Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Agent Reinforcement Learning on SMAC 3m to 8m
Loading...
100
Final Win Rate
GCT-MARL
74
80.75
87.5
94.25
Jun 23, 2026
Final Win Rate
Steps to 80% Reward (×10^5)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Final Win Rate
Steps to 80% Reward (×10^5)
GCT-MARL
2026.06
100
1.5
MAIL
2026.06
100
4.91
ASALT
2026.06
82
-
CORAL
transfer_scheme=agent-...
2026.06
81
-
LA-QTransformer
2026.06
81
-
CORAL
2026.06
81
2.8
LA-QT
2026.06
81
1.72
Baseline
training=from scratch...
2026.06
80
-
Baseline
2026.06
80
5.1
DANN
transfer_scheme=agent-...
2026.06
79
-
DANN
2026.06
79
3.1
CycleGAN
transfer_scheme=agent-...
2026.06
75
-
CycleGAN
2026.06
75
4.1
Feedback
Search any
task
Search any
task
