List your company
ResearchFormerly WizWand

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

3,178.7Average ReturnDOM2
-467.228479.3111,425.852,372.389Jul 4, 2023
Updated 4mo ago

Evaluation results

MethodLinks
DOM2Dataset Split=Expert2023.073,178.7
DOM2Dataset Split=Medium2023.072,788.5
DOM2Dataset Split=Medium Expert2023.072,731.7
MA-CQLDataset Split=Expert2023.072,678.2
OMARDataset Split=Medium2023.072,650
OMARDataset Split=Medium Expert2023.072,616.6
MA-SfBCDataset Split=Expert2023.072,397.4
OMARDataset Split=Expert2023.072,295
DOM2Dataset Split=Medium Replay2023.072,290.8
OMARDataset Split=Medium Replay2023.071,648
MA-SfBCDataset Split=Medium Expert2023.071,442.1
MA-SfBCDataset Split=Medium2023.071,367.6
MA-CQLDataset Split=Medium Expert2023.071,291.5
MA-CQLDataset Split=Medium Replay2023.071,279.6
DOM2Dataset Split=Random Medium2023.071,245.8
MA-CQLDataset Split=Medium2023.071,111.7
DOM2Dataset Split=Random2023.07581.8
OMARDataset Split=Random Medium2023.0790.8
MA-CQLDataset Split=Random2023.07-0.1
MA-CQLDataset Split=Random Medium2023.07-0.2
OMARDataset Split=Random2023.07-1
MA-SfBCDataset Split=Medium Replay2023.07-171.4
MA-SfBCDataset Split=Random2023.07-315.8
MA-SfBCDataset Split=Random Medium2023.07-327