Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning

Benchmark Model Rank Results
smac-on-smac-def-armored-parallelMASAC#8Median Win Rate: 0.0
smac-on-smac-def-armored-sequentialMASAC#10Median Win Rate: 0.0
smac-on-smac-def-infantry-parallelMASAC#8Median Win Rate: 30.0
smac-on-smac-def-infantry-sequentialMASAC#9Median Win Rate: 37.5
smac-on-smac-def-outnumbered-parallelMASAC#8Median Win Rate: 0.0
smac-on-smac-def-outnumbered-sequentialMASAC#9Median Win Rate: 0.0
smac-on-smac-off-complicated-parallelMASAC#8Median Win Rate: 0.0
smac-on-smac-off-distant-parallelMASAC#5Median Win Rate: 0.0
smac-on-smac-off-hard-parallelMASAC#8Median Win Rate: 0.0
smac-on-smac-off-near-parallelMASAC#8Median Win Rate: 0.0
smac-on-smac-off-superhard-parallelMASAC#8Median Win Rate: 0.0