Welcome Stable-baselines3 to the Hugging Face Hub 🤗

At Hugging Face, we are contributing to the ecosystem for Deep Reinforcement Learning researchers and enthusiasts. That’s why we’re happy to announce that we integrated Stable-Baselines3 to the Hugging Face Hub.

Stable-Baselines3 is one of the most popular PyTorch Deep Reinforcement Learning library that makes it easy to train and test your agents in a variety of environments (Gym, Atari, MuJoco, Procgen...). With this integration, you can now host your saved models 💾 and load powerful models from the community.

In this article, we’re going to show how you can do it.

Installation

To use stable-baselines3 with Hugging Face Hub, you just need to install these 2 libraries:

pip install huggingface_hub
pip install huggingface_sb3

Finding Models

We’re currently uploading saved models of agents playing Space Invaders, Breakout, LunarLander and more. On top of this, you can find all stable-baselines-3 models from the community here

When you found the model you need, you just have to copy the repository id:

Download a model from the Hub

The coolest feature of this integration is that you can now very easily load a saved model from Hub to Stable-baselines3.

In order to do that you just need to copy the repo-id that contains your saved model and the name of the saved model zip file in the repo.

For instancesb3/demo-hf-CartPole-v1:

Sharing a model to the Hub

In just a minute, you can get your saved model in the Hub.

First, you need to be logged in to Hugging Face to upload a model:

• If you're using Colab/Jupyter Notebooks:

from huggingface_hub import notebook_login
notebook_login()

• Else:

huggingface-cli login

Then, in this example, we train a PPO agent to play CartPole-v1 and push it to a new repo ThomasSimonini/demo-hf-CartPole-v1 `

Try it out and share your models with the community!

What's next?

In the coming weeks and months, we will be extending the ecosystem by:

The best way to keep in touch is to join our discord server to exchange with us and with the community.

👉 The tutorial