How to Install#

Install from source#

To install the latest development release, you can install directly from GitHub’s repository.

pip install git+

Install with pip#

First, please make sure that the latest pip version is installed in your working environment.

python3 -m pip install -U pip

Then you can install motornet using a simple pip install command.

python3 -m pip install motornet

Install with Anaconda#

Installation via Anaconda is not currently supported.


There is no third-party software required to run MotorNet. However, some freely available python dependencies are required.

  • PyTorch: MotorNet relies on PyTorch to create tensors and build the graph.

  • NumPy: For array and matrix computations when not using tensors.

  • Gymnasium: motornet environments inherit from gymnasium environments.

  • Matplotlib: For plotting utilities, mainly in the module.

If you are running a version earlier than 0.2.0, which relies on TensorFlow, the requirements are as follow.

  • TensorFlow: MotorNet is first and foremost built on TensorFlow. However, the standard TensorFlow toolbox is not compatible with recent Apple machines equipped with M1 silicon chips, and users must rely on an adapted version called tensorflow-macos. When installing MotorNet, the routine will automatically check the machine’s OS platform and hardware to assess whether to solve for the tensorflow or tensorflow-macos dependency.

  • NumPy: For array and matrix computations when not using tensors.

  • Matplotlib: For plotting utilities, mainly in the module.

  • IPython: Mainly for callbacks that output training metrics during model training.

  • joblib: For parallelization routines in the parallelizer script.


There are several tutorials available to get you started, available in the repository‘s examples folder, as well as on the documentation website. Hopefully they will give a sense of how the API is supposed to work.


Tutorials and API documentation for version 0.1.5 are still available on the website and GitHib repository for those who wish to consult them. They will remain available for the foreseeable future.