Metadata-Version: 2.1
Name: pyg-multiagent
Version: 0.0.4
Summary: Python Package for Multi-Agent Learning
Home-page: https://github.com/rainorangelemon/pytorch_geometric_multiagent
Download-URL: https://github.com/rainorangelemon/pytorch_geometric_multiagent/archive/0.0.4.tar.gz
Author: Chenning Yu
Author-email: Chenning Yu <rainorangelemon@gmail.com>
Project-URL: Homepage, https://github.com/rainorangelemon/pytorch_geometric_multiagent
Project-URL: Bug Tracker, https://github.com/rainorangelemon/pytorch_geometric_multiagent/issues
Keywords: deep-learning,pytorch,geometric-deep-learning,graph-neural-networks,pytorch-geometric,multi-agent
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: tqdm
Requires-Dist: numpy
Requires-Dist: matplotlib
Requires-Dist: scipy
Requires-Dist: cvxpy
Provides-Extra: benchmark
Requires-Dist: wandb ; extra == 'benchmark'
Provides-Extra: dev
Requires-Dist: pytest ; extra == 'dev'
Requires-Dist: pytest-cov ; extra == 'dev'
Requires-Dist: pre-commit ; extra == 'dev'
Provides-Extra: full
Requires-Dist: tqdm ; extra == 'full'
Requires-Dist: numpy ; extra == 'full'
Requires-Dist: matplotlib ; extra == 'full'
Requires-Dist: scipy ; extra == 'full'
Requires-Dist: cvxpy ; extra == 'full'
Provides-Extra: test
Requires-Dist: pytest ; extra == 'test'
Requires-Dist: pytest-cov ; extra == 'test'

![logo](https://raw.githubusercontent.com/rainorangelemon/pygma_sphinx_theme/master/pygma_sphinx_theme/static/img/text_logo.png)

-----------------------

**[Documentation](https://pytorch-geometric-multiagent.readthedocs.io/en/latest/)**

The official repo for the CoRL 2022 paper 'Learning Control Admissibility Models with Graph Neural Networks for Multi-Agent Navigation' [[project page](https://rainorangelemon.github.io/CoRL2022/)]

<!--The current repo only includes GNN for control. For planning methods such as CBS and SIPP, please stay tuned.-->

The ultimate goal is to provide a benchmark and a handy tool for GNN researchers to conduct evaluations properly and fairly for multi-agent tasks.

**Note: The current repo is actively under maintenance.**

## Installation

```bash
conda create -n pygma python=3.8
conda activate pygma
# install pytorch, modify the following line according to your environment
conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
# install torch geometric, refer to https://github.com/pyg-team/pytorch_geometric
conda install pyg -c pyg
# install pyg_multiagent
pip install pyg_multiagent
```
