Safe Offline Multi-Agent Reinforcement Learning on simple spread medium
0.88RewardCBFs-Guided Diffusion Model
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CBFs-Guided Diffusion Model2026.06 | 0.88 | 0 | |
| MA-TD3BC2026.06 | 0.71 | 2.1 | |
| OMAR2026.06 | 0.65 | 2.5 |
Loading the SOTA2 catalog…