List your company
ResearchFormerly WizWand

3-Agent 6-Landmark on 3-Agent 6-Landmark Expert

683.3Mean Episode ReturnDOM2
241.092355.896470.7585.504Jul 4, 2023
Updated 4mo ago

Evaluation results

MethodLinks
DOM2Environment=Standard, K (Rollout budget)=12023.07683.3
MA-SfBCEnvironment=Standard, K (Rollout budget)=12023.07606.1
OMAREnvironment=Standard, K (Rollout budget)=12023.07595
DOM2Environment=Shifted, K (Rollout budget)=102023.07487.6
MA-SfBCEnvironment=Shifted, K (Rollout budget)=102023.07470.6
MA-CQLEnvironment=Standard, K (Rollout budget)=12023.07457.5
DOM2Environment=Shifted, K (Rollout budget)=12023.07393.1
MA-SfBCEnvironment=Shifted, K (Rollout budget)=12023.07374.2
OMAREnvironment=Shifted, K (Rollout budget)=102023.07358.2
OMAREnvironment=Shifted, K (Rollout budget)=12023.07334
MA-CQLEnvironment=Shifted, K (Rollout budget)=102023.07277.7
MA-CQLEnvironment=Shifted, K (Rollout budget)=12023.07258.1