Offline Multi-Agent Reinforcement Learning on Multi-agent MuJoCo Ant (Expert, Medium, Medium-Replay)
2,162.8Return
FACMAC+B3C
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.01 | 2,162.8 | |
2025.01 | 2,077.6 | |
2025.01 | 1,516.5 | |
2025.01 | 1,259.8 | |
2025.01 | 1,226 |