Saved in:
Bibliographic Details
Main Authors: Zang, Hongzhi, Yu, Shu'ang, Lin, Hao, Zhou, Tianxing, Huang, Zefang, Guo, Zhen, Xu, Xin, Zhou, Jiakai, Sheng, Yuze, Zhang, Shizhe, Gao, Feng, Tang, Wenhao, Yue, Yufeng, Zhang, Quanlu, Chen, Xinlei, Yu, Chao, Wang, Yu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.07837
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912898489516032
author Zang, Hongzhi
Yu, Shu'ang
Lin, Hao
Zhou, Tianxing
Huang, Zefang
Guo, Zhen
Xu, Xin
Zhou, Jiakai
Sheng, Yuze
Zhang, Shizhe
Gao, Feng
Tang, Wenhao
Yue, Yufeng
Zhang, Quanlu
Chen, Xinlei
Yu, Chao
Wang, Yu
author_facet Zang, Hongzhi
Yu, Shu'ang
Lin, Hao
Zhou, Tianxing
Huang, Zefang
Guo, Zhen
Xu, Xin
Zhou, Jiakai
Sheng, Yuze
Zhang, Shizhe
Gao, Feng
Tang, Wenhao
Yue, Yufeng
Zhang, Quanlu
Chen, Xinlei
Yu, Chao
Wang, Yu
contents Online policy learning directly in the physical world is a promising yet challenging direction for embodied intelligence. Unlike simulation, real-world systems cannot be arbitrarily accelerated, cheaply reset, or massively replicated, which makes scalable data collection, heterogeneous deployment, and long-horizon effective training difficult. These challenges suggest that real-world policy learning is not only an algorithmic issue but fundamentally a systems problem. We present USER, a Unified and extensible SystEm for Real-world online policy learning. USER treats physical robots as first-class hardware resources alongside GPUs through a unified hardware abstraction layer, enabling automatic discovery, management, and scheduling of heterogeneous robots. To address cloud-edge communication, USER introduces an adaptive communication plane with tunneling-based networking, distributed data channels for traffic localization, and streaming-multiprocessor-aware weight synchronization to regulate GPU-side overhead. On top of this infrastructure, USER organizes learning as a fully asynchronous framework with a persistent, cache-aware buffer, enabling efficient long-horizon experiments with robust crash recovery and reuse of historical data. In addition, USER provides extensible abstractions for rewards, algorithms, and policies, supporting online imitation or reinforcement learning of CNN/MLP, generative policies, and large vision-language-action (VLA) models within a unified pipeline. Results in both simulation and the real world show that USER enables multi-robot coordination, heterogeneous manipulators, edge-cloud collaboration with large models, and long-running asynchronous training, offering a unified and extensible systems foundation for real-world online policy learning.
format Preprint
id arxiv_https___arxiv_org_abs_2602_07837
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RLinf-USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI
Zang, Hongzhi
Yu, Shu'ang
Lin, Hao
Zhou, Tianxing
Huang, Zefang
Guo, Zhen
Xu, Xin
Zhou, Jiakai
Sheng, Yuze
Zhang, Shizhe
Gao, Feng
Tang, Wenhao
Yue, Yufeng
Zhang, Quanlu
Chen, Xinlei
Yu, Chao
Wang, Yu
Robotics
Online policy learning directly in the physical world is a promising yet challenging direction for embodied intelligence. Unlike simulation, real-world systems cannot be arbitrarily accelerated, cheaply reset, or massively replicated, which makes scalable data collection, heterogeneous deployment, and long-horizon effective training difficult. These challenges suggest that real-world policy learning is not only an algorithmic issue but fundamentally a systems problem. We present USER, a Unified and extensible SystEm for Real-world online policy learning. USER treats physical robots as first-class hardware resources alongside GPUs through a unified hardware abstraction layer, enabling automatic discovery, management, and scheduling of heterogeneous robots. To address cloud-edge communication, USER introduces an adaptive communication plane with tunneling-based networking, distributed data channels for traffic localization, and streaming-multiprocessor-aware weight synchronization to regulate GPU-side overhead. On top of this infrastructure, USER organizes learning as a fully asynchronous framework with a persistent, cache-aware buffer, enabling efficient long-horizon experiments with robust crash recovery and reuse of historical data. In addition, USER provides extensible abstractions for rewards, algorithms, and policies, supporting online imitation or reinforcement learning of CNN/MLP, generative policies, and large vision-language-action (VLA) models within a unified pipeline. Results in both simulation and the real world show that USER enables multi-robot coordination, heterogeneous manipulators, edge-cloud collaboration with large models, and long-running asynchronous training, offering a unified and extensible systems foundation for real-world online policy learning.
title RLinf-USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI
topic Robotics
url https://arxiv.org/abs/2602.07837