English
Related papers

Related papers: Towards Better RL Training Data Utilization via Se…

200 papers

Reinforcement learning substantially improves pretrained language models, but it remains understudied why critic-free methods such as PPO and GRPO work as well as they do, and when they should provide the largest gains. We develop a…

Machine Learning · Computer Science 2026-05-22 Arip Asadulaev , Daniil Ognev , Karim Salta , Martin Takac

Recent advances have demonstrated the effectiveness of Reinforcement Learning (RL) in improving the reasoning capabilities of Large Language Models (LLMs). However, existing works inevitably rely on high-quality instructions and verifiable…

Computation and Language · Computer Science 2026-01-27 Wenkai Fang , Shunyu Liu , Yang Zhou , Kongcheng Zhang , Tongya Zheng , Kaixuan Chen , Mingli Song , Dacheng Tao

Recent high-capacity vision-language-action (VLA) models have demonstrated impressive performance on a range of robotic manipulation tasks by imitating human demonstrations. However, exploiting offline data with limited visited states will…

Robotics · Computer Science 2025-05-27 Guanxing Lu , Wenkai Guo , Chubin Zhang , Yuheng Zhou , Haonan Jiang , Zifeng Gao , Yansong Tang , Ziwei Wang

Frontier models have demonstrated exceptional capabilities following the integration of task-reward-based reinforcement learning (RL) into their training pipelines, enabling systems to evolve from pure reasoning models into sophisticated…

Machine Learning · Computer Science 2026-04-20 Sarthak Mittal , Leo Gagnon , Guillaume Lajoie

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

Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from…

Offline reinforcement learning (RL) provides a powerful framework for training robotic agents using pre-collected, suboptimal datasets, eliminating the need for costly, time-consuming, and potentially hazardous online interactions. This is…

Machine Learning · Computer Science 2025-08-01 Tung M. Luu , Donghoon Lee , Younghwan Lee , Chang D. Yoo

The advent of large pre-trained language models in the domain of Code Synthesis has shown remarkable performance on various benchmarks, treating the problem of Code Generation in a fashion similar to Natural Language Generation, trained…

Machine Learning · Computer Science 2023-10-23 Philip John Gorinski , Matthieu Zimmer , Gerasimos Lampouras , Derrick Goh Xin Deik , Ignacio Iacobacci

Large language models (LLMs) are predominantly used as evaluators for natural language generation (NLG) tasks, but their application to broader evaluation scenarios remains limited. In this work, we explore the potential of LLMs as general…

Artificial Intelligence · Computer Science 2025-12-02 Jie Meng , Jin Mao

Recent advancements have shown that reinforcement learning (RL) can substantially improve the reasoning abilities of large language models (LLMs). The effectiveness of such RL training, however, depends critically on the exploration space…

Computation and Language · Computer Science 2026-03-17 Haoyuan Wu , Hai Wang , Jiajia Wu , Jinxiang Ou , Keyao Wang , Weile Chen , Zihao Zheng , Bei Yu

Prevalent reinforcement learning~(RL) methods for fine-tuning LLM reasoners, such as GRPO or Leave-one-out PPO, abandon the learned value function in favor of empirically estimated returns. This hinders test-time compute scaling that relies…

Machine Learning · Computer Science 2026-04-14 Kusha Sareen , Morgane M Moss , Alessandro Sordoni , Rishabh Agarwal , Arian Hosseini

Large Reasoning Models (LRMs) with long chain-of-thought capabilities, optimized via reinforcement learning with verifiable rewards (RLVR), excel at objective reasoning tasks like mathematical problem solving and code generation. However,…

Computation and Language · Computer Science 2026-03-03 Yumeng Wang , Zhiyuan Fan , Jiayu Liu , Jen-tse Huang , Yi R. Fung

In this paper, we investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter. To acquire this capability, models must learn when and how to use external…

Computation and Language · Computer Science 2025-06-02 Fei Bai , Yingqian Min , Beichen Zhang , Zhipeng Chen , Wayne Xin Zhao , Lei Fang , Zheng Liu , Zhongyuan Wang , Ji-Rong Wen

Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning performance of large language models (LLMs) by increasing test-time compute. However, even after extensive RLVR training, such models still…

Artificial Intelligence · Computer Science 2026-03-10 Pinzheng Wang , Shuli Xu , Juntao Li , Yu Luo , Dong Li , Jianye Hao , Min Zhang

Vision-based reinforcement learning (RL) is a promising technique to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image…

Machine Learning · Computer Science 2021-09-29 Elie Aljalbout , Maximilian Ulmer , Rudolph Triebel

Training large language models (LLMs) typically involves pre-training on massive corpora, only to restart the process entirely when new data becomes available. A more efficient and resource-conserving approach would be continual…

Reinforcement Learning (RL) is a method for learning decision-making tasks that could enable robots to learn and adapt to their situation on-line. For an RL algorithm to be practical for robotic control tasks, it must learn in very few…

Artificial Intelligence · Computer Science 2015-03-19 Todd Hester , Michael Quinlan , Peter Stone

Bus holding control is a widely-adopted strategy for maintaining stability and improving the operational efficiency of bus systems. Traditional model-based methods often face challenges with the low accuracy of bus state prediction and…

Artificial Intelligence · Computer Science 2025-04-15 Jiajie Yu , Yuhong Wang , Wei Ma

Reinforcement Learning (RL) has achieved state-of-the-art results in domains such as robotics and games. We build on this previous work by applying RL algorithms to a selection of canonical online stochastic optimization problems with a…

Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…

‹ Prev 1 8 9 10 Next ›