Installation

GNN-RL is tested under the the following environment and dependencies:


Python >=3.6
PyTorch 1.9.1 (CUDA 11.1)
CUDA Toolkit 11.1


GNN-RL supports multiple Graph libraries as backends, e.g., DGL, PyG.


DGL (with CUDA 11.1)
PyG (torch-geometric)


GNN-RL installation from pip

Before installing the GNN-RL, installing the required PyTorch through pip,

pip install torch==1.9.1+cu111 torchvision==0.10.1+cu111 torchaudio==0.9.1 -f https://download.pytorch.org/whl/torch_stable.html

installing the required Graph libraries,

pip install torch-scatter torch-sparse torch-cluster torch-spline-conv torch-geometric -f https://data.pyg.org/whl/torch-1.9.0+cu111.html
pip install dgl-cu111 -f https://data.dgl.ai/wheels/repo.html

Install the gnnrl,

pip install gnnrl

GNN-RL installation from conda

Will release soon