Multi-Agent Reinforcement Learning on SMAC 5m_vs_6m v2
53.9Win RateACL-LFT
Evaluation results
| Method | Links | |
|---|---|---|
| ACL-LFTRL-Method=QPLEX2025.10 | 53.9 | |
| ACL-LFTRL-Method=MAPPO2025.10 | 52.7 | |
| ACL-LFTRL-Method=QMIX2025.10 | 52.4 | |
| AMAGORL-Method=QPLEX2025.10 | 49.5 | |
| AMAGORL-Method=QMIX2025.10 | 48.3 | |
| AMAGORL-Method=MAPPO2025.10 | 48.1 | |
| MambaRL-Method=QPLEX2025.10 | 47.8 | |
| ToSTRL-Method=QPLEX2025.10 | 47.3 | |
| ToSTRL-Method=QMIX2025.10 | 46.9 | |
| ToSTRL-Method=MAPPO2025.10 | 46.3 | |
| MambaRL-Method=MAPPO2025.10 | 46.2 | |
| MambaRL-Method=QMIX2025.10 | 46.1 | |
| TransformerRL-Method=QPLEX2025.10 | 45.6 | |
| TransformerRL-Method=MAPPO2025.10 | 44.5 | |
| TransformerRL-Method=QMIX2025.10 | 44.3 |