List your company
ResearchFormerly WizWand

Continuous Robotic Locomotion Control on MuJoCo Hopper v4 (1M Steps)

30.46Normalized Final ReturnDUPO
-0.17847.775815.7323.6842Jul 6, 2026
Updated 3mo ago

Evaluation results

MethodLinks
DUPOMaximum observation delay (ΔTmax)=10, Training steps=1M2026.0730.46
State AugmentationMaximum observation delay (ΔTmax)=10, Training steps=1M2026.0723.71
DUPOMaximum observation delay (ΔTmax)=25, Training steps=1M2026.0710.34
State AugmentationMaximum observation delay (ΔTmax)=25, Training steps=1M2026.077.32
DUPOMaximum observation delay (ΔTmax)=5, Training steps=1M2026.077.24
State AugmentationMaximum observation delay (ΔTmax)=5, Training steps=1M2026.076.78
State PredictionMaximum observation delay (ΔTmax)=10, Training steps=1M2026.076.41
State PredictionMaximum observation delay (ΔTmax)=25, Training steps=1M2026.074.01
State PredictionMaximum observation delay (ΔTmax)=5, Training steps=1M2026.073.19
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