Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Cooperative Multi-Agent Reinforcement Learning on SMAC 5m_vs_6m map
Loading...
19.1
Return
QMIX
6.516
9.783
13.05
16.317
Apr 8, 2026
Return
Win Rate
TPS
Updated 9d ago
Evaluation Results
Method
Method
Links
Return
Win Rate
TPS
QMIX
Configuration=FO
2026.04
19.1
58.93
12.3
MAPPO
Configuration=FO
2026.04
18
61.85
12
KD-MARL
Configuration=LH
2026.04
16.8
58.66
10
MAPPO
Configuration=LH
2026.04
16.5
58.09
14
KD-MARL
Configuration=LH+A
2026.04
16.5
56.15
8
VDN
Configuration=FO
2026.04
16
50.1
11
QMIX
Configuration=LH
2026.04
14
50.12
10.5
MAPPO
Configuration=LH+A
2026.04
13
44.78
12.7
VDN
Configuration=LH
2026.04
11
38.22
10.2
QMIX
Configuration=LH+A
2026.04
10
38.79
6.2
VDN
Configuration=LH+A
2026.04
7
25.14
8.2
Feedback
Search any
task
Search any
task
