List your company
ResearchFormerly WizWand

Multi-Agent Reinforcement Learning on MPE World Medium Replay

65.9Mean Episode ReturnDOM2
2.14818.69935.2551.801Jul 4, 2023
Updated 4mo ago

Evaluation results

MethodLinks
DOM22023.0765.9
DOM22023.0751.5
OMAR2023.0721.1
OMAR2023.0720.1
MA-CQL2023.0715.9
MA-SfBC2023.079.1
MA-CQL2023.078.1
MA-SfBC2023.074.6