Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Agent Coordination on XOR game n=k=2 (train eval)
Loading...
100
Success Rate (Greedy Policy pi*)
MAT
-4
23
50
77
May 7, 2026
Success Rate (Greedy Policy pi*)
Success Rate (Stochastic Policy pi)
Updated 23d ago
Evaluation Results
Method
Method
Links
Success Rate (Greedy Policy pi*)
Success Rate (Stochastic Policy pi)
MAT
2026.05
100
100
Diamond Attention
structured random mask...
2026.05
100
100
MAPPO
2026.05
0
50
QMIX
2026.05
0
50
IPPO
2026.05
0
50
MASAC
2026.05
0
50
pH-MARL
2026.05
0
50
GSA
2026.05
0
50
Diamond Attention (w/o mask)
structured random mask...
2026.05
0
50
Diamond Attention (dropout)
dropout=enabled
2026.05
0
50
Feedback
Search any
task
Search any
task