Multi-agent reinforcement learning on SMAC v2 (seen)
31.3Terran Win Rate
STAIRS-Former
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.03 | 31.3 | 32.5 | 29.2 | 31 | |
2026.03 | 24.9 | 29.5 | 21 | 25.1 | |
2026.03 | 15.2 | 12.7 | 10.4 | 12.7 | |
2026.03 | 10.9 | 9.9 | 6.6 | 9.1 |
STAIRS-Former
| Method | Links | ||||
|---|---|---|---|---|---|
2026.03 | 31.3 | 32.5 | 29.2 | 31 | |
2026.03 | 24.9 | 29.5 | 21 | 25.1 | |
2026.03 | 15.2 | 12.7 | 10.4 | 12.7 | |
2026.03 | 10.9 | 9.9 | 6.6 | 9.1 |