ma-league's Introduction

- Under construction

This repository based on components of oxwhirl/pymarl but does not hold a dependency to it.

Multi-Agent League

Framework to train Multi-Agent algorithms in Vanilla, Self-Play or League-Play.

See Wiki for in-depth guides and visit Getting Started

Multi-Agent Environment

The main supported MA Environment is: https://github.com/PMatthaei/ma-env

Sources and Codebase from

https://github.com/oxwhirl/pymarl/tree/master/src

@article{samvelyan19smac,
  title = {{The} {StarCraft} {Multi}-{Agent} {Challenge}},
  author = {Mikayel Samvelyan and Tabish Rashid and Christian Schroeder de Witt and Gregory Farquhar and Nantas Nardelli and Tim G. J. Rudner and Chia-Man Hung and Philiph H. S. Torr and Jakob Foerster and Shimon Whiteson},
  journal = {CoRR},
  volume = {abs/1902.04043},
  year = {2019},
}

https://github.com/shariqiqbal2810/REFIL

@InProceedings{iqbal2021refil,
  title={Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning},
  author={Iqbal, Shariq and de Witt, Christian A Schroeder and Peng, Bei and B{\"o}hmer, Wendelin and Whiteson, Shimon and Sha, Fei},
  booktitle =    {Proceedings of the 38th International Conference on Machine Learning},
  year =     {2021},
  series =   {Proceedings of Machine Learning Research},
  publisher =    {PMLR},
}

Recommend Projects