List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on D4RL hopper-medium-expert-sparse

113Average Normalized RewardGORMPO
-2.107227.776457.6687.5436May 23, 2026
Updated 5mo ago

Evaluation results

MethodLinks
GORMPOBase Model=MOBILE, Density Estimator=VAE2026.05113
GORMPOBase Model=MOBILE, Density Estimator=DDPM2026.05113
GORMPOBase Model=MOBILE, Density Estimator=RealNVP2026.0595.5
MOBILE2026.0595.2
MOBILEBase Model=MOBILE2026.0595.2
GORMPOBase Model=MOBILE, Density Estimator=KDE2026.0595.2
SPOT2026.0583.8
SPOT2026.0583.8
GORMPODensity Estimator=DDPM2026.0514.1
GORMPOBase Model=MBPO, Density Estimator=DDPM2026.0514.1
GORMPODensity Estimator=RealNVP2026.0510
GORMPOBase Model=MBPO, Density Estimator=RealNVP2026.0510
GORMPODensity Estimator=KDE2026.058.91
GORMPOBase Model=MBPO, Density Estimator=KDE2026.058.91
GORMPODensity Estimator=NeuralODE2026.055.05
MBPO2026.054.81
MBPOBase Model=MBPO2026.054.81
GORMPODensity Estimator=VAE2026.052.32
GORMPOBase Model=MBPO, Density Estimator=VAE2026.052.32