3-Agent 6-Landmark evaluation on 3-Agent 6-Landmark Random
470Mean Episode ReturnDOM2
Evaluation Results
| Method | Links | |
|---|---|---|
| DOM2Environment=Standard, K (Rollout budget)=12023.07 | 470 | |
| OMAREnvironment=Standard, K (Rollout budget)=12023.07 | 326 | |
| MA-CQLEnvironment=Standard, K (Rollout budget)=12023.07 | 321.2 | |
| DOM2Environment=Shifted, K (Rollout budget)=102023.07 | 283.7 | |
| DOM2Environment=Shifted, K (Rollout budget)=12023.07 | 262.5 | |
| MA-SfBCEnvironment=Shifted, K (Rollout budget)=102023.07 | 203.5 | |
| MA-SfBCEnvironment=Standard, K (Rollout budget)=12023.07 | 198.5 | |
| MA-CQLEnvironment=Shifted, K (Rollout budget)=102023.07 | 186.8 | |
| OMAREnvironment=Shifted, K (Rollout budget)=102023.07 | 186.7 | |
| OMAREnvironment=Shifted, K (Rollout budget)=12023.07 | 178.4 | |
| MA-CQLEnvironment=Shifted, K (Rollout budget)=12023.07 | 177.5 | |
| MA-SfBCEnvironment=Shifted, K (Rollout budget)=12023.07 | 142.2 |