MushroomRL/mushroom-rl
MushroomRL/mushroom-rl has 948 GitHub stars and 166 forks. GitHot measured +2 stars in 24 hours and +1 in 7 days. Last checked 2026-11-22 13:17 UTC. Last push 2026-11-17.
Measured star growth
- in 24h
- +2
- in 7 days
- +1
- in 15 days
- Collecting history
- in 1 month
- Collecting history
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
About
Python library for Reinforcement Learning.
Machine LearningREADME.md
OriginalMushroomRL
.. image:: https://github.com/MushroomRL/mushroom-rl/actions/workflows/continuous_integration.yml/badge.svg?branch=dev :target: https://github.com/MushroomRL/mushroom-rl/actions/workflows/continuous_integration.yml :alt: Continuous Integration
.. image:: https://app.readthedocs.org/projects/mushroomrl/badge/?version=dev :target: https://mushroomrl.readthedocs.io/en/dev/?badge=dev :alt: Documentation Status
.. image:: https://qlty.sh/gh/MushroomRL/projects/mushroom-rl/maintainability.svg :target: https://qlty.sh/gh/MushroomRL/projects/mushroom-rl :alt: Maintainability
.. image:: https://qlty.sh/gh/MushroomRL/projects/mushroom-rl/coverage.svg :target: https://qlty.sh/gh/MushroomRL/projects/mushroom-rl :alt: Test Coverage
MushroomRL: Reinforcement Learning Python library.
.. contents:: Contents of this document: :depth: 2
What is MushroomRL
MushroomRL is a Python Reinforcement Learning (RL) library whose modularity allows to easily use well-known Python libraries for tensor computation (e.g. PyTorch, Tensorflow) and RL benchmarks (e.g. Gymnasium, PyBullet, Deepmind Control Suite). It allows to perform RL experiments in a simple way providing classical RL algorithms (e.g. Q-Learning, SARSA, FQI), and deep RL algorithms (e.g. DQN, DDPG, SAC, TD3, TRPO, PPO).
Full documentation and tutorials available here <http://mushroomrl.readthedocs.io/en/latest/>_.
Installation
You can do a minimal installation of MushroomRL with:
.. code:: shell
pip install mushroom-rl
Installing everything
MushroomRL contains also some optional components e.g., support for Gymnasium
environments, Atari 2600 games from the Arcade Learning Environment, and the support
for physics simulators such as Pybullet and MuJoCo.
Support for these classes is not enabled by default.
To install the whole set of features, you will need additional packages installed. You can install everything by running:
.. code:: shell
pip install mushroom-rl[all]
This will install every dependency of MushroomRL, except Box2D, PyBullet and Isaac Sim. For ubuntu>20.04, you may need to install pygame and gym dependencies:
.. code:: shell
sudo apt -y install libsdl-image1.2-dev libsdl-mixer1.2-dev libsdl-ttf2.0-dev \
libsdl1.2-dev libsmpeg-dev libportmidi-dev ffmpeg libswscale-dev \
libavformat-dev libavcodec-dev swig
Notice that you still need to install some of these dependencies for different operating systems, e.g. swig for macOS
Below is the code that you need to run to install the live monitors dependencies:
.. code:: shell
pip install mushroom-rl[monitors]
Isaac Sim
Support for NVIDIA Isaac Sim environments is provided by a separate extra, which is deliberately
not part of [all]:
.. code:: shell
pip install mushroom-rl[isaacsim]
Install it in a dedicated environment, never alongside the other extras:
Isaac Simsupports Python 3.12 only (its metadata declaresRequires-Python: ==3.12.*), whereasMushroomRLalso supports Python 3.11.isaacsim-corepins exact versions of packages shared with the other extras (mujoco==3.11.0,mujoco-warp==3.11.0,torch==2.11.0,scipy==1.17.0), so they cannot move past those versions in the same environment.
Running the Isaac Sim environments additionally requires an NVIDIA RTX GPU. They are therefore not
covered by continuous integration, and their tests are skipped unless isaacsim can be imported.
Editable Installation
You can also perform a local editable installation by using:
.. code:: shell
pip install -e .
To install also optional dependencies:
.. code:: shell
pip install -e .[all]
How to set and run and experiment
To run experiments, MushroomRL requires a script file that provides the necessary information for the experiment. Follow the scripts in the "examples" folder to have an idea of how an experiment can be run.
For instance, to run a quick experiment with one of the provided example scripts, run:
.. code:: shell
python3 examples/papers/car_on_hill_fqi.py
Cite MushroomRL
If you are using MushroomRL for your scientific publications, please cite:
.. code:: bibtex
@article{JMLR:v22:18-056,
author = {Carlo D'Eramo and Davide Tateo and Andrea Bonarini and Marcello Restelli and Jan Peters},
title = {MushroomRL: Simplifying Reinforcement Learning Research},
journal = {Journal of Machine Learning Research},
year = {2021},
volume = {22},
number = {131},
pages = {1-5},
url = {http://jmlr.org/papers/v22/18-056.html}
}
How to contact us
For any question, drop an e-mail at [email protected].
Follow us on Twitter @Mushroom_RL <https://twitter.com/mushroom_rl>_!
Explore related projects
Loading…