English
Related papers

Related papers: Critique-RL: Training Language Models for Critiqui…

200 papers

Despite their unprecedented success, even the largest language models make mistakes. Similar to how humans learn and improve using feedback, previous work proposed providing language models with natural language feedback to guide them in…

Computation and Language · Computer Science 2023-07-13 Afra Feyza Akyürek , Ekin Akyürek , Aman Madaan , Ashwin Kalyan , Peter Clark , Derry Wijaya , Niket Tandon

In this paper, we consider the problem of actor-critic reinforcement learning. Firstly, we extend the actor-critic architecture to actor-critic-N architecture by introducing more critics beyond rewards. Secondly, we combine the reward-based…

Machine Learning · Computer Science 2020-06-15 Weiya Ren

Training large language models with reinforcement learning (RL) against verifiable rewards significantly enhances their reasoning abilities, yet remains computationally expensive due to inefficient uniform prompt sampling. We introduce…

Machine Learning · Computer Science 2026-03-06 Ruiqi Zhang , Daman Arora , Song Mei , Andrea Zanette

In this study, we investigate the use of global information to speed up the learning process and increase the cumulative rewards of reinforcement learning (RL) in competition tasks. Within the actor-critic RL, we introduce multiple…

Machine Learning · Computer Science 2020-03-03 Zehong Cao , Chin-Teng Lin

Reinforcement learning (RL) has proven highly effective in eliciting the reasoning capabilities of large language models (LLMs). Inspired by this success, recent studies have explored applying similar techniques to vision-language models…

Computer Vision and Pattern Recognition · Computer Science 2025-10-20 Yan Chen , Long Li , Teng Xi , Long Zeng , Jingdong Wang

While reinforcement learning (RL) demonstrated remarkable success in enhancing the reasoning capabilities of language models, the training dynamics of RL in LLMs remain unclear. In this work, we provide an explanation of the RL training…

Machine Learning · Computer Science 2025-09-30 Xingwu Chen , Tianle Li , Difan Zou

Actor-critic Reinforcement Learning (RL) algorithms have achieved impressive performance in continuous control tasks. However, they still suffer two nontrivial obstacles, i.e., low sample efficiency and overestimation bias. To this end, we…

Machine Learning · Computer Science 2022-05-10 Qing Li , Wengang Zhou , Zhenbo Lu , Houqiang Li

Effective human-agent collaboration is increasingly prevalent in real-world applications. Current trends in such collaborations are predominantly unidirectional, with users providing instructions or posing questions to agents, where agents…

Artificial Intelligence · Computer Science 2025-12-16 Emre Can Acikgoz , Jinoh Oh , Jie Hao , Joo Hyuk Jeon , Heng Ji , Dilek Hakkani-Tür , Gokhan Tur , Xiang Li , Chengyuan Ma , Xing Fan

Reinforcement Learning (RL) bears the promise of being a game-changer in many applications. However, since most of the literature in the field is currently focused on opaque models, the use of RL in high-stakes scenarios, where…

Machine Learning · Computer Science 2025-01-22 Leonardo Lucio Custode , Giovanni Iacca

Enhancing the reasoning capabilities of Large Language Models (LLMs) with efficiency and scalability remains a fundamental challenge in artificial intelligence research. This paper presents a rigorous experimental investigation into how…

Computation and Language · Computer Science 2025-04-02 Yunjie Ji , Sitong Zhao , Xiaoyu Tian , Haotian Wang , Shuaiting Chen , Yiping Peng , Han Zhao , Xiangang Li

Existing agents for solving tasks such as ML engineering rely on prompting powerful language models. As a result, these agents do not improve with more experience. In this paper, we show that agents backed by weaker models that improve via…

Machine Learning · Computer Science 2025-09-04 Sherry Yang , Joy He-Yueya , Percy Liang

In recommendation systems, diversity and novelty are essential for capturing varied user preferences and encouraging exploration, yet many systems prioritize click relevance. While reinforcement learning (RL) has been explored to improve…

Machine Learning · Computer Science 2025-07-30 Jiin Woo , Alireza Bagheri Garakani , Tianchen Zhou , Zhishen Huang , Yan Gao

Reinforcement learning (RL), a common tool in decision making, learns control policies from various experiences based on the associated cumulative return/rewards without treating them differently. Humans, on the contrary, often learn to…

Machine Learning · Computer Science 2025-11-25 Mingkang Wu , Devin White , Vernon Lawhern , Nicholas R. Waytowich , Yongcan Cao

Reinforcement learning with verifiable rewards has been used to elicit impressive performance from language models in many domains. But, broadly beneficial deployments of AI may require us to train models with strong capabilities in…

Machine Learning · Computer Science 2026-05-07 Christine Ye , Joe Benton

Reinforcement Learning (RL) plays an important role in the robotic manipulation domain since it allows self-learning from trial-and-error interactions with the environment. Still, sample efficiency and reward specification seriously limit…

Robotics · Computer Science 2023-11-07 Kun Chu , Xufeng Zhao , Cornelius Weber , Mengdi Li , Stefan Wermter

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

We focus on a simulation-based optimization problem of choosing the best design from the feasible space. Although the simulation model can be queried with finite samples, its internal processing rule cannot be utilized in the optimization…

Machine Learning · Computer Science 2021-11-02 Kuo Li , Qing-Shan Jia , Jiaqi Yan

As with any machine learning problem with limited data, effective offline RL algorithms require careful regularization to avoid overfitting. One-step methods perform regularization by doing just a single step of policy improvement, while…

Machine Learning · Computer Science 2023-07-25 Benjamin Eysenbach , Matthieu Geist , Sergey Levine , Ruslan Salakhutdinov

LLM-as-a-Judge refers to the automatic modeling of preferences for responses generated by Large Language Models (LLMs), which is of significant importance for both LLM evaluation and reward modeling. Although generative LLMs have made…

Computation and Language · Computer Science 2026-01-13 Hui Huang , Yancheng He , Hongli Zhou , Rui Zhang , Wei Liu , Weixun Wang , Jiaheng Liu , Wenbo Su

Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, stemming not only from sparse outcome feedback but also from the agent's inability to leverage prior…

Machine Learning · Computer Science 2026-03-19 Dilxat Muhtar , Jiashun Liu , Wei Gao , Weixun Wang , Shaopan Xiong , Ju Huang , Siran Yang , Wenbo Su , Jiamang Wang , Ling Pan , Bo Zheng