English
Related papers

Related papers: Corruption Robust Offline Reinforcement Learning w…

200 papers

Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from…

This paper studies the alignment process of generative models with Reinforcement Learning from Human Feedback (RLHF). We first identify the primary challenges of existing popular methods like offline PPO and offline DPO as lacking in…

Machine Learning · Computer Science 2024-05-02 Wei Xiong , Hanze Dong , Chenlu Ye , Ziqi Wang , Han Zhong , Heng Ji , Nan Jiang , Tong Zhang

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning Large Language Models (LLMs) with human values. However, RLHF has been continuously challenged by its high complexity in implementation and computation consumption,…

Machine Learning · Computer Science 2026-03-24 Yuhao Du , Zhuo Li , Pengyu Cheng , Zhihong Chen , Yuejiao Xie , Xiang Wan , Anningzhe Gao

Reinforcement Learning from Human Feedback (RLHF) is currently the leading approach for aligning large language models with human preferences. Typically, these models rely on extensive offline preference datasets for training. However,…

Machine Learning · Computer Science 2024-12-17 Avinandan Bose , Zhihan Xiong , Aadirupa Saha , Simon Shaolei Du , Maryam Fazel

Reinforcement Learning from Human Feedback (RLHF) is central in aligning large language models (LLMs) with human values and expectations. However, the process remains susceptible to governance challenges, including evaluator bias,…

Computers and Society · Computer Science 2025-04-22 Dana Alsagheer , Abdulrahman Kamal , Mohammad Kamal , Weidong Shi

Distributionally robust offline reinforcement learning (RL) aims to find a policy that performs the best under the worst environment within an uncertainty set using an offline dataset collected from a nominal model. While recent advances in…

Machine Learning · Computer Science 2025-01-07 Ruiquan Huang , Yingbin Liang , Jing Yang

We initiate the study of multi-stage episodic reinforcement learning under adversarial corruptions in both the rewards and the transition probabilities of the underlying system extending recent results for the special case of stochastic…

Machine Learning · Computer Science 2023-11-02 Thodoris Lykouris , Max Simchowitz , Aleksandrs Slivkins , Wen Sun

We consider the hybrid reinforcement learning setting where the agent has access to both offline data and online interactive access. While Reinforcement Learning (RL) research typically assumes offline data contains complete action, reward…

Machine Learning · Computer Science 2024-06-12 Yuda Song , J. Andrew Bagnell , Aarti Singh

We study episodic reinforcement learning under unknown adversarial corruptions in both the rewards and the transition probabilities of the underlying system. We propose new algorithms which, compared to the existing results in (Lykouris et…

Machine Learning · Computer Science 2021-03-09 Yifang Chen , Simon S. Du , Kevin Jamieson

Collecting high-quality preference datasets for reinforcement learning from human feedback (RLHF) is resource-intensive and challenging. As a result, researchers often train reward models on extensive offline datasets which aggregate…

Machine Learning · Computer Science 2024-12-17 Shambhavi Krishna , Aishwarya Sahoo

Reinforcement Learning from Human Feedback (RLHF) assumes annotator preferences reflect stable internal states. We challenge this through three experiments spanning the preference pipeline. In a human choice blindness study, 91% of…

Computation and Language · Computer Science 2026-03-10 Wenbin Wu

Offline reinforcement learning (RL) provides a promising direction to exploit massive amount of offline data for complex decision-making tasks. Due to the distribution shift issue, current offline RL algorithms are generally designed to be…

Machine Learning · Computer Science 2022-10-25 Rui Yang , Chenjia Bai , Xiaoteng Ma , Zhaoran Wang , Chongjie Zhang , Lei Han

Reward inference (learning a reward model from human preferences) is a critical intermediate step in the Reinforcement Learning from Human Feedback (RLHF) pipeline for fine-tuning Large Language Models (LLMs). In practice, RLHF faces…

Machine Learning · Computer Science 2025-03-04 Qining Zhang , Lei Ying

Reinforcement Learning with Human Feedback (RLHF) is at the core of fine-tuning methods for generative AI models for language and images. Such feedback is often sought as rank or preference feedback from human raters, as opposed to…

Machine Learning · Computer Science 2025-05-19 Akhil Agnihotri , Rahul Jain , Deepak Ramachandran , Zheng Wen

In this paper, we study the offline and online settings of reinforcement learning from human feedback (RLHF) with KL-regularization -- a widely used objective function in large language model alignment -- under the $\epsilon$ local…

Machine Learning · Computer Science 2025-10-16 Yulian Wu , Rushil Thareja , Praneeth Vepakomma , Francesco Orabona

In today's era of big data, robust least-squares regression becomes a more challenging problem when considering the adversarial corruption along with explosive growth of datasets. Traditional robust methods can handle the noise but suffer…

Data Structures and Algorithms · Computer Science 2017-10-04 Xuchao Zhang , Liang Zhao , Arnold P. Boedihardjo , Chang-Tien Lu

We study the problem of learning the optimal policy in a discounted, infinite-horizon reinforcement learning (RL) setting in the presence of adversarially corrupted rewards. To address this problem, we develop a novel robust variant of the…

Machine Learning · Computer Science 2026-05-22 Sreejeet Maity , Aritra Mitra

With the development of large language models (LLMs), striking a balance between the performance and safety of AI systems has never been more critical. However, the inherent tension between the objectives of helpfulness and harmlessness…

Artificial Intelligence · Computer Science 2023-10-20 Josef Dai , Xuehai Pan , Ruiyang Sun , Jiaming Ji , Xinbo Xu , Mickel Liu , Yizhou Wang , Yaodong Yang

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

We develop a model selection approach to tackle reinforcement learning with adversarial corruption in both transition and reward. For finite-horizon tabular MDPs, without prior knowledge on the total amount of corruption, our algorithm…

Machine Learning · Computer Science 2024-12-31 Chen-Yu Wei , Christoph Dann , Julian Zimmert