This repository was based on the mujoco playground done by Google deepmind, I just added the training code and xml (that adapted from the xml from mujoco menagerie) for the Unitree Go2 Walking Policy.
git clone git@github.com:bhenriquezsoto/mujoco-playground.git- Install CUDA 12 jax:
python3 -m pip install -U "jax[cuda12]"- Verify GPU backend:
python3 -c "import jax; print(jax.default_backend())"should print gpu
- Verify GPU backend:
- Install playground:
python3 -m pip install -e ".[all]" - Verify installation (and download Menagerie):
python3 -c "import mujoco_playground"
If you use Playground in your scientific works, please cite it as follows:
@misc{mujoco_playground_2025,
title = {MuJoCo Playground: An open-source framework for GPU-accelerated robot learning and sim-to-real transfer.},
author = {Zakka, Kevin and Tabanpour, Baruch and Liao, Qiayuan and Haiderbhai, Mustafa and Holt, Samuel and Luo, Jing Yuan and Allshire, Arthur and Frey, Erik and Sreenath, Koushil and Kahrs, Lueder A. and Sferrazza, Carlo and Tassa, Yuval and Abbeel, Pieter},
year = {2025},
publisher = {GitHub},
url = {https://github.com/google-deepmind/mujoco_playground}
}The texture used in the rough terrain for the locomotion environments is from Polyhaven and licensed under CC0.
All other content in this repository is licensed under the Apache License, Version 2.0. A copy of this license is provided in the top-level LICENSE file in this repository. You can also obtain it from https://www.apache.org/licenses/LICENSE-2.0.
This is not an officially supported Google product.