are used by the unknown behavior…

Machine Learning · Computer Science 2022-04-05 David Bruns-Smith

Off-policy policy evaluation (OPE) estimates the outcome of a new policy using historical data collected from a different policy. However, existing OPE methods cannot handle cases when the new policy introduces novel actions. This issue…

Artificial Intelligence · Computer Science 2025-02-04 Hyunji Nam , Allen Nie , Ge Gao , Vasilis Syrgkanis , Emma Brunskill

Methods for sequential decision-making are often built upon a foundational assumption that the underlying decision process is stationary. This limits the application of such methods because real-world problems are often subject to changes…

Machine Learning · Computer Science 2023-01-26 Yash Chandak , Shiv Shankar , Nathaniel D. Bastian , Bruno Castro da Silva , Emma Brunskil , Philip S. Thomas

Off-policy evaluation (OPE) is crucial for assessing a target policy's impact offline before its deployment. However, achieving accurate OPE in large state spaces remains challenging. This paper studies state abstractions -- originally…

Machine Learning · Statistics 2025-03-05 Meiling Hao , Pingfan Su , Liyuan Hu , Zoltan Szabo , Qingyuan Zhao , Chengchun Shi

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 consider off-policy evaluation (OPE) in Partially Observable Markov Decision Processes (POMDPs), where the evaluation policy depends only on observable variables and the behavior policy depends on unobservable latent variables. Existing…

Machine Learning · Computer Science 2022-06-17 Chengchun Shi , Masatoshi Uehara , Jiawei Huang , Nan Jiang

We study the off-policy evaluation (OPE) problem in an infinite-horizon Markov decision process with continuous states and actions. We recast the $Q$-function estimation into a special form of the nonparametric instrumental variables (NPIV)…

Statistics Theory · Mathematics 2022-06-28 Xiaohong Chen , Zhengling Qi

This work aims to study off-policy evaluation (OPE) under scenarios where two key reinforcement learning (RL) assumptions -- temporal stationarity and individual homogeneity are both violated. To handle the ``double inhomogeneities", we…

Methodology · Statistics 2024-08-20 Zeyu Bian , Chengchun Shi , Zhengling Qi , Lan Wang

A variety of theoretically-sound policy gradient algorithms exist for the on-policy setting due to the policy gradient theorem, which provides a simplified form for the gradient. The off-policy setting, however, has been less clear due to…

Machine Learning · Computer Science 2023-04-17 Eric Graves , Ehsan Imani , Raksha Kumaraswamy , Martha White