Downloads · 30 days
24
16% of all-time downloads
Juelg/octo-base-1.5-finetuned-maniskill
octo-base-1.5-finetuned-maniskill is a robotics model from Juelg. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for octo. The card lists the license as mit.
This repo contains the Octo weights used in Refined Policy Distillation (RPD). RPD distills VLAs into small expert policies using online Reinforcement Learning.
Downloads · 30 days
24
16% of all-time downloads
All-time downloads
150
Public
Repo size
810 MB
Likes
0
Public
Click a slice to open those files.
Other810 MB · 100%
From the Hugging Face model README
This repo contains the Octo weights used in Refined Policy Distillation (RPD). RPD distills VLAs into small expert policies using online Reinforcement Learning.
Paper: Refined Policy Distillation: From VLA Generalists to RL Experts Project Page: https://refined-policy-distillation.github.io Code: https://github.com/Refined-Policy-Distillation/RPD
The dataset used to fine-tune this checkpoint can be found here.
Also checkout the RPD OpenVLA weights.
Adapted from the Octo Repo
from octo.model.octo_model import OctoModel
model = OctoModel.load_pretrained("hf://Juelg/octo-base-1.5-finetuned-maniskill")
task = model.create_tasks(texts=["pick the cube"])
action = model.sample_actions(observation, task, rng=jax.random.PRNGKey(0))
For details on how Octo was used in RPD checkout the RPD Code Repo and the Agents library.
If you find RPD useful for your work, please consider citing it:
@inproceedings{juelg2025refinedpolicydistillationvla,
title={{Refined Policy Distillation}: {F}rom {VLA} Generalists to {RL} Experts},
author={Tobias Jülg and Wolfram Burgard and Florian Walter},
year={2025},
booktitle={Proc.~of the IEEE/RSJ Int.~Conf.~on Intelligent Robots and Systems (IROS)},
note={Accepted for publication.}
}