3-Agent 6-Landmark on 3-Agent 6-Landmark Medium
532.5Mean Episode ReturnDOM2
Evaluation Results
| Method | Links | |
|---|---|---|
| DOM2Environment=Standard, K (Rollout budget)=12023.07 | 532.5 | |
| MA-SfBCEnvironment=Standard, K (Rollout budget)=12023.07 | 459.9 | |
| OMAREnvironment=Standard, K (Rollout budget)=12023.07 | 349.9 | |
| MA-SfBCEnvironment=Shifted, K (Rollout budget)=102023.07 | 343.7 | |
| DOM2Environment=Shifted, K (Rollout budget)=102023.07 | 315.5 | |
| DOM2Environment=Shifted, K (Rollout budget)=12023.07 | 284.8 | |
| MA-SfBCEnvironment=Shifted, K (Rollout budget)=12023.07 | 276.7 | |
| MA-CQLEnvironment=Standard, K (Rollout budget)=12023.07 | 267.4 | |
| OMAREnvironment=Shifted, K (Rollout budget)=102023.07 | 235.7 | |
| OMAREnvironment=Shifted, K (Rollout budget)=12023.07 | 214 | |
| MA-CQLEnvironment=Shifted, K (Rollout budget)=102023.07 | 181.9 | |
| MA-CQLEnvironment=Shifted, K (Rollout budget)=12023.07 | 171.6 |