English
Related papers

Related papers: Conformal Off-Policy Evaluation in Markov Decision…

200 papers

We study offline reinforcement learning problems with a long-run average reward objective. The state-action pairs generated by any fixed behavioral policy thus follow a Markov chain, and the {\em empirical} state-action-next-state…

Optimization and Control · Mathematics 2025-03-18 Mengmeng Li , Daniel Kuhn , Tobias Sutter

Off-Policy evaluation (OPE) is concerned with evaluating a new target policy using offline data generated by a potentially different behavior policy. It is critical in a number of sequential decision making problems ranging from healthcare…

Machine Learning · Statistics 2023-01-02 Yang Xu , Chengchun Shi , Shikai Luo , Lan Wang , Rui Song

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

This paper addresses the problem of policy selection in domains with abundant logged data, but with a restricted interaction budget. Solving this problem would enable safe evaluation and deployment of offline reinforcement learning policies…

Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability…

Machine Learning · Computer Science 2025-06-05 Yaru Hao , Li Dong , Xun Wu , Shaohan Huang , Zewen Chi , Furu Wei

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

In applying reinforcement learning (RL) to high-stakes domains, quantitative and qualitative evaluation using observational data can help practitioners understand the generalization performance of new policies. However, this type of…

Machine Learning · Computer Science 2023-10-27 Shengpu Tang , Jenna Wiens

Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed for online learning struggle in the offline setting as they…

Machine Learning · Computer Science 2025-03-18 Natinael Solomon Neggatu , Jeremie Houssineau , Giovanni Montana

The goal of off-policy evaluation (OPE) is to evaluate a new policy using historical data obtained via a behavior policy. However, because the contextual bandit algorithm updates the policy based on past observations, the samples are not…

Machine Learning · Computer Science 2020-10-27 Masahiro Kato , Yusuke Kaneko

Modern decision-making systems, from robots to web recommendation engines, are expected to adapt: to user preferences, changing circumstances or even new tasks. Yet, it is still uncommon to deploy a dynamically learning agent (rather than a…

Machine Learning · Computer Science 2022-11-15 Shengpu Tang , Felipe Vieira Frujeri , Dipendra Misra , Alex Lamb , John Langford , Paul Mineiro , Sebastian Kochman

In offline-to-online reinforcement learning (O2O-RL), policies are first safely trained offline using previously collected datasets and then further fine-tuned for tasks via limited online interactions. In a typical O2O-RL pipeline,…

Machine Learning · Computer Science 2026-05-07 Alper Kamil Bozkurt , Xiaoan Xu , Shangtong Zhang , Miroslav Pajic , Yuichi Motai

Offline reinforcement learning provides a viable approach to obtain advanced control strategies for dynamical systems, in particular when direct interaction with the environment is not available. In this paper, we introduce a conceptual…

Machine Learning · Computer Science 2024-01-04 Marc Weber , Phillip Swazinna , Daniel Hein , Steffen Udluft , Volkmar Sterzing

Contextual bandit algorithms are ubiquitous tools for active sequential experimentation in healthcare and the tech industry. They involve online learning algorithms that adaptively learn policies over time to map observed contexts $X_t$ to…

Methodology · Statistics 2024-08-19 Ian Waudby-Smith , Lili Wu , Aaditya Ramdas , Nikos Karampatziakis , Paul Mineiro

This work focuses on off-policy evaluation (OPE) with function approximation in infinite-horizon undiscounted Markov decision processes (MDPs). For MDPs that are ergodic and linear (i.e. where rewards and dynamics are linear in some known…

Machine Learning · Computer Science 2020-06-24 Nevena Lazic , Dong Yin , Mehrdad Farajtabar , Nir Levine , Dilan Gorur , Chris Harris , Dale Schuurmans

We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new…

Machine Learning · Computer Science 2019-12-12 Riashat Islam , Raihan Seraj , Samin Yeasar Arnob , Doina Precup

We consider off-policy evaluation (OPE), which evaluates the performance of a new policy from observed data collected from previous experiments, without requiring the execution of the new policy. This finds important applications in areas…

Machine Learning · Computer Science 2020-08-18 Yihao Feng , Tongzheng Ren , Ziyang Tang , Qiang Liu

Reinforcement learning (RL) can be used to learn treatment policies and aid decision making in healthcare. However, given the need for generalization over complex state/action spaces, the incorporation of function approximators (e.g., deep…

Machine Learning · Computer Science 2021-07-26 Shengpu Tang , Jenna Wiens

A key problem in off-policy Reinforcement Learning (RL) is the mismatch, or distribution shift, between the dataset and the distribution over states and actions visited by the learned policy. This problem is exacerbated in the fully offline…

Machine Learning · Computer Science 2023-11-28 Melrose Roderick , Gaurav Manek , Felix Berkenkamp , J. Zico Kolter

We study the problem of estimating the distribution of the return of a policy using an offline dataset that is not generated from the policy, i.e., distributional offline policy evaluation (OPE). We propose an algorithm called Fitted…

Machine Learning · Computer Science 2024-01-01 Runzhe Wu , Masatoshi Uehara , Wen Sun

Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…

Machine Learning · Computer Science 2026-01-06 Alexander W. Goodall , Edwin Hamel-De le Court , Francesco Belardinelli