Safe Offline Multi-Agent Reinforcement Learning on 2ant poor
0.33RewardCBFs-Guided Diffusion Model
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CBFs-Guided Diffusion Model2026.06 | 0.33 | 0.29 | |
| MA-TD3BC2026.06 | 0.21 | 0.55 | |
| OMAR2026.06 | 0.2 | 0.43 |
Loading the SOTA2 catalog…
| Method | Links | ||
|---|---|---|---|
| CBFs-Guided Diffusion Model2026.06 | 0.33 | 0.29 | |
| MA-TD3BC2026.06 | 0.21 | 0.55 | |
| OMAR2026.06 | 0.2 | 0.43 |