List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on D4RL Adroit Pen Human Cloned Expert

119.3Normalized ScoreReBRAC
72.584.6596.8108.95May 27, 2026
Updated 5mo ago

Evaluation results

MethodLinks
ReBRAC2026.05119.3
MoMa QL2026.05108.3
IFQL2026.0596.7
IQL2026.0596.3
IDQL2026.0593.3
FQL2026.0589.7
SRPO2026.0588
FBRAC2026.0587.7
FAWAC2026.0582.3
BC2026.0577.7
CAC2026.0574.3