• 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.

• 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.

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.

• 💻 Installation
• 🏆 Offline Policy Training & Value Model
• 🔮 Dynamics Model
• 🦾 Online Policy Training
• 🛠️ Deployment on Piper

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

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}
}