English
Related papers

Related papers: Unleashing Efficient Asynchronous RL Post-Training…

200 papers

LLM post-training with reinforcement learning (RL) requires frequent synchronization of large model parameters between the trainer and distributed rollout actors. High-throughput RL post-training therefore relies on dedicated RDMA HPC…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-13 Chaoyi Ruan , Geng Luo , Xinyi Wan , Long Zhao , Qinghe Wang , Jiaan Zhu , Duling Xu , Guanbin Xu , Dehui Wei , Xiang Liu , Cheng Li , Haifeng Sun , Congcong Miao , Jialin Li

Asynchronous Distributed Reinforcement Learning (DRL) can suffer from degraded convergence when model updates become stale, often the result of network congestion and packet loss during large-scale training. This work introduces a network…

Networking and Internet Architecture · Computer Science 2025-07-09 Nehal Baganal Krishna , Anam Tahir , Firas Khamis , Mina Tahmasbi Arashloo , Michael Zink , Amr Rizk

While flow matching is elegant, its reliance on single-sample conditional velocities leads to high-variance training targets that destabilize optimization and slow convergence. By explicitly characterizing this variance, we identify 1) a…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Donglin Yang , Yongxing Zhang , Xin Yu , Liang Hou , Xin Tao , Pengfei Wan , Xiaojuan Qi , Renjie Liao

Flow matching policies learn continuous velocity fields that transport noise to actions, enabling fast deterministic inference for robot manipulation. However, standard training optimizes a pointwise velocity objective while inference…

Robotics · Computer Science 2026-05-12 Riad Ahmed , Sujosh Nag , Moniruzzaman Akash , Mostafa Hussein , Momotaz Begum

Reinforcement learning (RL) is effective in enhancing the accuracy of large language models in complex reasoning tasks. Existing RL policy optimization frameworks rely on final-answer correctness as feedback signals and rarely capture the…

Artificial Intelligence · Computer Science 2026-04-13 Jinghan Zhang , Fengran Mo , Tharindu Cyril Weerasooriya , Ruimin Dai , Xiaoyan Han , Yanjie Fu , Dakuo Wang , Kunpeng Liu

Temporal information is essential to learning effective policies with Reinforcement Learning (RL). However, current state-of-the-art RL algorithms either assume that such information is given as part of the state space or, when learning…

Machine Learning · Computer Science 2021-01-07 Wenling Shang , Xiaofei Wang , Aravind Srinivas , Aravind Rajeswaran , Yang Gao , Pieter Abbeel , Michael Laskin

Batch reinforcement learning (RL) aims at leveraging pre-collected data to find an optimal policy that maximizes the expected total rewards in a dynamic environment. The existing methods require absolutely continuous assumption (e.g., there…

Machine Learning · Statistics 2024-06-27 Xiaohong Chen , Zhengling Qi , Runzhe Wan

Meta reinforcement learning (Meta-RL) methods such as RL$^2$ have emerged as promising approaches for learning data-efficient RL algorithms tailored to a given task distribution. However, they show poor asymptotic performance and struggle…

Machine Learning · Computer Science 2025-07-29 Abhinav Bhatia , Samer B. Nashed , Shlomo Zilberstein

Stabilizing unsecured payloads against the inherent oscillations of dynamic bipedal locomotion remains a critical engineering bottleneck for humanoids in unstructured environments. To solve this, we introduce ReST-RL, a hierarchical…

Robotics · Computer Science 2026-03-12 Anlun Huang , Zhenyu Wu , Soofiyan Atar , Yuheng Zhi , Michael Yip

The exponential growth of data-intensive applications has placed unprecedented demands on modern storage systems, necessitating dynamic and efficient optimization strategies. Traditional heuristics employed for storage performance…

Operating Systems · Computer Science 2025-08-25 Chiyu Cheng , Chang Zhou , Yang Zhao

Reinforcement learning (RL) is essential for enhancing the complex reasoning capabilities of large language models (LLMs). However, existing RL training pipelines are computationally inefficient and resource-intensive, with the rollout…

Machine Learning · Computer Science 2026-01-27 Haocheng Xi , Charlie Ruan , Peiyuan Liao , Yujun Lin , Han Cai , Yilong Zhao , Shuo Yang , Kurt Keutzer , Song Han , Ligeng Zhu

Reinforcement learning (RL) is highly suitable for devising control strategies in the context of dynamical systems. A prominent instance of such a dynamical system is the system of equations governing fluid dynamics. Recent research results…

Machine Learning · Computer Science 2022-11-21 Marius Kurz , Philipp Offenhäuser , Dominic Viola , Oleksandr Shcherbakov , Michael Resch , Andrea Beck

In cross-device Federated Learning (FL) environments, scaling synchronous FL methods is challenging as stragglers hinder the training process. Moreover, the availability of each client to join the training is highly variable over time due…

Machine Learning · Computer Science 2023-04-17 Tuo Zhang , Lei Gao , Sunwoo Lee , Mi Zhang , Salman Avestimehr

Deep reinforcement learning approaches are becoming appealing for the design of nonlinear controllers for voltage control problems, but the lack of stability guarantees hinders their deployment in real-world scenarios. This paper constructs…

Systems and Control · Electrical Eng. & Systems 2023-08-31 Jie Feng , Wenqi Cui , Jorge Cortés , Yuanyuan Shi

Reinforcement learning (RL) has become a dominant paradigm for training large language models (LLMs), particularly for reasoning tasks. Effective RL for LLMs requires massive parallelization and poses an urgent need for efficient training…

Machine Learning · Computer Science 2026-03-03 Wei Fu , Jiaxuan Gao , Xujie Shen , Chen Zhu , Zhiyu Mei , Chuyi He , Shusheng Xu , Guo Wei , Jun Mei , Jiashu Wang , Tongkai Yang , Binhang Yuan , Yi Wu

In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods still face key challenges, including strategy collapse under…

Artificial Intelligence · Computer Science 2026-05-15 Mingda Zhang , Tiesunlong Shen , Haoran Luo , Wenjin Liu , Zikai Xiao , Erik Cambria , Xiaoying Tang

We introduce a reinforcement learning (RL) environment to design and benchmark control strategies aimed at reducing drag in turbulent fluid flows enclosed in a channel. The environment provides a framework for computationally-efficient,…

Fluid Dynamics · Physics 2023-02-09 L. Guastoni , J. Rabault , P. Schlatter , H. Azizpour , R. Vinuesa

Rollout-training disaggregation is emerging as the standard architecture for Reinforcement Learning (RL) post-training, where memory-bound rollout and compute-bound training are physically disaggregated onto purpose-built clusters to…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-16 Tianyuan Wu , Lunxi Cao , Yining Wei , Wei Gao , Yuheng Zhao , Dakai An , Shaopan Xiong , Zhiqiang Lv , Ju Huang , Siran Yang , Yinghao Yu , Jiamang Wang , Lin Qu , Wei Wang

Coflow is a recently proposed networking abstraction to help improve the communication performance of data-parallel computing jobs. In multi-stage jobs, each job consists of multiple coflows and is represented by a Directed Acyclic Graph…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-12-22 Xin Wang , Hong Shen

Reinforcement learning (RL) has attracted increasing interest for adaptive traffic signal control due to its model-free ability to learn control policies directly from interaction with the traffic environment. However, several challenges…

Machine Learning · Computer Science 2026-03-17 Dickens Kwesiga , Angshuman Guin , Khaled Abdelghany , Michael Hunter