HanbumKo/distributed-wqmix

distributed training code of Weighted QMIX (NeurIPS 2020)

A distributed implementation of Weighted QMIX: Expanding Monotonic Value Function Factorisation with Ray

python train.py

paper https://arxiv.org/abs/2006.10800

Env https://github.com/oxwhirl/smac

Reference

Most of training code from

https://github.com/oxwhirl/wqmix

https://github.com/starry-sky6688/StarCraft