Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Agent Reinforcement Learning on MPE Speaker-Listener
Loading...
-46
Return
MAPPO
-247.76
-195.38
-143
-90.62
Apr 8, 2026
Return
Latency (ms)
Updated 9d ago
Evaluation Results
Method
Method
Links
Return
Latency (ms)
MAPPO
Observation Setting=FO
2026.04
-46
6
KD-MARL
Observation Setting=LH
2026.04
-48
4
KD-MARL
Observation Setting=LH+A
2026.04
-50
3.9
QMIX
Observation Setting=FO
2026.04
-55
4.8
MAPPO
Observation Setting=LH
2026.04
-82
5.3
VDN
Observation Setting=FO
2026.04
-90
4.7
MAPPO
Observation Setting=LH+A
2026.04
-118
4
QMIX
Observation Setting=LH
2026.04
-138
4.6
VDN
Observation Setting=LH
2026.04
-170
4.5
QMIX
Observation Setting=LH+A
2026.04
-205
4.2
VDN
Observation Setting=LH+A
2026.04
-240
4.3
Feedback
Search any
task
Search any
task
