List your company

Locomotion on D4RL halfcheetah-medium-expert

105.9Normalized ScoreMBOP
51.19665.39879.693.802Oct 15, 2022May 10, 2023Dec 4, 2023Jun 29, 2024Jan 22, 2025Aug 18, 2025Mar 14, 2026

Evaluation results

MethodLinks
MBOP2026.03105.9—
O2SACOnline update way=SAC2024.12100.416.24
Off2OnOnline update way=SAC2024.1298.332.67
TD3+BC2026.0297.9—
A2PO2024.0395.6—
SAGE2026.0395.4—
TT2023.1295—
TT2026.0295—
TT2026.0395—
PORMethod Category=Conditioned BC, Seeds=52022.1094.7—
DMEMM2026.0294.6—
PRDC2024.0394.5—
One-step RLMethod Category=Weighted BC, Seeds=52022.1093.4—
10%BCMethod Category=Weighted BC, Seeds=52022.1092.9—
%BC2024.0392.9—
DVreproduced=true2026.0392.7—
IQL+ReD2024.0392.6—
HD-DA2026.0292.5—
RvSMethod Category=Conditioned BC, Seeds=52022.1092.2—
HDMI2026.0292.1—
IMLE+Exp RW2026.0391.9—
CQLMethod Category=Best RL Baseline, Seeds=52022.1091.6—
CQL2023.1291.6—
CQL2026.0291.6—
CQL2026.0291.6—
CQL2026.0391.6—
ISCTSeeds=5, Episodes=102026.0291.4—
LoMAP2026.0391.1—
RGG2026.0390.8—
DD2023.1290.6—
LDCQ2026.0390.2—
O2PPOOnline update way=IQL2024.1289.61-3.29
Diffuser2026.0288.9—
Diffuserreproduced=true2026.0388.9—
Diffuser2026.0388.9—
DTAMP2023.1288.2—
DTMethod Category=Conditioned BC, Seeds=52022.1086.8—
DT2023.1286.8—
DT2024.0386.8—
DT2026.0286.8—
DT2026.0286.8—
DT2026.0386.8—
IQLMethod Category=Weighted BC, Seeds=52022.1086.7—
IQL2023.1286.7—
IQL2026.0286.7—
IQL2026.0286.7—
IQL2026.0386.7—
Diffuser2023.1279.8—
MOPO2026.0363.3—
BC2026.0255.2—
BC2026.0355.2—
MOReL2026.0253.3—
MOReL2026.0353.3—