Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Agent Reinforcement Learning on SMAC 3s5z v1
Loading...
99.4
Normalized Win Rate
MAST
31.384
49.042
66.7
84.358
Sep 28, 2024
Normalized Win Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Normalized Win Rate
MAST
Alg.=RES, Sparsity=85%...
2024.09
99.4
MAST
Alg.=Q-MIX, Sparsity=9...
2024.09
99
MAST
Alg.=WQ-MIX, Sparsity=...
2024.09
96.1
Tiny
Alg.=RES, Sparsity=85%...
2024.09
95.1
RigL
Alg.=RES, Sparsity=85%...
2024.09
92.8
SET
Alg.=RES, Sparsity=85%...
2024.09
90.3
SS
Alg.=RES, Sparsity=85%...
2024.09
89
RLx2
Alg.=RES, Sparsity=85%...
2024.09
86.2
Tiny
Alg.=WQ-MIX, Sparsity=...
2024.09
70.7
Tiny
Alg.=Q-MIX, Sparsity=9...
2024.09
68.2
SS
Alg.=WQ-MIX, Sparsity=...
2024.09
62.5
RLx2
Alg.=WQ-MIX, Sparsity=...
2024.09
60.7
SET
Alg.=WQ-MIX, Sparsity=...
2024.09
56
SET
Alg.=Q-MIX, Sparsity=9...
2024.09
52.3
RigL
Alg.=WQ-MIX, Sparsity=...
2024.09
50.4
RLx2
Alg.=Q-MIX, Sparsity=9...
2024.09
50.1
RigL
Alg.=Q-MIX, Sparsity=9...
2024.09
45.2
SS
Alg.=Q-MIX, Sparsity=9...
2024.09
34
Feedback
Search any
task
Search any
task
