← 研踪 PaperTrailarXiv:2602.07837 · v6
USER: A Unified and Extensible System for Online Real-World Policy Learning in Embodied AI
首次提交 2026-02-08 14:23
版本更新 2026-11-15 14:38
雷达观测 2026-11-17 19:15
摘要
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, suggesting that real-world policy learning is not merely an algorithmic problem, but inherently a systems problem. We present \user, a \underline{U}nified and extensible \underline{S}yst\underline{E}m for online real-world policy lea\underline{R}ning. On the systems side, \user introduces a hardware abstraction layer for unified robot management and an adaptive communication plane that enables efficient cloud-edge training. On the learning side, \user adopts a fully asynchronous training framework, designs a persistent and cache-aware replay buffer, and provides extensible abstractions for rewards, algorithms, and policies. Experiments in both simulation and the real world demonstrate that \user supports multi-robot coordination, heterogeneous manipulators, cloud-edge training with large models, and long-running asynchronous training. Together, these capabilities establish \user as a unified and extensible systems foundation for online real-world policy learning.
作者备注:Accepted to RSS 2026
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v6 · 2026-11-15 14:38 · 最新观测版本
USER: A Unified and Extensible System for Online Real-World Policy Learning in Embodied AI
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, suggesting that real-world policy learning is not merely an algorithmic problem, but inherently a systems problem. We present \user, a \underline{U}nified and extensible \underline{S}yst\underline{E}m for online real-world policy lea\underline{R}ning. On the systems side, \user introduces a hardware abstraction layer for unified robot management and an adaptive communication plane that enables efficient cloud-edge training. On the learning side, \user adopts a fully asynchronous training framework, designs a persistent and cache-aware replay buffer, and provides extensible abstractions for rewards, algorithms, and policies. Experiments in both simulation and the real world demonstrate that \user supports multi-robot coordination, heterogeneous manipulators, cloud-edge training with large models, and long-running asynchronous training. Together, these capabilities establish \user as a unified and extensible systems foundation for online real-world policy learning.
查看此版本解读 →查看此版本原文 ↗