Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-agent coordination on Overcooked-AI Pipeline 3-agent
Loading...
155.5
Mean Reward
MAPPO+IS
51.5
78.5
105.5
132.5
May 14, 2026
Mean Reward
Std Dev Reward
Maximum Reward
Updated 16d ago
Evaluation Results
Method
Method
Links
Mean Reward
Std Dev Reward
Maximum Reward
MAPPO+IS
Layout=Pipeline, Team...
2026.05
155.5
48.4
272
HAPPO+IS
Layout=Pipeline, Team...
2026.05
136.6
29.7
207
HAPPO
Layout=Pipeline, Team...
2026.05
121.3
15.3
150
SP
Layout=Pipeline, Team...
2026.05
119.1
35.6
204
MAPPO
Layout=Pipeline, Team...
2026.05
105.1
16.8
134
FCP
Layout=Pipeline, Team...
2026.05
55.5
7.8
67
Feedback
Search any
task
Search any
task
