List your company
ResearchFormerly WizWand

Reinforcement Learning on Walker2d medium-expert

1,515ReturnGELATO
-62.68346.91756.51,166.09Feb 22, 2021
Updated 8mo ago

Evaluation results

MethodLinks
GELATOvariant=metric2021.021,515
MOPO2021.021,296
GELATOvariant=L2021.021,255
Data Score2021.021,062
Imitation2021.02329
MBPO2021.02222
SAC2021.02-2