Safe Offline Multi-Agent Reinforcement Learning on 2ant medium
0.6RewardCBFs-Guided Diffusion Model
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CBFs-Guided Diffusion Model2026.06 | 0.6 | 0.8 | |
| MA-TD3BC2026.06 | 0.41 | 1.45 | |
| OMAR2026.06 | 0.18 | 0.35 |
Loading the SOTA2 catalog…
| Method | Links | ||
|---|---|---|---|
| CBFs-Guided Diffusion Model2026.06 | 0.6 | 0.8 | |
| MA-TD3BC2026.06 | 0.41 | 1.45 | |
| OMAR2026.06 | 0.18 | 0.35 |