Safe Offline Multi-Agent Reinforcement Learning on 2halfcheetah good
1.11Reward (2halfcheetah)MA-TD3BC
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MA-TD3BC2026.06 | 1.11 | 2.14 | |
| CBFs-Guided Diffusion Model2026.06 | 1.08 | 0.66 | |
| OMAR2026.06 | 0.81 | 1.76 |
Loading the SOTA2 catalog…