English
Related papers

Related papers: Online Bandit Learning with Offline Preference Dat…

200 papers

How can we make models robust to even imperfect human feedback? In reinforcement learning from human feedback (RLHF), human preferences over model outputs are used to train a reward model that assigns scalar values to responses. Because…

Artificial Intelligence · Computer Science 2026-05-11 Tiffany Horter , Andrew Markham , Niki Trigoni , Serena Booth

Efficient use of large language models (LLMs) is critical for deployment at scale: without adaptive routing, systems either overpay for strong models or risk poor performance from weaker ones. Selecting the right LLM for each query is…

Machine Learning · Computer Science 2025-10-10 Wang Wei , Tiankai Yang , Hongjie Chen , Yue Zhao , Franck Dernoncourt , Ryan A. Rossi , Hoda Eldardiry

While reinforcement learning (RL) enables robots to acquire skills autonomously, its real-world deployment is severely limited by inefficient and unsafe exploration. Human-in-the-loop interventions offer a practical solution, yet existing…

Robotics · Computer Science 2026-05-26 Yunyang Mo , Jian Li , Qiwei Wu , Yihang Kang , Renjing Xu

We consider reinforcement learning (RL) methods in offline domains without additional online data collection, such as mobile health applications. Most of existing policy optimization algorithms in the computer science literature are…

Machine Learning · Statistics 2022-07-28 Chengchun Shi , Shikai Luo , Yuan Le , Hongtu Zhu , Rui Song

Recommender systems are a ubiquitous feature of online platforms. Increasingly, they are explicitly tasked with increasing users' long-term satisfaction. In this context, we study a content exploration task, which we formalize as a…

Machine Learning · Computer Science 2023-07-21 Thomas M. McDonald , Lucas Maystre , Mounia Lalmas , Daniel Russo , Kamil Ciosek

Reinforcement learning from human feedback (RLHF) has contributed to performance improvements in large language models. To tackle its reliance on substantial amounts of human-labeled data, a successful approach is multi-task representation…

Machine Learning · Computer Science 2025-03-06 Ruitao Chen , Liwei Wang

The RKHS bandit problem (also called kernelized multi-armed bandit problem) is an online optimization problem of non-linear functions with noisy feedback. Although the problem has been extensively studied, there are unsatisfactory results…

Machine Learning · Computer Science 2021-07-27 Sho Takemori , Masahiro Sato

Reinforcement learning from human feedback (RLHF) is the mainstream paradigm used to align large language models (LLMs) with human preferences. Yet existing RLHF heavily relies on accurate and informative reward models, which are vulnerable…

Computation and Language · Computer Science 2024-03-15 Wei Shen , Xiaoying Zhang , Yuanshun Yao , Rui Zheng , Hongyi Guo , Yang Liu

Aligning generative recommender systems to user preferences via post-training is critical for closing the gap between next-item prediction and actual recommendation quality. Existing post-training methods are ill-suited for production-scale…

Machine Learning · Computer Science 2026-03-12 Keertana Chidambaram , Sanath Kumar Krishnamurthy , Qiuling Xu , Ko-Jen Hsiao , Moumita Bhattacharya

Preference-based reinforcement learning (PbRL) provides a powerful paradigm to avoid meticulous reward engineering by learning rewards based on human preferences. However, real-time human feedback is hard to obtain in online tasks. Most…

Machine Learning · Computer Science 2024-12-24 Songjun Tu , Jingbo Sun , Qichao Zhang , Xiangyuan Lan , Dongbin Zhao

Text classification models are typically trained via supervised fine-tuning (SFT). However, SFT essentially performs behavior cloning from instance-wise labels and thus fails to adequately capture relative preference relations among…

Machine Learning · Computer Science 2026-05-19 Tianxiang Xu , Xiaoyan Zhu , Xin Lai , Jiayin Wang

Large Language Models (LLMs) aligned using Reinforcement Learning from Human Feedback (RLHF) have shown remarkable generation abilities in numerous tasks. However, collecting high-quality human preferences creates costly bottlenecks in…

Machine Learning · Computer Science 2025-06-10 Nirjhar Das , Souradip Chakraborty , Aldo Pacchiano , Sayak Ray Chowdhury

Reinforcement Learning from Human Feedback (RLHF) has greatly improved the performance of modern Large Language Models (LLMs). The RLHF process is resource-intensive and technically challenging, generally requiring a large collection of…

In this paper, we study a special bandit setting of online stochastic linear optimization, where only one-bit of information is revealed to the learner at each round. This problem has found many applications including online advertisement…

Machine Learning · Computer Science 2015-09-28 Lijun Zhang , Tianbao Yang , Rong Jin , Zhi-Hua Zhou

Offline (or batch) reinforcement learning (RL) algorithms seek to learn an optimal policy from a fixed dataset without active data collection. Based on the composition of the offline dataset, two main categories of methods are used:…

Machine Learning · Computer Science 2023-07-04 Paria Rashidinejad , Banghua Zhu , Cong Ma , Jiantao Jiao , Stuart Russell

Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs). Typically in pairwise rewarding tasks, GRMs generate reasoning chains ending with…

Computation and Language · Computer Science 2026-05-04 Zongqi Wang , Rui Wang , Yuchuan Wu , Yiyao Yu , Pinyi Zhang , Shaoning Sun , Yujiu Yang , Yongbin Li

In modern ML Ops environments, model deployment is a critical process that traditionally relies on static heuristics such as validation error comparisons and A/B testing. However, these methods require human intervention to adapt to…

Machine Learning · Computer Science 2025-03-31 S. Aaron McClendon , Vishaal Venkatesh , Juan Morinelli

We consider the problem of learning personalized decision policies from observational bandit feedback data across multiple heterogeneous data sources. In our approach, we introduce a novel regret analysis that establishes finite-sample…

Machine Learning · Computer Science 2024-10-14 Aldo Gael Carranza , Susan Athey

Bandits with feedback graphs are powerful online learning models that interpolate between the full information and classic bandit problems, capturing many real-life applications. A recent work by Zhang et al. (2023) studies the contextual…

Machine Learning · Computer Science 2024-02-14 Mengxiao Zhang , Yuheng Zhang , Haipeng Luo , Paul Mineiro

Applying Reinforcement Learning (RL) to Restless Multi-Arm Bandits (RMABs) offers a promising avenue for addressing allocation problems with resource constraints and temporal dynamics. However, classic RMAB models largely overlook the…

Machine Learning · Computer Science 2025-03-20 Yunfan Zhao , Tonghan Wang , Dheeraj Nagaraj , Aparna Taneja , Milind Tambe