English
Related papers

Related papers: Learning Action Embeddings for Off-Policy Evaluati…

200 papers

Offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. This problem setting offers the promise of utilizing such datasets to acquire policies without any…

Machine Learning · Computer Science 2020-11-24 Tianhe Yu , Garrett Thomas , Lantao Yu , Stefano Ermon , James Zou , Sergey Levine , Chelsea Finn , Tengyu Ma

We study the problem of Safe Policy Improvement (SPI) under constraints in the offline Reinforcement Learning (RL) setting. We consider the scenario where: (i) we have a dataset collected under a known baseline policy, (ii) multiple reward…

Machine Learning · Computer Science 2021-11-01 Harsh Satija , Philip S. Thomas , Joelle Pineau , Romain Laroche

Training practical agents usually involve offline and online reinforcement learning (RL) to balance the policy's performance and interaction costs. In particular, online fine-tuning has become a commonly used method to correct the erroneous…

Machine Learning · Computer Science 2023-06-07 Qisen Yang , Shenzhi Wang , Matthieu Gaetan Lin , Shiji Song , Gao Huang

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

On-Policy Distillation (OPD) has gained wide attraction as an LLM post-training paradigm due to its effectiveness in improving capabilities without introducing model distribution drift, and consequently, regression in general tasks.…

Artificial Intelligence · Computer Science 2026-05-25 Aristotelis Lazaridis , Dylan Bates , Aman Sharma , Brian King , Vincent Lu , Jack FitzGerald

While the classic off-policy evaluation (OPE) literature commonly assumes decision time points to be evenly spaced for simplicity, in many real-world scenarios, such as those involving user-initiated visits, decisions are made at…

Methodology · Statistics 2024-09-17 Xin Chen , Wenbin Lu , Shu Yang , Dipankar Bandyopadhyay

Estimation of importance sampling weights for off-policy evaluation of contextual bandits often results in imbalance - a mismatch between the desired and the actual distribution of state-action pairs after weighting. In this work we present…

Machine Learning · Computer Science 2020-03-06 Arjun Sondhi , David Arbour , Drew Dimmery

We explore off-policy evaluation and learning (OPE/L) in contextual combinatorial bandits (CCB), where a policy selects a subset in the action space. For example, it might choose a set of furniture pieces (a bed and a drawer) from available…

Machine Learning · Statistics 2024-08-22 Tatsuhiro Shimizu , Koichi Tanaka , Ren Kishimoto , Haruka Kiyohara , Masahiro Nomura , Yuta Saito

A critical need for industrial recommender systems is the ability to evaluate recommendation policies offline, before deploying them to production. Unfortunately, widely used off-policy evaluation methods either make strong assumptions…

Machine Learning · Computer Science 2022-10-19 Alexander Buchholz , Ben London , Giuseppe di Benedetto , Thorsten Joachims

Learning complex policies with Reinforcement Learning (RL) is often hindered by instability and slow convergence, a problem exacerbated by the difficulty of reward engineering. Imitation Learning (IL) from expert demonstrations bypasses…

Machine Learning · Computer Science 2026-05-19 Sayambhu Sen , Shalabh Bhatnagar

Imitation learning is a data-driven approach to learning policies from expert behavior, but it is prone to unreliable outcomes in out-of-sample (OOS) regions. While previous research relying on stable dynamical systems guarantees…

Machine Learning · Computer Science 2025-03-27 Amin Abyaneh , Mahrokh G. Boroujeni , Hsiu-Chin Lin , Giancarlo Ferrari-Trecate

Model-based methods have recently shown great potential for off-policy evaluation (OPE); offline trajectories induced by behavioral policies are fitted to transitions of Markov decision processes (MDPs), which are used to rollout simulated…

Machine Learning · Computer Science 2023-02-06 Qitong Gao , Ge Gao , Min Chi , Miroslav Pajic

This work studies the problem of batch off-policy evaluation for Reinforcement Learning in partially observable environments. Off-policy evaluation under partial observability is inherently prone to bias, with risk of arbitrarily large…

Machine Learning · Computer Science 2019-11-26 Guy Tennenholtz , Shie Mannor , Uri Shalit

We study off-policy learning (OPL) in contextual bandits, which plays a key role in a wide range of real-world applications such as recommendation systems and online advertising. Typical OPL in contextual bandits assumes an unconstrained…

Machine Learning · Computer Science 2026-05-19 Koichi Tanaka , Ren Kishimoto , Bushun Kawagishi , Yusuke Narita , Yasuo Yamamoto , Nobuyuki Shimizu , Yuta Saito

Evaluating off-policy decisions using batch data poses significant challenges due to limited sample sizes leading to high variance. To improve Off-Policy Evaluation (OPE), we must identify and address the sources of this variance. Recent…

Machine Learning · Statistics 2024-12-02 Ritam Majumdar , Jack Teversham , Sonali Parbhoo

Off-policy model-free deep reinforcement learning methods using previously collected data can improve sample efficiency over on-policy policy gradient techniques. On the other hand, on-policy algorithms are often more stable and easier to…

Machine Learning · Computer Science 2017-06-02 Shixiang Gu , Timothy Lillicrap , Zoubin Ghahramani , Richard E. Turner , Bernhard Schölkopf , Sergey Levine

Off-policy evaluation (OPE) estimates the performance of a target policy using offline data collected from a behavior policy, and is crucial in domains such as robotics or healthcare where direct interaction with the environment is costly…

We consider off-policy policy evaluation with function approximation (FA) in average-reward MDPs, where the goal is to estimate both the reward rate and the differential value function. For this problem, bootstrapping is necessary and,…

Machine Learning · Computer Science 2022-10-19 Shangtong Zhang , Yi Wan , Richard S. Sutton , Shimon Whiteson

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

In many settings, a decision-maker wishes to learn a rule, or policy, that maps from observable characteristics of an individual to an action. Examples include selecting offers, prices, advertisements, or emails to send to consumers, as…

Machine Learning · Statistics 2018-11-20 Zhengyuan Zhou , Susan Athey , Stefan Wager