LeRobot

Team

community

https://huggingface.co/docs/lerobot

LeRobotHF

Activity Feed Request to join this org

AI & ML interests

State-of-the-art Machine Learning for real-world robotics

Recent Activity

pepijn223 updated a dataset about 16 hours ago

lerobot/openarms-hardware-modifications

CarolinePascal updated a dataset about 18 hours ago

lerobot/droid_1.0.1

pepijn223 published a Space 1 day ago

lerobot/robot-folding

View all activity

Papers

Robot Learning: A Tutorial

View all Papers

pepijn223

updated a dataset about 16 hours ago

lerobot/openarms-hardware-modifications

Updated about 16 hours ago • 2

CarolinePascal

updated a dataset about 18 hours ago

lerobot/droid_1.0.1

Viewer • Updated about 11 hours ago • 27.4M • 12.1k • 12

pepijn223

published a Space 1 day ago

Unfolding Robotics: Open-Source Shirt Folding from Data to Deployment

🤖

Explore a robot that folds clothes with open‑source tools

pepijn223

published a dataset 2 days ago

lerobot/openarms-hardware-modifications

Updated about 16 hours ago • 2

pepijn223

updated a Space 2 days ago

Unfolding Robotics: Open-Source Shirt Folding from Data to Deployment

🤖

Explore a robot that folds clothes with open‑source tools

pepijn223

in lerobot/robot-folding 2 days ago

few additions & improvements

#16 opened 4 days ago by

imstevenpmwork

in lerobot/robot-folding 4 days ago

few additions & improvements

#16 opened 4 days ago by

imstevenpmwork

CarolinePascal

in lerobot/robot-folding 8 days ago

fix(CLI tools): fixing CLI tools examples

#15 opened 8 days ago by

CarolinePascal

qgallouedec

posted an update 9 days ago

Post

2159

TRL v1.0 is out!

Hugging Face's TRL library is downloaded 3 million times a month. Over 130k models trained with it are public on the Hub, and major projects like @unsloth and @axolotl-ai-co build directly on top of it. v1.0 is the moment we acknowledged that responsibility explicitly, with a real stability contract.

The field hasn't settled. Building stable software in a domain that keeps invalidating its own assumptions is the actual problem we're solving. The answer is a design that can absorb the next shift without breaking what people rely on.

What's in v1.0:
Deep Hugging Face integration, low infrastructure burden
What's next: asynchronous GRPO, better scaling support, and making training legible enough that agents can inspect and steer it.