Multi-Agent Reinforcement Learning on SMAC Stalker-Zealot Seen (train)
63.4Mean Win RateSTAIRS-Former
Evaluation Results
| Method | Links | |
|---|---|---|
| STAIRS-Former2026.03 | 63.4 | |
| HiSSD2026.03 | 45.9 | |
| ODIS2026.03 | 34.8 | |
| UPDeT-m2026.03 | 20.3 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| STAIRS-Former2026.03 | 63.4 | |
| HiSSD2026.03 | 45.9 | |
| ODIS2026.03 | 34.8 | |
| UPDeT-m2026.03 | 20.3 |