Value-Decomposition Networks For Cooperative Multi-Agent Learning

Benchmark Model Rank Results
smac-on-smac-def-armored-parallelVDN#3Median Win Rate: 5.0
smac-on-smac-def-armored-sequentialVDN#1Median Win Rate: 96.9
smac-on-smac-def-infantry-parallelVDN#2Median Win Rate: 95.0
smac-on-smac-def-infantry-sequentialVDN#4Median Win Rate: 96.9
smac-on-smac-def-outnumbered-parallelVDN#4Median Win Rate: 0.0
smac-on-smac-def-outnumbered-sequentialVDN#3Median Win Rate: 15.6
smac-on-smac-off-complicated-parallelVDN#1Median Win Rate: 70.0
smac-on-smac-off-distant-parallelVDN#1Median Win Rate: 85.0
smac-on-smac-off-hard-parallelVDN#1Median Win Rate: 15.0
smac-on-smac-off-near-parallelVDN#2Median Win Rate: 90.0
smac-on-smac-off-superhard-parallelVDN#2Median Win Rate: 0.0