Safe Offline Multi-Agent Reinforcement Learning on 2halfcheetah poor
0.13RewardCBFs-Guided Diffusion Model
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CBFs-Guided Diffusion Model2026.06 | 0.13 | 0.17 | |
| MA-TD3BC2026.06 | 0.09 | 0.2 | |
| OMAR2026.06 | 0.05 | 0.19 |
Loading the SOTA2 catalog…