This is a pytorch implementation of the multi-agent reinforcement learning algrithms, QMIX and VDN, both of which are the state of art MARL algrithms. We trained these algrithms on SMAC, which is the decentralised micromanagement scenario of StarCraft II.
$ python main.py --evaluate_epoch=100 --map=3mDirectly run the main.py, then the two algrithms will be respectively tested on map '3m' for 100 episodes, using the pretrained model.
Although qmix and vdn are the state of art multi-agent algrithms, they are unstable sometimes, you need to independently run several times to get better performence.
