English
Related papers

Related papers: A General Framework for Off-Policy Learning with P…

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

In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy.…

Machine Learning · Computer Science 2022-11-04 Jie Wang , Rui Gao , Hongyuan Zha

Offline contextual bandits allow one to learn policies from historical/offline data without requiring online interaction. However, offline policy optimization that maximizes overall expected rewards can unintentionally amplify the reward…

Machine Learning · Computer Science 2026-01-07 Yihong Guo , Junjie Luo , Guodong Gao , Ritu Agarwal , Anqi Liu

Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment. However, in many tasks the…

Machine Learning · Computer Science 2022-02-18 Daniel Shin , Daniel S. Brown , Anca D. Dragan

Offline preference-based reinforcement learning (RL), which focuses on optimizing policies using human preferences between pairs of trajectory segments selected from an offline dataset, has emerged as a practical avenue for RL applications.…

Machine Learning · Computer Science 2024-07-08 Chen-Xiao Gao , Shengjun Fang , Chenjun Xiao , Yang Yu , Zongzhang Zhang

Off-policy evaluation (OPE) in reinforcement learning is an important problem in settings where experimentation is limited, such as education and healthcare. But, in these very same settings, observed actions are often confounded by…

Machine Learning · Computer Science 2020-07-29 Andrew Bennett , Nathan Kallus , Lihong Li , Ali Mousavi

Offline reinforcement learning (RL) methods can generally be categorized into two types: RL-based and Imitation-based. RL-based methods could in principle enjoy out-of-distribution generalization but suffer from erroneous off-policy…

Machine Learning · Computer Science 2023-04-06 Haoran Xu , Li Jiang , Jianxiong Li , Xianyuan Zhan

Off-policy evaluation (OPE) is to evaluate a target policy with data generated by other policies. Most previous OPE methods focus on precisely estimating the true performance of a policy. We observe that in many applications, (1) the end…

Machine Learning · Computer Science 2022-06-22 Yue Jin , Yue Zhang , Tao Qin , Xudong Zhang , Jian Yuan , Houqiang Li , Tie-Yan Liu

Off-policy evaluation (OPE) is the problem of estimating the value of a target policy from samples obtained via different policies. Recently, applying OPE methods for bandit problems has garnered attention. For the theoretical guarantees of…

Machine Learning · Computer Science 2020-10-26 Masahiro Kato , Kenshi Abe , Kaito Ariu , Shota Yasui

Reinforcement learning (RL) is increasingly used to align large language models (LLMs). Off-policy methods offer greater implementation simplicity and data efficiency than on-policy techniques, but often result in suboptimal performance. In…

Machine Learning · Computer Science 2025-12-01 Charles Arnal , Gaëtan Narozniak , Vivien Cabannes , Yunhao Tang , Julia Kempe , Remi Munos

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

The off-policy learning paradigm allows for recommender systems and general ranking applications to be framed as decision-making problems, where we aim to learn decision policies that optimize an unbiased offline estimate of an online…

Machine Learning · Computer Science 2024-08-15 Shashank Gupta , Olivier Jeunen , Harrie Oosterhuis , Maarten de Rijke

This study focuses on the topic of offline preference-based reinforcement learning (PbRL), a variant of conventional reinforcement learning that dispenses with the need for online interaction or specification of reward functions. Instead,…

Machine Learning · Computer Science 2023-06-12 Yachen Kang , Diyuan Shi , Jinxin Liu , Li He , Donglin Wang

Offline reinforcement learning (RL) methods aim to learn optimal policies with access only to trajectories in a fixed dataset. Policy constraint methods formulate policy learning as an optimization problem that balances maximizing reward…

Machine Learning · Computer Science 2025-03-04 Padmanaba Srinivasan , William Knottenbelt

In safe offline reinforcement learning (RL), the objective is to develop a policy that maximizes cumulative rewards while strictly adhering to safety constraints, utilizing only offline data. Traditional methods often face difficulties in…

Machine Learning · Computer Science 2026-02-11 Prajwal Koirala , Zhanhong Jiang , Soumik Sarkar , Cody Fleming

Offline reinforcement learning can enable policy learning from pre-collected, sub-optimal datasets without online interactions. This makes it ideal for real-world robots and safety-critical scenarios, where collecting online data or expert…

Robotics · Computer Science 2025-08-07 Sreyas Venkataraman , Yufei Wang , Ziyu Wang , Navin Sriram Ravie , Zackory Erickson , David Held

Preference learning (PL) with large language models (LLMs) aims to align the LLMs' generations with human preferences. Previous work on reinforcement learning from human feedback (RLHF) has demonstrated promising results in in-distribution…

Machine Learning · Computer Science 2024-06-11 Chen Jia

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

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

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