3-Agent 6-Landmark on 3-Agent 6-Landmark Expert
683.3Mean Episode ReturnDOM2
Evaluation Results
| Method | Links | |
|---|---|---|
| DOM2Environment=Standard, K (Rollout budget)=12023.07 | 683.3 | |
| MA-SfBCEnvironment=Standard, K (Rollout budget)=12023.07 | 606.1 | |
| OMAREnvironment=Standard, K (Rollout budget)=12023.07 | 595 | |
| DOM2Environment=Shifted, K (Rollout budget)=102023.07 | 487.6 | |
| MA-SfBCEnvironment=Shifted, K (Rollout budget)=102023.07 | 470.6 | |
| MA-CQLEnvironment=Standard, K (Rollout budget)=12023.07 | 457.5 | |
| DOM2Environment=Shifted, K (Rollout budget)=12023.07 | 393.1 | |
| MA-SfBCEnvironment=Shifted, K (Rollout budget)=12023.07 | 374.2 | |
| OMAREnvironment=Shifted, K (Rollout budget)=102023.07 | 358.2 | |
| OMAREnvironment=Shifted, K (Rollout budget)=12023.07 | 334 | |
| MA-CQLEnvironment=Shifted, K (Rollout budget)=102023.07 | 277.7 | |
| MA-CQLEnvironment=Shifted, K (Rollout budget)=12023.07 | 258.1 |