3-Agent 6-Landmark Evaluation on 3-Agent 6-Landmark Medium Expert
678.7Mean Episode ReturnDOM2
Evaluation Results
| Method | Links | |
|---|---|---|
| DOM2Environment=Standard, K (Rollout budget)=12023.07 | 678.7 | |
| MA-SfBCEnvironment=Standard, K (Rollout budget)=12023.07 | 552.1 | |
| DOM2Environment=Shifted, K (Rollout budget)=102023.07 | 486.3 | |
| MA-SfBCEnvironment=Shifted, K (Rollout budget)=102023.07 | 440.9 | |
| OMAREnvironment=Standard, K (Rollout budget)=12023.07 | 395.5 | |
| DOM2Environment=Shifted, K (Rollout budget)=12023.07 | 382.3 | |
| MA-SfBCEnvironment=Shifted, K (Rollout budget)=12023.07 | 328.7 | |
| MA-CQLEnvironment=Standard, K (Rollout budget)=12023.07 | 300.9 | |
| OMAREnvironment=Shifted, K (Rollout budget)=102023.07 | 274.2 | |
| OMAREnvironment=Shifted, K (Rollout budget)=12023.07 | 241.9 | |
| MA-CQLEnvironment=Shifted, K (Rollout budget)=102023.07 | 213.8 | |
| MA-CQLEnvironment=Shifted, K (Rollout budget)=12023.07 | 201.2 |