Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Agent Reinforcement Learning Transfer on SMAC 8m to 8mvs9m
Loading...
0.53
Steps to 80% Reward (x10^6)
GCT-MARL
0.3176
1.7513
3.185
4.6187
Jun 23, 2026
Steps to 80% Reward (x10^6)
Final Win Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Steps to 80% Reward (x10^6)
Final Win Rate
GCT-MARL
Scenario=8m → 8mvs9m
2026.06
0.53
100
MAIL
Scenario=8m → 8mvs9m
2026.06
2.25
100
MALT
Scenario=8m → 8mvs9m
2026.06
2.41
89
EPC
Scenario=8m → 8mvs9m
2026.06
3.02
89
Distilled
Scenario=8m → 8mvs9m
2026.06
4.28
86
PSMARL
Scenario=8m → 8mvs9m
2026.06
5.23
91
Baseline
Scenario=8m → 8mvs9m
2026.06
5.84
94
Feedback
Search any
task
Search any
task
