List your company

Locomotion on D4RL HalfCheetah (medium)

63.5Normalized ScorePRDC
40.72446.63752.5558.463Oct 15, 2022May 10, 2023Dec 4, 2023Jun 29, 2024Jan 22, 2025Aug 18, 2025Mar 14, 2026

Evaluation results

MethodLinks
PRDC2024.0363.5——
SAGE2026.0351.6——
DVreproduced=true2026.0350.4——
DMEMM2026.0249.2——
DD2023.1249.1——
PORMethod Category=Conditioned BC, Seeds=52022.1048.8——
BiTrajDiffRL Algorithm=CQL2025.0648.7——
One-step RLMethod Category=Weighted BC, Seeds=52022.1048.4——
Onestep RLTraining Time (min)=202023.0648.4——
TD3+BCMethod Category=Best RL Baseline, Seeds=52022.1048.3——
TD3 + BCTraining Time (min)=202023.0648.3——
SyntherRL Algorithm=CQL2025.0648.3——
HDMI2026.0248——
DiffStitchRL Algorithm=CQL2025.0648——
RTDiffRL Algorithm=CQL2025.0647.8——
IQL+ReD2024.0347.6——
IQLMethod Category=Weighted BC, Seeds=52022.1047.4——
IQLTraining Time (min)=202023.0647.4——
IQL2023.1247.4——
IQL2026.0247.4——
IQL2026.0247.4——
IQL2026.0347.4——
BaseRL Algorithm=CQL2025.0647.4——
DTAMP2023.1247.3——
A2PO2024.0347.1——
TT2023.1246.9——
TT2026.0246.9——
TT2026.0346.9——
HD-DA2026.0246.7——
LoMAP2026.0345.4——
MBOP2026.0344.6——
Diffuser2023.1244.2——
CQLTraining Time (min)=802023.0644——
CQL2026.0244——
CQL2026.0244——
RGG2026.0344——
CQL2026.0344——
BiTrajDiffRL Algorithm=DT2025.0643.3——
IMLE+Exp RW2026.0343.1——
WT (Ours)Training Time (min)=202023.0643——
ISCTSeeds=5, Episodes=102026.0242.9——
TD3+BC2026.0242.8——
Diffuser2026.0242.8——
Diffuserreproduced=true2026.0342.8——
LDCQ2026.0342.8——
Diffuser2026.0342.8——
DiffStitchRL Algorithm=DT2025.0642.8——
BaseRL Algorithm=DT2025.0642.7——
SyntherRL Algorithm=DT2025.0642.7——
DTMethod Category=Conditioned BC, Seeds=52022.1042.6——
BC 10%Training Time (min)=102023.0642.6——
CQL2023.1242.6——
DT2023.1242.6——
DT2024.0342.6——
DT2026.0242.6——
BC2026.0242.6——
DT2026.0242.6——
BC2026.0342.6——
DT2026.0342.6——
RTDiffRL Algorithm=DT2025.0642.6——
10%BCMethod Category=Weighted BC, Seeds=52022.1042.5——
BCTraining Time (min)=102023.0642.5——
%BC2024.0342.5——
DTTraining Time (min)=1502023.0642.4——
QDT2023.0642.3——
MOPO2026.0342.3——
MOReL2026.0242.1——
MOReL2026.0342.1——
RvSMethod Category=Conditioned BC, Seeds=52022.1041.6——
RvS-R/GTraining Time (min)=802023.0641.6——
ACAOnline update way=SAC, Evaluation protocol=Offline-to-online2024.12—66.5920.09
AWACOnline update way=IQL/Policy constraint, Evaluation protocol=Offline-to-online2024.12—51.111.43
Cal-QLOnline update way=SAC, Evaluation protocol=Offline-to-online2024.12—54.366.81
IQLOnline update way=IQL/Policy constraint, Evaluation protocol=Offline-to-online2024.12—48.850.33
O2PPOOnline update way=IQL/Policy constraint, Evaluation protocol=Offline-to-online2024.12—59.9611.54
O2SACOnline update way=SAC, Evaluation protocol=Offline-to-online2024.12—74.1827.32
O2TD3Online update way=TD3, Evaluation protocol=Offline-to-online2024.12—65.5817.45
Off2OnOnline update way=SAC, Evaluation protocol=Offline-to-online2024.12—94.2247.37
PEXOnline update way=IQL/Policy constraint, Evaluation protocol=Offline-to-online2024.12—57.058.53