List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on D4RL MuJoCo hopper-medium-replay

104.5Normalized ScoreISEP-FM
14.64437.97261.384.628May 18, 2026May 22, 2026May 26, 2026May 30, 2026Jun 3, 2026Jun 7, 2026Jun 12, 2026
Updated 4mo ago

Evaluation results

MethodLinks
ISEP-FMFlow Matching=true2026.05104.5
ISEPFlow Matching=false2026.05102.7
BFQPolicy Type=One-Step Flow/Diffusion Policy2026.06102.1
SPAR-MLPLearning Paradigm=Ours2026.05101.9
OFQLPolicy Type=One-Step Flow/Diffusion Policy2026.06101.9
DQL2026.05101.3
Diff-QLLearning Paradigm=Policy Gradient Guidance2026.05101.3
QIPO2026.05101.2
SRPOPolicy Type=One-Step Flow/Diffusion Policy2026.06101.2
IDQLPolicy Type=Diffusion Policy2026.0699.4
QGPO2026.0596.9
CQL2026.0595
CQLLearning Paradigm=Policy Gradient Guidance2026.0595
IQL2026.0594.7
IQLLearning Paradigm=In-Support Learning2026.0594.7
IQLSeeds=52026.0694.7
SORLPolicy Type=One-Step Flow/Diffusion Policy2026.0693
DQLPolicy Type=Diffusion Policy2026.0691.2
PDiTSeeds=52026.0689.6
DRIVESeeds=52026.0689.2
IQLPolicy Type=Gaussian Policy2026.0686.8
FQLPolicy Type=One-Step Flow/Diffusion Policy2026.0685.4
EDPPolicy Type=Diffusion Policy2026.0683
IDQL2026.0582.4
IDQLLearning Paradigm=In-Support Learning2026.0582.4
DTSeeds=52026.0678.7
EQLLearning Paradigm=In-Support Learning2026.0574.6
CQL-AWLearning Paradigm=In-Support Learning2026.0571
SPAR-PROJLearning Paradigm=Ours2026.0570.4
TD3+BCLearning Paradigm=Policy Gradient Guidance2026.0560.9
TD3+BCSeeds=52026.0660.9
TD3-BCPolicy Type=Gaussian Policy2026.0655.2
BCQLearning Paradigm=Policy Gradient Guidance2026.0553.3
PLASLearning Paradigm=Policy Gradient Guidance2026.0551.9
LAPOLearning Paradigm=In-Support Learning2026.0550.1
CQLSeeds=52026.0648.6
BCSeeds=52026.0648
BaseLearning Paradigm=Ours2026.0542.9
AWACLearning Paradigm=In-Support Learning2026.0537.2
BEARSeeds=52026.0633.7
BCPolicy Type=Gaussian Policy2026.0619.7
BC2026.0518.1