List your company
ResearchFormerly WizWand

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

2,757.2Average ReturnMA-SfBC
-452.656380.6721,2142,047.328Jul 4, 2023
Updated 4mo ago

Evaluation results

MethodLinks
MA-SfBCDataset Split=Expert2023.072,757.2
DOM2Dataset Split=Expert2023.072,641.3
DOM2Dataset Split=Medium2023.072,232.4
DOM2Dataset Split=Medium Expert2023.072,219
OMARDataset Split=Medium2023.072,197.4
OMARDataset Split=Medium Expert2023.072,196.9
MA-CQLDataset Split=Expert2023.072,117
DOM2Dataset Split=Medium Replay2023.071,904.2
OMARDataset Split=Expert2023.071,615.7
OMARDataset Split=Medium Replay2023.071,549.9
MA-SfBCDataset Split=Medium Expert2023.071,393.7
MA-SfBCDataset Split=Medium2023.071,355
MA-CQLDataset Split=Medium Replay2023.071,290.4
MA-CQLDataset Split=Medium Expert2023.071,127.1
MA-CQLDataset Split=Medium2023.071,108.1
DOM2Dataset Split=Random Medium2023.07482
DOM2Dataset Split=Random2023.07372.9
OMARDataset Split=Random Medium2023.07129.8
MA-CQLDataset Split=Random2023.07-0.1
MA-CQLDataset Split=Random Medium2023.07-0.1
OMARDataset Split=Random2023.07-1
MA-SfBCDataset Split=Medium Replay2023.07-169.8
MA-SfBCDataset Split=Random2023.07-309.8
MA-SfBCDataset Split=Random Medium2023.07-329.2