List your company
ResearchFormerly WizWand

Continuous robotic locomotion control on MuJoCo Swimmer v4 (Normalized final return)

2.98Normalized Final ReturnDUPO
0.92081.45541.992.5246Jul 6, 2026
Updated 3mo ago

Evaluation results

MethodLinks
DUPOMaximum observation delay (ΔTmax)=25, Training steps=1M2026.072.98
State AugmentationMaximum observation delay (ΔTmax)=25, Training steps=1M2026.072.75
DUPOMaximum observation delay (ΔTmax)=10, Training steps=1M2026.072.36
State PredictionMaximum observation delay (ΔTmax)=25, Training steps=1M2026.072.3
State AugmentationMaximum observation delay (ΔTmax)=10, Training steps=1M2026.072.15
State PredictionMaximum observation delay (ΔTmax)=10, Training steps=1M2026.071.75
State PredictionMaximum observation delay (ΔTmax)=5, Training steps=1M2026.071.65
DUPOMaximum observation delay (ΔTmax)=5, Training steps=1M2026.071.25
State AugmentationMaximum observation delay (ΔTmax)=5, Training steps=1M2026.071.07
DC/ACMaximum observation delay (ΔTmax)=5, Training steps=1M2026.071
DC/ACMaximum observation delay (ΔTmax)=10, Training steps=1M2026.071
DC/ACMaximum observation delay (ΔTmax)=25, Training steps=1M2026.071