Safe Offline Multi-Agent Reinforcement Learning on simple spread random
0.56RewardCBFs-Guided Diffusion Model
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CBFs-Guided Diffusion Model2026.06 | 0.56 | 0 | |
| OMAR2026.06 | 0.49 | 1.5 | |
| MA-TD3BC2026.06 | 0.23 | 0 |
Loading the SOTA2 catalog…