DOP: Off-Policy Multi-Agent Decomposed Policy Gradients

2s3z

2 Zealots 3 Stalkers vs 2 Zealots 3 Stalkers

MMM2

1 Medivac, 2 Marauders, and 7 Marines vs 1 Medivac, 3 Marauders, and 8 Marines


so_many_baneling

7 ally Zealots vs 32 enemy Banelings