English
Related papers

Related papers: Online Bandit Learning with Offline Preference Dat…

200 papers

Reinforcement Learning from Human Feedback (RLHF) is a widely adopted approach for aligning large language models with human values. However, RLHF relies on a reward model that is trained with a limited amount of human preference data,…

Machine Learning · Computer Science 2024-10-23 Shun Zhang , Zhenfang Chen , Sunli Chen , Yikang Shen , Zhiqing Sun , Chuang Gan

Offline reinforcement learning (RL) is crucial for real-world applications where exploration can be costly or unsafe. However, offline learned policies are often suboptimal, and further online fine-tuning is required. In this paper, we…

Machine Learning · Computer Science 2024-06-03 Hao Hu , Yiqin Yang , Jianing Ye , Chengjie Wu , Ziqing Mai , Yujing Hu , Tangjie Lv , Changjie Fan , Qianchuan Zhao , Chongjie Zhang

Preference-based reinforcement learning (RL) has emerged as a new field in robot learning, where humans play a pivotal role in shaping robot behavior by expressing preferences on different sequences of state-action pairs. However,…

Robotics · Computer Science 2024-02-26 Simon Holk , Daniel Marta , Iolanda Leite

Interactive preference learning systems infer human preferences by presenting queries as pairs of options and collecting binary choices. Although binary choices are simple and widely used, they provide limited information about preference…

Machine Learning · Computer Science 2025-01-03 Shen Li , Yuyang Zhang , Zhaolin Ren , Claire Liang , Na Li , Julie A. Shah

Reinforcement Learning from Human Feedback (RLHF) is a widely used approach to align large-scale AI systems with human values. However, RLHF typically assumes a single, universal reward, which overlooks diverse preferences and limits…

Machine Learning · Computer Science 2026-03-16 Gihoon Kim , Euntai Kim

A critical component of the current generation of language models is preference alignment, which aims to precisely control the model's behavior to meet human needs and values. The most notable among such methods is Reinforcement Learning…

Artificial Intelligence · Computer Science 2024-10-22 Oh Joon Kwon , Daiki E. Matsunaga , Kee-Eung Kim

Reinforcement Learning with Human Feedback (RLHF) has been demonstrated to significantly enhance the performance of large language models (LLMs) by aligning their outputs with desired human values through instruction tuning. However, RLHF…

Computation and Language · Computer Science 2024-03-06 Zhang Ze Yu , Lau Jia Jaw , Zhang Hui , Bryan Kian Hsiang Low

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

We consider the problem of contextual bandits and imitation learning, where the learner lacks direct knowledge of the executed action's reward. Instead, the learner can actively query an expert at each round to compare two actions and…

Machine Learning · Computer Science 2023-07-25 Ayush Sekhari , Karthik Sridharan , Wen Sun , Runzhe Wu

Motivated by a natural problem in online model selection with bandit information, we introduce and analyze a best arm identification problem in the rested bandit setting, wherein arm expected losses decrease with the number of times the arm…

Machine Learning · Statistics 2020-12-08 Leonardo Cella , Claudio Gentile , Massimiliano Pontil

Training reinforcement learning agents with human feedback is crucial when task objectives are difficult to specify through dense reward functions. While prior methods rely on offline trajectory comparisons to elicit human preferences, such…

Machine Learning · Computer Science 2025-10-08 Zhengran Ji , Boyuan Chen

Learning from human feedback (LHF) -- and in particular learning from pairwise preferences -- has recently become a crucial ingredient in training large language models (LLMs), and has been the subject of much research. Most recent works…

Machine Learning · Computer Science 2024-01-11 Vincent Dumoulin , Daniel D. Johnson , Pablo Samuel Castro , Hugo Larochelle , Yann Dauphin

Reinforcement learning from human feedback (RLHF) has emerged as a key enabling technology for aligning AI behaviour with human preferences. The traditional way to collect data in RLHF is via pairwise comparisons: human raters are asked to…

Machine Learning · Computer Science 2025-12-01 Jan Kompatscher , Danqing Shi , Giovanna Varni , Tino Weinkauf , Antti Oulasvirta

Online and offline RLHF methods, such as PPO and DPO, have been highly successful in aligning AI with human preferences. Despite their success, however, these methods suffer from fundamental limitations: (a) Models trained with RLHF can…

Machine Learning · Computer Science 2025-04-15 Eugene Choi , Arash Ahmadian , Matthieu Geist , Oilvier Pietquin , Mohammad Gheshlaghi Azar

Learning from prior tasks and transferring that experience to improve future performance is critical for building lifelong learning agents. Although results in supervised and reinforcement learning show that transfer may significantly…

Machine Learning · Statistics 2013-07-29 Mohammad Gheshlaghi Azar , Alessandro Lazaric , Emma Brunskill

While reinforcement learning (RL) has become a more popular approach for robotics, designing sufficiently informative reward functions for complex tasks has proven to be extremely difficult due their inability to capture human intent and…

Robotics · Computer Science 2022-12-08 Joey Hejna , Dorsa Sadigh

Learning from human feedback is a prominent technique to align the output of large language models (LLMs) with human expectations. Reinforcement learning from human feedback (RLHF) leverages human preference signals that are in the form of…

Computation and Language · Computer Science 2023-11-27 Di Jin , Shikib Mehri , Devamanyu Hazarika , Aishwarya Padmakumar , Sungjin Lee , Yang Liu , Mahdi Namazifar

We develop a new approach to obtaining high probability regret bounds for online learning with bandit feedback against an adaptive adversary. While existing approaches all require carefully constructing optimistic and biased loss…

Machine Learning · Computer Science 2020-11-02 Chung-Wei Lee , Haipeng Luo , Chen-Yu Wei , Mengxiao Zhang

This paper studies bandit problems where an agent has access to offline data that might be utilized to potentially improve the estimation of each arm's reward distribution. A major obstacle in this setting is the existence of compound…

Machine Learning · Computer Science 2023-12-21 Wen Huang , Xintao Wu

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with…

Machine Learning · Computer Science 2025-10-21 Keertana Chidambaram , Karthik Vinay Seetharaman , Vasilis Syrgkanis