List your company
ResearchFormerly WizWand

Multi-Agent Reinforcement Learning on MAMuJoCo HalfCheetah Standard Env v2 (various)

3,676.6Average ReturnDOM2
-551.52546.1651,643.852,741.535Jul 4, 2023
Updated 4mo ago

Evaluation results

MethodLinks
DOM2Dataset Split=Expert2023.073,676.6
OMARDataset Split=Expert2023.072,963.8
DOM2Dataset Split=Medium Expert2023.072,919.6
OMARDataset Split=Medium Expert2023.072,900.2
DOM2Dataset Split=Medium2023.072,851.2
OMARDataset Split=Medium2023.072,797
MA-CQLDataset Split=Expert2023.072,722.8
DOM2Dataset Split=Medium Replay2023.072,564.3
MA-SfBCDataset Split=Expert2023.072,386.6
MA-CQLDataset Split=Medium Expert2023.071,989.8
OMARDataset Split=Medium Replay2023.071,674.8
MA-SfBCDataset Split=Medium Expert2023.071,392.3
MA-SfBCDataset Split=Medium2023.071,386.8
MA-CQLDataset Split=Medium Replay2023.071,216.6
MA-CQLDataset Split=Medium2023.07963.4
DOM2Dataset Split=Random Medium2023.07875
DOM2Dataset Split=Random2023.07799.8
OMARDataset Split=Random Medium2023.07219.5
MA-CQLDataset Split=Random2023.07-0.1
MA-CQLDataset Split=Random Medium2023.07-0.1
OMARDataset Split=Random2023.07-0.9
MA-SfBCDataset Split=Medium Replay2023.07-128.3
MA-SfBCDataset Split=Random Medium2023.07-383.1
MA-SfBCDataset Split=Random2023.07-388.9