Installation

To install Maze with pip, run:

pip install -U maze-rl

Note

Pip does not install PyTorch, you need to make sure it is available in your Python environment.

Note

For the graph neural network perception blocks you also need to install torch_scatter by following the instructions here.

Note

The graphical representation of models requires pygraphviz to be installed, see this page for detailed information on the installation instructions.

Note

Maze is compatible with Python 3.9 to 3.10. We encourage you to start with Python 3.10. If you intend to use popular environments like Atari or Box2D you might need to install a few additional dependencies because of this OpenAI gym issue .

For Debian systems

apt install libjpeg8-dev zlib1g-dev

more info on building pillow.

Note

Using Box2D environments such as LunarLander, additionally require the installation of swig and box2d-py.

For Debian systems this can be simply done with

apt install swig

and

pip install gymnasium[box2d]

To install the bleeding-edge development version from GitHub, first clone the repo.

git clone https://github.com/enlite-ai/maze.git
cd maze

Finally, install the project with pip in development mode and you are ready to start developing.

pip install -e .

Alternatively you can install with pip directly from the GitHub repository

pip install -e git+https://github.com/enlite-ai/maze.git