Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-agent pathfinding on POGEMA
Loading...
2.16
Average Throughput (Random)
Expert
0.132
0.6585
1.185
1.7115
Apr 7, 2026
Average Throughput (Random)
Average Throughput (Mazes)
Average Throughput (Warehouse)
Average Throughput (Cities-tiles)
Updated 11d ago
Evaluation Results
Method
Method
Links
Average Throughput (Random)
Average Throughput (Mazes)
Average Throughput (Warehouse)
Average Throughput (Cities-tiles)
Expert
Task Specificity=Singl...
2026.04
2.16
1.55
-
-
MARL-GPT
Training Scope=Multi-E...
2026.04
1.16
0.96
1.02
2.72
CQL
Training Scope=Single-...
2026.04
0.26
0.14
0.17
0.66
BC
Training Scope=Single-...
2026.04
0.24
0.1
0.14
0.46
BC-LSTM
Training Scope=Single-...
2026.04
0.23
0.11
0.12
0.49
DT
Training Scope=Single-...
2026.04
0.22
0.12
0.13
0.68
RATE
Training Scope=Single-...
2026.04
0.21
0.12
0.13
0.65
Feedback
Search any
task
Search any
task
