List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on D4RL Adroit hammer (3 tasks: human, cloned, expert)

46.2Normalized ScoreMoMa QL
31.1235.03538.9542.865May 27, 2026
Updated 5mo ago

Evaluation results

MethodLinks
MoMa QL2026.0546.2
FQL2026.0545.7
ReBRAC2026.0545.3
IQL2026.0544.3
BC2026.0543.7
SRPO2026.0543.3
IDQL2026.0543
FBRAC2026.0541
IFQL2026.0540.7
FAWAC2026.0540.3
CAC2026.0531.7