English
Related papers

Related papers: ENCORE: Entropy-guided Reward Composition for Mult…

200 papers

We trained 13,440 large language models and found that entropy minimization requires only a single unlabeled data and 10 steps optimization to achieve performance improvements comparable to or even greater than those obtained using…

Computation and Language · Computer Science 2025-08-22 Zitian Gao , Lynx Chen , Haoming Luo , Joey Zhou , Bryan Dai

We propose Reinforcement Learning with Explicit Human Values (RLEV), a method that aligns Large Language Model (LLM) optimization directly with quantifiable human value signals. While Reinforcement Learning with Verifiable Rewards (RLVR)…

Machine Learning · Computer Science 2025-10-24 Dian Yu , Yulai Zhao , Kishan Panaganti , Linfeng Song , Haitao Mi , Dong Yu

Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a…

Computation and Language · Computer Science 2019-09-11 Jiawei Wu , Wenhan Xiong , William Yang Wang

Aligning human preference and value is an important requirement for building contemporary foundation models and embodied AI. However, popular approaches such as reinforcement learning with human feedback (RLHF) break down the task into…

Artificial Intelligence · Computer Science 2024-12-03 Chenliang Li , Siliang Zeng , Zeyi Liao , Jiaxiang Li , Dongyeop Kang , Alfredo Garcia , Mingyi Hong

Reinforcement learning (RL) is a key paradigm for post-training large language models (LLMs), but the widely used Group Relative Policy Optimization (GRPO) often suffers from entropy collapse: exploration quickly disappears, policies…

Machine Learning · Computer Science 2026-05-19 Chen Wang , Zhaochun Li , Jionghao Bai , Hexuan Deng , Ge Lan , Yue Wang

Reinforcement Learning with Verifiable Rewards (RLVR) improves the reasoning ability of Large Language Models (LLMs), but sparse outcome rewards make token-level credit assignment difficult. We study token-level credit as a…

Machine Learning · Computer Science 2026-05-27 Yuhang He , Haodong Wu , Siyi Liu , Hongyu Ge , Hange Zhou , Keyi Wu , Zhuo Zheng , Qihong Lin , Zixin Zhong , Yongqi Zhang

Reinforcement Learning (RL) heavily relies on the careful design of the reward function. However, accurately assigning rewards to each state-action pair in Long-Term Reinforcement Learning (LTRL) tasks remains a significant challenge. As a…

Machine Learning · Computer Science 2025-06-03 Qi Ju , Falin Hei , Zhemei Fang , Yunfeng Luo

Large Reasoning Models (LRMs) have achieved impressive performance on complex reasoning tasks by generating detailed chain-of-thought (CoT) explanations. However, these responses are often excessively long, containing redundant reasoning…

Artificial Intelligence · Computer Science 2025-10-13 Chen Huang , Wei Lu , Wenxuan Zhang

There are a variety of mechanisms (i.e., input types) for real-time human interaction that can facilitate effective human-robot teaming. For example, previous works have shown how teleoperation, corrective, and discrete (i.e., preference…

Robotics · Computer Science 2025-04-15 Michael Hagenow , Julie A. Shah

The ability of reinforcement learning algorithms to learn effective policies is determined by the rewards available during training. However, for practical problems, obtaining large quantities of reward labels is often infeasible due to…

Machine Learning · Computer Science 2025-10-02 Shreyas Chaudhari , Renhao Zhang , Philip S. Thomas , Bruno Castro da Silva

Reinforcement learning from human feedback (RLHF) is a recent technique to improve the quality of the text generated by a language model, making it closer to what humans would generate. A core ingredient in RLHF's success in aligning and…

Computation and Language · Computer Science 2024-07-08 Miguel Moura Ramos , Patrick Fernandes , António Farinhas , André F. T. Martins

A common approach for aligning language models to human preferences is to first learn a reward model from preference data, and then use this reward model to update the language model. We study two closely related problems that arise in this…

Computation and Language · Computer Science 2024-07-22 Zihao Wang , Chirag Nagpal , Jonathan Berant , Jacob Eisenstein , Alex D'Amour , Sanmi Koyejo , Victor Veitch

Designing effective reward functions remains a fundamental challenge in reinforcement learning (RL), as it often requires extensive human effort and domain expertise. While RL from human feedback has been successful in aligning agents with…

Machine Learning · Computer Science 2025-06-17 Tung Minh Luu , Younghwan Lee , Donghoon Lee , Sunho Kim , Min Jun Kim , Chang D. Yoo

Reinforcement learning from human feedback (RLHF) has demonstrated effectiveness in aligning large language models (LLMs) with human preferences. However, token-level RLHF suffers from the credit assignment problem over long sequences,…

Computation and Language · Computer Science 2025-02-18 Yekun Chai , Haoran Sun , Huang Fang , Shuohuan Wang , Yu Sun , Hua Wu

Feature attribution methods such as SHapley Additive exPlanations (SHAP) have become instrumental in understanding machine learning models, but their role in guiding model optimization remains underexplored. In this paper, we propose a…

Machine Learning · Computer Science 2025-08-01 Amal Saadallah

We study inverse reinforcement learning (IRL) and imitation learning (IM), the problems of recovering a reward or policy function from expert's demonstrated trajectories. We propose a new way to improve the learning process by adding a…

Machine Learning · Computer Science 2022-08-23 The Viet Bui , Tien Mai , Patrick Jaillet

While Large Language Models (LLMs) can generate fluent text, producing high-quality creative stories remains challenging. Reinforcement Learning (RL) offers a promising solution but faces two critical obstacles: designing reliable reward…

Artificial Intelligence · Computer Science 2026-01-13 Zhaoyan Li , Hang Lei , Yujia Wang , Lanbo Liu , Hao Liu , Liang Yu

Designing reward functions for continuous-control robotics often leads to subtle misalignments or reward hacking, especially in complex tasks. Preference-based RL mitigates some of these pitfalls by learning rewards from comparative…

Artificial Intelligence · Computer Science 2025-03-19 Anukriti Singh , Amisha Bhaskar , Peihong Yu , Souradip Chakraborty , Ruthwik Dasyam , Amrit Bedi , Pratap Tokekar

Language models (LMs) often exhibit undesirable text generation behaviors, including generating false, toxic, or irrelevant outputs. Reinforcement learning from human feedback (RLHF) - where human preference judgments on LM outputs are…

Computation and Language · Computer Science 2023-10-31 Zeqiu Wu , Yushi Hu , Weijia Shi , Nouha Dziri , Alane Suhr , Prithviraj Ammanabrolu , Noah A. Smith , Mari Ostendorf , Hannaneh Hajishirzi

The effectiveness of reinforcement learning (RL) agents in continuous control robotics tasks is mainly dependent on the design of the underlying reward function, which is highly prone to reward hacking. A misalignment between the reward…