Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Cooperative Multi-Agent Reinforcement Learning on SMAC 3s5z map
Loading...
18.7
Return
QMIX
6.532
9.691
12.85
16.009
Apr 8, 2026
Return
Win rate
TPS
Updated 9d ago
Evaluation Results
Method
Method
Links
Return
Win rate
TPS
QMIX
Configuration=FO
2026.04
18.7
60.48
12
MAPPO
Configuration=FO
2026.04
18.5
68.31
11.5
KD-MARL
Configuration=LH
2026.04
17.2
60.28
9.7
MAPPO
Configuration=LH
2026.04
16.8
55.66
13.5
VDN
Configuration=FO
2026.04
16.5
53.42
10.8
KD-MARL
Configuration=LH+A
2026.04
16.5
58.17
7.9
QMIX
Configuration=LH
2026.04
15
50.12
10.2
MAPPO
Configuration=LH+A
2026.04
13.5
42.54
12.2
VDN
Configuration=LH
2026.04
11
40.33
9.8
QMIX
Configuration=LH+A
2026.04
10.5
36.95
6
VDN
Configuration=LH+A
2026.04
7
24.12
8
Feedback
Search any
task
Search any
task
