Installation

Install TorchRL

You can install TorchRL from PyPi.

pip install torchrl

For more details, or for installing nightly versions, see the TorchRL installation guide.

Install BenchMARL

You can just install it from PyPi

pip install benchmarl

Or also clone it locally to access the configs and scripts

git clone https://github.com/facebookresearch/BenchMARL.git
pip install -e BenchMARL

Install optional packages

By default, BenchMARL has only the core requirements. Here are some optional packages you may want to install.

Logging

You may want to install the following rendering and logging tools

pip install wandb moviepy torchvision av

Install environments

All environment dependencies are optional in BenchMARL and can be installed separately.

VMAS

GitHub

pip install vmas

PettingZoo

GitHub

pip install "pettingzoo[all]"

MeltingPot

GitHub

pip install "dm-meltingpot"

SMACv2

GitHub

Follow the instructions on the environment repository.

Here is how we install it on linux.

Install models

Some models in BenchMARL require extra dependencies that can be installed separately

GNN

GNN models require pytorch_geometric.

To install it, you can run:

pip install torch_geometric

For more information, see the installation instructions of the library.