English
Related papers

Related papers: Similarity as Reward Alignment: Robust and Versati…

200 papers

Modern language models often rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors. However, they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of…

Reinforcement learning has become a cornerstone for enhancing the reasoning capabilities of Large Language Models, where group-based approaches such as GRPO have emerged as efficient paradigms that optimize policies by leveraging…

In online learning from non-stationary data streams, it is necessary to learn robustly to outliers and to adapt quickly to changes in the underlying data generating mechanism. In this paper, we refer to the former attribute of online…

Machine Learning · Statistics 2021-09-29 Shintaro Fukushima , Atsushi Nitanda , Kenji Yamanishi

In this paper, we study offline preference-based reinforcement learning (PbRL), where learning is based on pre-collected preference feedback over pairs of trajectories. While offline PbRL has demonstrated remarkable empirical success,…

Machine Learning · Computer Science 2025-06-04 Hyungkyu Kang , Min-hwan Oh

Model-based offline reinforcement learning (RL) has emerged as a promising approach for recommender systems, enabling effective policy learning by interacting with frozen world models. However, the reward functions in these world models,…

Information Retrieval · Computer Science 2025-05-13 Yi Zhang , Ruihong Qiu , Xuwei Xu , Jiajun Liu , Sen Wang

How to improve discriminative feature learning is central in classification. Existing works address this problem by explicitly increasing inter-class separability and intra-class similarity, whether by constructing positive and negative…

Machine Learning · Computer Science 2024-08-21 Qingsong Zhao , Yi Wang , Shuguang Dou , Chen Gong , Yin Wang , Cairong Zhao

Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL:…

Machine Learning · Computer Science 2026-02-26 Ningyuan Yang , Weihua Du , Weiwei Sun , Sean Welleck , Yiming Yang

Reinforcement learning (RL) provides a naturalistic framing for learning through trial and error, which is appealing both because of its simplicity and effectiveness and because of its resemblance to how humans and animals acquire skills…

Machine Learning · Computer Science 2022-08-09 Archit Sharma , Kelvin Xu , Nikhil Sardana , Abhishek Gupta , Karol Hausman , Sergey Levine , Chelsea Finn

Aligning human preference and value is an important requirement for contemporary foundation models. State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning…

Artificial Intelligence · Computer Science 2024-10-29 Jiaxiang Li , Siliang Zeng , Hoi-To Wai , Chenliang Li , Alfredo Garcia , Mingyi Hong

Scalar reward models compress multi-dimensional human preferences into a single opaque score, creating an information bottleneck that often leads to brittleness and reward hacking in open-ended alignment. We argue that robust alignment for…

Computation and Language · Computer Science 2026-03-02 Ruipeng Jia , Yunyi Yang , Yuxin Wu , Yongbo Gai , Siyuan Tao , Mengyu Zhou , Jianhe Lin , Xiaoxi Jiang , Guanjun Jiang

Preference learning is critical for aligning large language models (LLMs) with human values, with the quality of preference datasets playing a crucial role in this process. While existing metrics primarily assess data quality based on…

Machine Learning · Computer Science 2025-03-05 Kexin Huang , Junkang Wu , Ziqian Chen , Xue Wang , Jinyang Gao , Bolin Ding , Jiancan Wu , Xiangnan He , Xiang Wang

Explicit engineering of reward functions for given environments has been a major hindrance to reinforcement learning methods. While Inverse Reinforcement Learning (IRL) is a solution to recover reward functions from demonstrations only,…

Machine Learning · Computer Science 2020-02-24 David Venuto , Jhelum Chakravorty , Leonard Boussioux , Junhao Wang , Gavin McCracken , Doina Precup

The recent focus and release of pre-trained models have been a key components to several advancements in many fields (e.g. Natural Language Processing and Computer Vision), as a matter of fact, pre-trained models learn disparate latent…

Machine Learning · Computer Science 2025-07-11 Elia Piccoli , Malio Li , Giacomo Carfì , Vincenzo Lomonaco , Davide Bacciu

Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…

Machine Learning · Computer Science 2025-05-13 Shenao Zhang , Zhihan Liu , Boyi Liu , Yufeng Zhang , Yingxiang Yang , Yongfei Liu , Liyu Chen , Tao Sun , Zhaoran Wang

Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment. However, in many tasks the…

Machine Learning · Computer Science 2022-02-18 Daniel Shin , Daniel S. Brown , Anca D. Dragan

Preference-based reinforcement learning (PbRL) is emerging as a promising approach to teaching robots through human comparative feedback, sidestepping the need for complex reward engineering. However, the substantial volume of feedback…

Robotics · Computer Science 2025-01-09 Ruiqi Wang , Dezhong Zhao , Ziqin Yuan , Ike Obi , Byung-Cheol Min

We study the problem of online multi-agent reinforcement learning (MARL) in environments with sparse rewards, where reward feedback is not provided at each interaction but only revealed at the end of a trajectory. This setting, though…

Machine Learning · Computer Science 2025-09-29 The Viet Bui , Tien Mai , Hong Thanh Nguyen

Large language models are increasingly used for complex reasoning tasks where high-quality offline data such as expert-annotated solutions and distilled reasoning traces are often available. However, in environments with sparse rewards,…

Artificial Intelligence · Computer Science 2025-08-11 Yihao Liu , Shuocheng Li , Lang Cao , Yuhang Xie , Mengyu Zhou , Haoyu Dong , Xiaojun Ma , Shi Han , Dongmei Zhang

Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations for preference data. These methods commonly utilize the same…

Machine Learning · Computer Science 2025-04-29 Zhaoyang Wang , Weilei He , Zhiyuan Liang , Xuchao Zhang , Chetan Bansal , Ying Wei , Weitong Zhang , Huaxiu Yao

Reward modeling is central to alignment pipelines such as RLHF, RLAIF, and PPO-based policy optimization, yet its reliability is constrained by limited and heterogeneous human preference data that are expensive to collect at scale. While…

Machine Learning · Computer Science 2026-05-26 Payel Bhattacharjee , Osvaldo Simeone , Ravi Tandon