English
Related papers

Related papers: Asynchronous RLHF: Faster and More Efficient Off-P…

200 papers

Enhancing the mathematical reasoning of Large Language Models (LLMs) is a pivotal challenge in advancing AI capabilities. While Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) are the dominant training paradigms, a systematic…

Machine Learning · Computer Science 2025-07-14 Hiroshi Yoshihara , Taiki Yamaguchi , Yuichi Inoue

Reinforcement Learning (RL) has become essential for eliciting complex reasoning capabilities in Large Language Models (LLMs). However, the substantial memory overhead of storing Key-Value (KV) caches during long-horizon rollouts acts as a…

Machine Learning · Computer Science 2026-03-31 Sijia Luo , Xiaokang Zhang , Yuxuan Hu , Bohan Zhang , Ke Wang , Jinbo Su , Mengshu Sun , Lei Liang , Jing Zhang

As Large Language Models (LLMs) continue to progress toward more advanced forms of intelligence, Reinforcement Learning from Human Feedback (RLHF) is increasingly seen as a key pathway toward achieving Artificial General Intelligence (AGI).…

Machine Learning · Computer Science 2024-10-17 Yuzi Yan , Xingzhou Lou , Jialian Li , Yiping Zhang , Jian Xie , Chao Yu , Yu Wang , Dong Yan , Yuan Shen

Asynchronous reinforcement learning improves rollout throughput for large language model agents by decoupling sample generation from policy optimization, but it also introduces a critical failure mode for PPO-style off-policy correction. In…

Machine Learning · Computer Science 2026-05-19 Zhong Guan , Yongjian Guo , Haoran Sun , Wen Huang , Shuai Di , Likang Wu , Xiong Jun Wu , Hongke Zhao

Large Language Models (LLMs) tend to respond correctly to prompts that align well with the data they were trained and fine-tuned on. Yet, small shifts in wording, format, or language can trigger surprisingly large failures, especially on…

Machine Learning · Computer Science 2026-05-12 Yeping Jin , Jiaming Hu , Ioannis Ch. Paschalidis

LLM alignment ensures that large language models behave safely and effectively by aligning their outputs with human values, goals, and intentions. Aligning LLMs employ huge amounts of data, computation, and time. Moreover, curating data…

Machine Learning · Computer Science 2025-02-19 Amrit Khera , Rajat Ghosh , Debojyoti Dutta

Offline reinforcement learning (RL) extends the paradigm of classical RL algorithms to purely learning from static datasets, without interacting with the underlying environment during the learning process. A key challenge of offline RL is…

Machine Learning · Computer Science 2022-06-16 Shentao Yang , Yihao Feng , Shujian Zhang , Mingyuan Zhou

Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) are two prominent post-training paradigms for refining the capabilities and aligning the behavior of Large Language Models (LLMs). Existing approaches that integrate SFT and RL…

Machine Learning · Computer Science 2026-03-18 Wenhao Zhang , Yuexiang Xie , Yuchang Sun , Yanxi Chen , Guoyin Wang , Yaliang Li , Bolin Ding , Jingren Zhou

We present Sequential Policy Optimization for Simultaneous Machine Translation (SeqPO-SiMT), a new policy optimization framework that defines the simultaneous machine translation (SiMT) task as a sequential decision making problem,…

Computation and Language · Computer Science 2025-05-28 Ting Xu , Zhichao Huang , Jiankai Sun , Shanbo Cheng , Wai Lam

The alignment of large language models (LLMs) with human preferences is commonly achieved through Reinforcement Learning from Human Feedback (RLHF). Direct Preference Optimization (DPO) simplified this paradigm by establishing a direct…

Machine Learning · Computer Science 2025-09-26 Yuandong Tan

Recent advances in behavior cloning (BC) have enabled impressive visuomotor control policies. However, these approaches are limited by the quality of human demonstrations, the manual effort required for data collection, and the diminishing…

Robotics · Computer Science 2025-09-29 Lars Ankile , Zhenyu Jiang , Rocky Duan , Guanya Shi , Pieter Abbeel , Anusha Nagabandi

Scaling reinforcement learning (RL) has shown strong promise for enhancing the reasoning abilities of large language models (LLMs), particularly in tasks requiring long chain-of-thought generation. However, RL training efficiency is often…

Machine Learning · Computer Science 2026-03-25 Yiqi Zhang , Huiqiang Jiang , Xufang Luo , Zhihe Yang , Chengruidong Zhang , Yifei Shen , Dongsheng Li , Yuqing Yang , Lili Qiu , Yang You

Large language models (LLMs) have recently advanced in reasoning when optimized with reinforcement learning (RL) under verifiable rewards. Existing methods primarily rely on outcome-based supervision to strengthen internal LLM reasoning,…

Artificial Intelligence · Computer Science 2026-05-29 Siyao Song , Cong Ma , Zhihao Cheng , Shiye Lei , Minghao Li , Ying Zeng , Huaixiao Tou , Kai Jia

Offline Reinforcement learning (RL) has shown potent in many safe-critical tasks in robotics where exploration is risky and expensive. However, it still struggles to acquire skills in temporally extended tasks. In this paper, we study the…

Robotics · Computer Science 2022-05-25 Jinning Li , Chen Tang , Masayoshi Tomizuka , Wei Zhan

Distributed training and increasing the gradient update frequency are practical strategies to accelerate learning and improve performance, but both exacerbate a central challenge: \textit{policy lag}, which is the mismatch between the…

Reward-model training is the cost bottleneck in modern Reinforcement Learning Human Feedback (RLHF) pipelines, often requiring tens of billions of parameters and an offline preference-tuning phase. In the proposed method, a frozen,…

Machine Learning · Computer Science 2025-06-09 Rudransh Agnihotri , Ananya Pandey

While Large Language Models (LLM) enable non-experts to specify open-world multi-robot tasks, the generated plans often lack kinematic feasibility and are not efficient, especially in long-horizon scenarios. Formal methods like Linear…

Robotics · Computer Science 2026-02-11 Shuyuan Hu , Tao Lin , Kai Ye , Yang Yang , Tianwei Zhang

Sample efficiency and exploration remain major challenges in online reinforcement learning (RL). A powerful approach that can be applied to address these issues is the inclusion of offline data, such as prior trajectories from a human…

Machine Learning · Computer Science 2023-06-01 Philip J. Ball , Laura Smith , Ilya Kostrikov , Sergey Levine

Vision-Language-Action (VLA) models based on flow matching have shown excellent performance in general-purpose robotic manipulation tasks. However, the action accuracy of these models on complex downstream tasks is unsatisfactory. One…

Robotics · Computer Science 2025-09-05 Hongyin Zhang , Shiyuan Zhang , Junxi Jin , Qixin Zeng , Yifan Qiao , Hongchao Lu , Donglin Wang

Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation and alignment capabilities. However, RLHF encounters…

Computation and Language · Computer Science 2024-05-31 Kuo Liao , Shuang Li , Meng Zhao , Liqun Liu , Mengge Xue , Zhenyu Hu , Honglin Han , Chengguo Yin
‹ Prev 1 8 9 10 Next ›