List your company
ResearchFormerly WizWand

Reinforcement Learning on Hopper medium-expert

3,907ReturnImitation
440.681,340.592,240.53,140.41Feb 22, 2021
Updated 8mo ago

Evaluation results

MethodLinks
Imitation2021.023,907
MBPO2021.022,105
SAC2021.021,850
Data Score2021.021,849
MOPO2021.021,063
GELATOvariant=L2021.02815
GELATOvariant=metric2021.02574