Add model card for $\pi_\\texttt{RL}$: Online RL Fine-tuning Robotics Model
#1
by
nielsr
HF Staff
- opened
This PR adds a comprehensive model card for the $\pi_\\texttt{RL}$ model, presented in the paper "$\pi_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models".
It includes:
- The
roboticspipeline tag for improved discoverability. - The
apache-2.0license, consistent with theRLinfproject. - A link to the official GitHub repository:
https://github.com/RLinf/RLinf. - A link to the RLinf project documentation:
https://rlinf.readthedocs.io/en/latest/. - The paper's abstract and relevant citations.
Please review and merge if everything looks good!
andylin-hao
changed pull request status to
merged