Multi-agent reinforcement learning on SMAC v2 (overall)
30.3Total Mean Win RateSTAIRS-Former
Evaluation Results
| Method | Links | |
|---|---|---|
| STAIRS-Former2026.03 | 30.3 | |
| HiSSD2026.03 | 24.4 | |
| ODIS2026.03 | 11.5 | |
| UPDeT-m2026.03 | 7.4 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| STAIRS-Former2026.03 | 30.3 | |
| HiSSD2026.03 | 24.4 | |
| ODIS2026.03 | 11.5 | |
| UPDeT-m2026.03 | 7.4 |