3-Agent 6-Landmark evaluation on 3-Agent 6-Landmark Medium Replay
542.4Mean Episode ReturnDOM2
Evaluation Results
| Method | Links | |
|---|---|---|
| DOM2Environment=Standard, K (Rollout budget)=12023.07 | 542.4 | |
| OMAREnvironment=Standard, K (Rollout budget)=12023.07 | 455.7 | |
| MA-CQLEnvironment=Standard, K (Rollout budget)=12023.07 | 396.9 | |
| DOM2Environment=Shifted, K (Rollout budget)=102023.07 | 357.2 | |
| MA-SfBCEnvironment=Standard, K (Rollout budget)=12023.07 | 339.3 | |
| DOM2Environment=Shifted, K (Rollout budget)=12023.07 | 317.2 | |
| OMAREnvironment=Shifted, K (Rollout budget)=102023.07 | 294.3 | |
| MA-SfBCEnvironment=Shifted, K (Rollout budget)=102023.07 | 288.7 | |
| OMAREnvironment=Shifted, K (Rollout budget)=12023.07 | 274.4 | |
| MA-CQLEnvironment=Shifted, K (Rollout budget)=102023.07 | 253.3 | |
| MA-CQLEnvironment=Shifted, K (Rollout budget)=12023.07 | 247 | |
| MA-SfBCEnvironment=Shifted, K (Rollout budget)=12023.07 | 205.7 |