List your company

Offline Reinforcement Learning on D4RL MuJoCo Locomotion Total

91.5Normalized ScoreISEP-FM
50.31661.00871.782.392May 18, 2026

Evaluation results

MethodLinks
ISEP-FMFlow Matching=true2026.0591.5
QIPO2026.0588.1
DQL2026.0588
QGPO2026.0586.6
ISEPFlow Matching=false2026.0584
IDQL2026.0579.1
IQL2026.0577
CQL2026.0574.6
BC2026.0551.9