Multi-Agent Reinforcement Learning on MPE Predator Prey (Medium Replay)
150.5Mean Episode ReturnDOM2
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DOM22023.07 | 150.5 | — | |
| CFCQL2023.07 | 130.8 | — | |
| MADIFF2023.07 | 114.1 | — | |
| DOM22023.07 | 104.2 | — | |
| DoF2023.07 | 94 | — | |
| MA-Diffusion-QL2023.07 | 83.9 | — | |
| MA-EDP-DDPM2023.07 | 70 | — | |
| MA-EDP-DPM-Solver2023.07 | 69.4 | — | |
| OMAR2023.07 | 60 | — | |
| MA-BRAC2023.07 | 45.2 | — | |
| MA-IQL2023.07 | 37 | — | |
| MA-CQL2023.07 | 35.6 | — | |
| OMAC2023.07 | 20.5 | — | |
| MA-SfBC2023.07 | 11.9 | — | |
| OMIGA2023.07 | 8.4 | — | |
| DOM22023.07 | — | 150.5 | |
| MA-CQL2023.07 | — | 35 | |
| MA-SfBC2023.07 | — | 26.1 | |
| OMAR2023.07 | — | 86.8 |