RISE

OpenDriveLab更新放缓

RISE 用组合式世界模型让机器人策略自我进化，通过生成模型与价值学习提升操作任务表现，适合研究机器人学习与 VLA 的团队。

[RSS 2026] Code for RISE: Self-Improving Robot Policy with Compositional World Model

暂无版本386star24fork同步于 2026-11-07 07:31 UTC

机器人策略世界模型扩散模型价值学习视觉语言模型

对比 GitHub 官网 diffusion-models generative-models manipulation robot-learning value-learning

怎么上手

由 README 提炼，执行前请确认

原文

详见 docs/installation.md，README 未给出可直接复制的安装命令

硬件要求按 README 说明

README 未说明具体显存与 GPU 型号要求，仅提及训练需下载预训练动力学模型；部署部分指向 Piper 平台文档。

下载：源码 zip·GitHub Releases（安装包）本站不镜像安装包

项目说明

由 README 自动翻译提炼

没人工点评？写下你的经验

用组合式世界模型在想象中做强化学习，让机器人策略自我改进的框架

RISE 用组合式世界模型让机器人策略自我进化，通过生成模型与价值学习提升操作任务表现，适合研究机器人学习与 VLA 的团队。

核心能力

组合多视角动力学模型与进度价值模型
在想象 rollout 中做 RL，免去真机交互与重置成本
基于 OpenPI 的离线策略与价值模型训练
提供动作条件动力学模型与在线策略训练流程
在动态分拣、装包、封箱等任务上报告显著提升

容易踩的坑

训练代码与预训练动力学模型需按 News 说明单独获取，不在仓库内直接可用；仓库分为离线策略/价值、动力学模型、在线策略三部分，需按文档顺序分别配置环境；作者提示需拉取最新代码以获取重要 bug 修复。

内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README

用户点评

登录用户的真实使用记录，可按版本和硬件筛选

共 0 条

还没有人点评。第一个说出真实体验的人最有价值。

README 原文

未翻译

在 GitHub 打开

🌏 RISE

📢 News

2026/Jun/03 ❗❗❗ Please pull the latest code for important bug fixes.
2026/Mar/27 🚀 RISE got accepted to RSS 2026.
2026/Mar/22 Training code and pre-trained dynamics model are released.
2026/Feb/11 Paper released on arXiv.

🔥 Highlights

A compositional world model. A principled design that combines a controllable multi-view dynamics model with a progress value model, yielding informative advantages for robust policy improvement.
RL in imagination. A scalable self-improving framework that bootstraps robot policies through imaginary rollouts, avoiding the hardware cost and laborious reset of real-world interactions.
Real-world manipulation gains. Non-trivial performance improvements on challenging dexterous tasks, including +35% on dynamic brick sorting, +45% on backpack packing, and +35% on box closing.

🗺️ Overview

RISE repository is structured with three major parts:

policy_and_value/policy_offline_and_value: OpenPI-based offline policy and value training. They are put together since they share similar model architecture and training pipeline.
dynamics/dynamics_model: Action-conditioned dynamics model.
policy_and_value/policy_online: Online RL for policy improvement.

🧑‍💻 Getting Started

❤️ Acknowledgement

We thank the following projects for their open-source contributions: OpenPI Pi0 / Pi05, Genie Envisioner, RLinf, LTX-Video, Kai0.

📄 License and Citation

All assets and code in this repository are under the Apache 2.0 license unless specified otherwise. The data and checkpoint are under CC BY-NC-SA 4.0. Other modules inherit their own distribution licenses.

@article{rise2026,
  title={RISE: Self-Improving Robot Policy with Compositional World Model},
  author={Yang, Jiazhi and Lin, Kunyang and Li, Jinwei and Zhang, Wencong and Lin, Tianwei and Wu, Longyan and Su, Zhizhong and Zhao, Hao and Zhang, Ya-Qin and Chen, Li and Luo, Ping and Yue, Xiangyu and Li, Hongyang},
  journal={arXiv preprint arXiv:2602.11075},
  year={2026}
}