List your company

Offline Reinforcement Learning on D4RL MuJoCo halfcheetah-medium

69.1Normalized ScoreCAC
41.43648.61855.862.982Feb 20, 2026Mar 10, 2026Mar 28, 2026Apr 15, 2026May 3, 2026May 21, 2026Jun 9, 2026

Evaluation results

MethodLinks
CACPolicy Type=Diffusion, Seeds=82026.0269.1
EPQPolicy Type=Gaussian, Seeds=82026.0267.3
BFQPolicy Type=One-Step Flow/Diffusion Policy2026.0666.1
ReBRACPolicy Type=Gaussian, Seeds=82026.0265.6
FACPolicy Type=Flow, Seeds=82026.0265
MCQPolicy Type=Gaussian, Seeds=82026.0264.3
OFQLPolicy Type=One-Step Flow/Diffusion Policy2026.0663.8
SRPOPolicy Type=Diffusion, Seeds=82026.0260.4
SRPOPolicy Type=One-Step Flow/Diffusion Policy2026.0660.4
FQLPolicy Type=Flow, Seeds=82026.0260.3
FQLPolicy Type=One-Step Flow/Diffusion Policy2026.0660.1
ISEP-FMFlow Matching=true2026.0559.9
SPOTPolicy Type=Gaussian, Seeds=82026.0258.4
SORLPolicy Type=One-Step Flow/Diffusion Policy2026.0657.4
QIPO-OTPolicy Type=Diffusion, Seeds=82026.0254.2
QGPO2026.0554.1
QIPO2026.0554.1
DQLPolicy Type=Diffusion Policy2026.0652.3
IDQLPolicy Type=Diffusion Policy2026.0651.5
DQL2026.0551.1
IDQLPolicy Type=Diffusion, Seeds=82026.0251
EDPPolicy Type=Diffusion Policy2026.0650.8
IDQL2026.0549.7
ISEPFlow Matching=false2026.0549.3
TD3-BCPolicy Type=Gaussian Policy2026.0648.5
TD3+BCPolicy Type=Gaussian, Seeds=82026.0248.3
IQLPolicy Type=Gaussian Policy2026.0647.7
IQL2026.0547.5
IQLPolicy Type=Gaussian, Seeds=82026.0247.4
CQL2026.0544.4
CQLPolicy Type=Gaussian, Seeds=82026.0244
BC2026.0542.6
BCPolicy Type=Gaussian Policy2026.0642.5