English
Related papers

Related papers: Sample Complexity of Preference-Based Nonparametri…

200 papers

Data selection is a critical aspect of Reinforcement Learning with Verifiable Rewards (RLVR) for enhancing the reasoning capabilities of large language models (LLMs). Current data selection methods are largely heuristic-based, lacking…

Machine Learning · Computer Science 2026-04-16 Erle Zhu , Dazhi Jiang , Yuan Wang , Xujun Li , Jiale Cheng , Yuxian Gu , Yilin Niu , Aohan Zeng , Jie Tang , Minlie Huang , Hongning Wang

Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment. These are critical shortcomings for applying RL to real-world problems where…

Aligning Large Language Models (LLMs) with human preferences is crucial, but standard methods like Reinforcement Learning from Human Feedback (RLHF) are often complex and unstable. In this work, we propose a new, simpler approach that…

Machine Learning · Computer Science 2026-01-27 Saeed Najafi , Alona Fyshe

We offer a theoretical characterization of off-policy evaluation (OPE) in reinforcement learning using function approximation for marginal importance weights and $q$-functions when these are estimated using recent minimax methods. Under…

Machine Learning · Computer Science 2022-07-26 Masatoshi Uehara , Masaaki Imaizumi , Nan Jiang , Nathan Kallus , Wen Sun , Tengyang Xie

Reinforcement learning from human feedback (RLHF) has emerged as a central framework for aligning large language models (LLMs) with human preferences. Despite its practical success, RLHF raises fundamental statistical questions because it…

Machine Learning · Statistics 2026-04-06 Pangpang Liu , Chengchun Shi , Will Wei Sun

Reinforcement learning from human feedback (RLHF) has evolved to be one of the main methods for fine-tuning large language models (LLMs). However, existing RLHF methods are non-robust, and their performance deteriorates if the downstream…

Machine Learning · Computer Science 2025-03-04 Debmalya Mandal , Paulius Sasnauskas , Goran Radanovic

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

Off-policy evaluation (OPE) methods aim to estimate the value of a new reinforcement learning (RL) policy prior to deployment. Recent advances have shown that leveraging auxiliary datasets, such as those synthesized by generative models,…

Machine Learning · Computer Science 2025-07-29 Aishwarya Mandyam , Jason Meng , Ge Gao , Jiankai Sun , Mac Schwager , Barbara E. Engelhardt , Emma Brunskill

Learning from preference feedback has emerged as an essential step for improving the generation quality and performance of modern language models (LMs). Despite its widespread use, the way preference-based learning is applied varies wildly,…

Computation and Language · Computer Science 2024-10-10 Hamish Ivison , Yizhong Wang , Jiacheng Liu , Zeqiu Wu , Valentina Pyatkin , Nathan Lambert , Noah A. Smith , Yejin Choi , Hannaneh Hajishirzi

Value function estimation is an indispensable subroutine in reinforcement learning, which becomes more challenging in the offline setting. In this paper, we propose Hybrid Value Estimation (HVE) to reduce value estimation error, which…

Machine Learning · Computer Science 2022-06-07 Xue-Kun Jin , Xu-Hui Liu , Shengyi Jiang , Yang Yu

Preference-based reinforcement learning (PbRL) is an approach that enables RL agents to learn from preference, which is particularly useful when formulating a reward function is challenging. Existing PbRL methods generally involve a…

Machine Learning · Computer Science 2023-10-30 Gaon An , Junhyeok Lee , Xingdong Zuo , Norio Kosaka , Kyung-Min Kim , Hyun Oh Song

Aligning large language models with multiple human expectations and values is crucial for ensuring that they adequately serve a variety of user needs. To this end, offline multiobjective alignment algorithms such as the Rewards-in-Context…

Machine Learning · Computer Science 2026-01-01 Haoran Gu , Handing Wang , Yi Mei , Mengjie Zhang , Yaochu Jin

Off-policy evaluation (OPE) is the problem of estimating the value of a target policy using historical data collected under a different logging policy. OPE methods typically assume overlap between the target and logging policy, enabling…

Methodology · Statistics 2024-03-12 Samir Khan , Martin Saveski , Johan Ugander

Personalizing large language models (LLMs) to accommodate diverse user preferences is essential for enhancing alignment and user satisfaction. Traditional reinforcement learning from human feedback (RLHF) approaches often rely on monolithic…

Machine Learning · Computer Science 2025-04-22 Avinandan Bose , Zhihan Xiong , Yuejie Chi , Simon Shaolei Du , Lin Xiao , Maryam Fazel

Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for large language model (LLM) alignment. This paper studies the setting of online RLHF and focus on improving sample efficiency. All existing algorithms…

Machine Learning · Computer Science 2025-09-29 Mingyu Chen , Yiding Chen , Wen Sun , Xuezhou Zhang

Offline reinforcement learning aims to utilize datasets of previously gathered environment-action interaction records to learn a policy without access to the real environment. Recent work has shown that offline reinforcement learning can be…

Machine Learning · Computer Science 2023-08-30 Hanhan Zhou , Tian Lan , Vaneet Aggarwal

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 the classical Reinforcement Learning from Human Feedback (RLHF) framework, Proximal Policy Optimization (PPO) is employed to learn from sparse, sentence-level rewards -- a challenging scenario in traditional deep reinforcement learning.…

Machine Learning · Computer Science 2025-05-22 Han Zhong , Zikang Shan , Guhao Feng , Wei Xiong , Xinle Cheng , Li Zhao , Di He , Jiang Bian , Liwei Wang

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

Off-policy evaluation (OPE) and off-policy learning (OPL) are foundational for decision-making in offline contextual bandits. Recent advances in OPL primarily optimize OPE estimators with improved statistical properties, assuming that…

Machine Learning · Statistics 2025-09-04 Imad Aouali , Otmane Sakhi