Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-agent reinforcement learning on GRF academy_counterattack_hard (4v3)
Loading...
69
Mean Win Rate
FULLOBS
49.24
54.37
59.5
64.63
Jun 28, 2026
Mean Win Rate
Updated 26d ago
Evaluation Results
Method
Method
Links
Mean Win Rate
FULLOBS
Algorithm=MAPPO
2026.06
69
T2MAC
Algorithm=MAPPO
2026.06
66
HiComm
Algorithm=MAPPO
2026.06
66
CACOM
Algorithm=MAPPO
2026.06
63
FULLOBS
Algorithm=IPPO
2026.06
59
PARTIALOBS
Algorithm=MAPPO
2026.06
59
HiComm
Algorithm=IPPO
2026.06
56
CACOM
Algorithm=IPPO
2026.06
53
T2MAC
Algorithm=IPPO
2026.06
53
PARTIALOBS
Algorithm=IPPO
2026.06
50
Feedback
Search any
task
Search any
task