Skip to main content

Musculoskeletal environments simulated in MuJoCo

Project description

Support Ukraine PyPI Documentation Status PyPI - License PRs Welcome Downloads Open In Colab

MyoSuite is a collection of musculoskeletal environments and tasks simulated with the MuJoCo physics engine and wrapped in the OpenAI gym API to enable the application of Machine Learning to bio-mechanic control problems

Below is an overview of the tasks in the MyoSuite. Full task details are available here, and baseline details are available here TasksALL

Getting Started

You will need Python 3.7.1 or later versions. At this moment the library has been tested only on MacOs and Linux with MuJoCo v2.1.0.

It is recommended to use Miniconda and to create a separate environment with

conda create --name myosuite python=3.7.1
conda activate myosuite

It is possible to install MyoSuite with:

pip install -U myosuite

for advance installation see here.

Test your installation using (this will return also a list of all the current environments):

python myosuite/tests/

You can also visualize the environments with random controls using the command below:

$ python myosuite/utils/ --env_name myoElbowPose1D6MRandom-v0

NOTE: If the visualization results in a GLFW error, this is because mujoco-py does not see some graphics drivers correctly. This can usually be fixed by explicitly loading the correct drivers before running the python script. See this page for details.


It is possible to create and interface with MyoSuite environments like any other OpenAI gym environments. For example, to use the myoElbowPose1D6MRandom-v0 environment it is possible simply to run: Open In Colab

import myosuite
import gym
env = gym.make('myoElbowPose1D6MRandom-v0')
for _ in range(1000):
  env.step(env.action_space.sample()) # take a random action

You can find tutorials on how to load MyoSuite models/tasks, train them and visualize their outcome. Also, you can find baselines to test some pre-trained policies.


MyoSuite is licensed under the Apache License


If you find this repository useful in your research, please consider giving a star ⭐ and cite it by using the following BibTeX entrys.

  author =       {Vittorio, Caggiano AND Huawei, Wang AND Guillaume, Durandau AND Massimo, Sartori AND Vikash, Kumar},
  title =        {MyoSuite: A fast and contact-rich simulation suite for musculoskeletal motor control},
  howpublished = {\url{}},
  year =         {2022}

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

MyoSuite-1.0.1-py2.py3-none-any.whl (17.6 MB view hashes)

Uploaded Python 2 Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page