Multi-Agent Reinforcement Learning on SMAC corridor v2
79.2Win RateACL-LFT
Evaluation results
| Method | Links | |
|---|---|---|
| ACL-LFTRL-Method=QPLEX2025.10 | 79.2 | |
| ACL-LFTRL-Method=QMIX2025.10 | 78.6 | |
| ACL-LFTRL-Method=MAPPO2025.10 | 77.9 | |
| AMAGORL-Method=QPLEX2025.10 | 76.3 | |
| AMAGORL-Method=QMIX2025.10 | 75 | |
| AMAGORL-Method=MAPPO2025.10 | 74.3 | |
| MambaRL-Method=QPLEX2025.10 | 73.5 | |
| ToSTRL-Method=QPLEX2025.10 | 72.9 | |
| MambaRL-Method=QMIX2025.10 | 71.2 | |
| TransformerRL-Method=QPLEX2025.10 | 70.6 | |
| ToSTRL-Method=QMIX2025.10 | 70.3 | |
| MambaRL-Method=MAPPO2025.10 | 69 | |
| TransformerRL-Method=QMIX2025.10 | 68.5 | |
| ToSTRL-Method=MAPPO2025.10 | 68.1 | |
| TransformerRL-Method=MAPPO2025.10 | 65.6 |