# RLinf v0.4 released: open-source training framework upgrade for embodied reinforcement learning

- Source: Xbotics具身智能实验室 · 微信公众号
- Published: 2026-10-20T02:56:39.000Z
- RoboHot: https://robohot.news/en/items/eoqifizp7tnwddyt2tyzlerd7
- Original: https://mp.weixin.qq.com/s?__biz=MzkyMTc1NTI3Ng==&mid=2247509281&idx=1&sn=da72fce9f47acbd2fa70f16c9b907649&chksm=c00dacb03a1ad3d17668768ce9f0244bb4f956bb2614aa28709a03cbd4320990c4c3787e42e1&scene=126&sessionid=1792517452#rd

## Summary

RLinf, an open-source training framework for embodied reinforcement learning developed by Tsinghua University, Infinigence AI, and the Beijing Zhongguancun Academy, has officially released v0.4, with updates across four areas: a Lego-style real-machine system, real-machine post-training algorithms, full-modality model support, and a domestic computing power foundation.

## Why it matters

It outlines the framework's evolution from simulation to real-machine training, helping readers understand the capability boundaries of the embodied reinforcement learning engineering stack.