English
Related papers

Related papers: Offline Constrained RLHF with Multiple Preference …

200 papers

We study online alignment of large language models under misspecified preference feedback, where the observed preference oracle deviates from an ideal but unknown ground-truth oracle. The online LLM alignment problem is a bi-level…

Machine Learning · Computer Science 2026-02-25 Zimeng Li , Mudit Gaur , Vaneet Aggarwal

Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone technique for post-training large language models. While most existing approaches rely on the reverse KL-regularization, recent empirical studies have begun…

Machine Learning · Computer Science 2026-05-11 Di Wu , Chengshuai Shi , Jing Yang , Cong Shen

We consider the problem of offline reinforcement learning from human feedback (RLHF) with pairwise comparisons proposed by Zhu et al. (2023), where the implicit reward is a linear function of an unknown parameter. Given an offline dataset,…

Machine Learning · Computer Science 2026-01-23 Zhirui Chen , Vincent Y. F. Tan

Inverse Reinforcement Learning (IRL) and Reinforcement Learning from Human Feedback (RLHF) are pivotal methodologies in reward learning, which involve inferring and shaping the underlying reward function of sequential decision-making…

Machine Learning · Computer Science 2024-10-16 Kihyun Kim , Jiawei Zhang , Asuman Ozdaglar , Pablo A. Parrilo

We address the challenge of online Reinforcement Learning from Human Feedback (RLHF) with a focus on self-rewarding alignment methods. In online RLHF, obtaining feedback requires interaction with the environment, which can be costly when…

Artificial Intelligence · Computer Science 2024-10-15 Ruijie Xu , Zhihan Liu , Yongfei Liu , Shipeng Yan , Zhaoran Wang , Zhi Zhang , Xuming He

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

Offline reinforcement learning seeks to utilize offline (observational) data to guide the learning of (causal) sequential decision making strategies. The hope is that offline reinforcement learning coupled with function approximation…

Machine Learning · Computer Science 2020-10-23 Ruosong Wang , Dean P. Foster , Sham M. Kakade

Aligning large language models (LLMs) with human preferences is critical to recent advances in generative artificial intelligence. Reinforcement learning from human feedback (RLHF) is widely applied to achieve this objective. A key step in…

Machine Learning · Statistics 2025-01-03 Pangpang Liu , Chengchun Shi , Will Wei Sun

Reinforcement learning (RL) is a control approach that can handle nonlinear stochastic optimal control problems. However, despite the promise exhibited, RL has yet to see marked translation to industrial practice primarily due to its…

Machine Learning · Computer Science 2021-04-15 Elton Pan , Panagiotis Petsagkourakis , Max Mowbray , Dongda Zhang , Antonio del Rio-Chanona

Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world applications. However, obtaining human feedback for preferences…

Machine Learning · Computer Science 2026-04-06 Yiqin Yang , Hao Hu , Yihuan Mao , Jin Zhang , Chengjie Wu , Yuhua Jiang , Xu Yang , Runpeng Xie , Yi Fan , Bo Liu , Yang Gao , Bo Xu , Chongjie Zhang

We study data corruption robustness for reinforcement learning with human feedback (RLHF) in an offline setting. Given an offline dataset of pairs of trajectories along with feedback about human preferences, an $\varepsilon$-fraction of the…

Machine Learning · Computer Science 2024-02-13 Debmalya Mandal , Andi Nika , Parameswaran Kamalaruban , Adish Singla , Goran Radanović

Goal-conditioned reinforcement learning (GCRL) refers to learning general-purpose skills that aim to reach diverse goals. In particular, offline GCRL only requires purely pre-collected datasets to perform training tasks without additional…

Machine Learning · Computer Science 2023-10-13 Hanlin Zhu , Amy Zhang

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

Diffusion models have achieved remarkable success in sequential decision-making by leveraging the highly expressive model capabilities in policy learning. A central problem for learning diffusion policies is to align the policy output with…

Machine Learning · Computer Science 2024-12-17 Zhao Shan , Chenyou Fan , Shuang Qiu , Jiyuan Shi , Chenjia Bai

Preference learning from pairwise feedback is a widely adopted framework in applications such as reinforcement learning with human feedback and recommendations. In many practical settings, however, user interactions are limited or costly,…

Machine Learning · Computer Science 2025-11-03 Jingyuan Liu , Fatemeh Ghaffari , Xuchuang Wang , Xutong Liu , Mohammad Hajiesmaili , Carlee Joe-Wong

Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful approach for aligning generative models, but its reliance on learned reward models makes it vulnerable to mis-specification and reward hacking. Preference-based…

Machine Learning · Computer Science 2026-04-23 Akhil Agnihotri , Rahul Jain , Deepak Ramachandran , Zheng Wen

Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem. To mitigate this issue, a typical solution…

Machine Learning · Computer Science 2023-09-06 Qisen Yang , Shenzhi Wang , Qihang Zhang , Gao Huang , Shiji Song

Offline preference optimization allows fine-tuning large models directly from offline data, and has proved effective in recent alignment practices. We propose generalized preference optimization (GPO), a family of offline losses…

Learning policies from fixed offline datasets is a key challenge to scale up reinforcement learning (RL) algorithms towards practical applications. This is often because off-policy RL algorithms suffer from distributional shift, due to…

Imagine if AI decision-support tools not only complemented our ability to make accurate decisions, but also improved our skills, boosted collaboration, and elevated the joy we derive from our tasks. Despite the potential to optimize a broad…

Human-Computer Interaction · Computer Science 2024-04-16 Zana Buçinca , Siddharth Swaroop , Amanda E. Paluch , Susan A. Murphy , Krzysztof Z. Gajos