admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-05-18 02:00:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: improve assets (#2777)

Browse Source 
* add assets

* add libero results pifast:

* update

* update

* update size

* update naems:
:

* update training tokenizer
This commit is contained in:
Jade Choghari
2026-01-12 13:33:28 +01:00
committed by GitHub
parent 91ff9c4975
commit 473f1bd0e0
8 changed files with 129 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/source/sarm.mdx
+6
View File
@@ -4,6 +4,12 @@ SARM (Stage-Aware Reward Modeling) is a video-based reward modeling framework fo
**Paper**: [SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation](https://arxiv.org/abs/2509.25358)
<img
src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/lerobot/lerobot-sarm.png"
alt="An overview of SARM"
width="80%"
/>
## Why Reward Models?
Standard behavior cloning treats all demonstration frames equally, but real-world robot datasets are messy. They contain hesitations, corrections, and variable-quality trajectories. Reward models solve this by learning a generalizable notion of **task progress** from demonstrations: given video frames and a task description, they predict how close the robot is to completing the task (0→1). This learned "progress signal" can be used in multiple ways, two promising applications are: (1) **weighted imitation learning** (RA-BC), where high-progress frames receive more weight during policy training, and (2) **reinforcement learning**, where the reward model provides dense rewards for online or offline policy improvement.