List your company
ResearchFormerly WizWand

Offline Multi-Agent Reinforcement Learning on Bridge (Mix)

-1.29Mean ReturnAlberDICE
-6.7916-5.3633-3.935-2.5067Nov 3, 2023
Updated 8mo ago

Evaluation results

MethodLinks
AlberDICE2023.11-1.29
OptiDICE2023.11-1.76
BC2023.11-5.88
ICQ2023.11-6.01
OMAR2023.11-6.01
MADTKD2023.11-6.58