List your company
ResearchFormerly WizWand

Multi-Agent Reinforcement Learning on MPE World Medium

57.5Mean Episode ReturnDOM2
30.9837.86544.7551.635Jul 4, 2023
Updated 4mo ago

Evaluation results

MethodLinks
DOM22023.0757.5
MA-SfBC2023.0735.6
MA-CQL2023.0733.3
OMAR2023.0732