Safe Offline Multi-Agent Reinforcement Learning on 4ant poor
0.4RewardCBFs-Guided Diffusion Model
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CBFs-Guided Diffusion Model2026.06 | 0.4 | 0.44 | |
| MA-TD3BC2026.06 | 0.25 | 0.74 | |
| OMAR2026.06 | 0.23 | 0.53 |
Loading the SOTA2 catalog…
| Method | Links | ||
|---|---|---|---|
| CBFs-Guided Diffusion Model2026.06 | 0.4 | 0.44 | |
| MA-TD3BC2026.06 | 0.25 | 0.74 | |
| OMAR2026.06 | 0.23 | 0.53 |