List your company
ResearchFormerly WizWand

Continuous Locomotion Control on MuJoCo Ant v4 (train)

2.43Normalized Final ReturnDUPO
0.94281.32891.7152.1011Jul 6, 2026
Updated 3mo ago

Evaluation results

MethodLinks
DUPOMaximum observation delay (ΔTmax)=5, Training steps=1M2026.072.43
State PredictionMaximum observation delay (ΔTmax)=5, Training steps=1M2026.072.28
DUPOMaximum observation delay (ΔTmax)=25, Training steps=1M2026.072.14
State PredictionMaximum observation delay (ΔTmax)=25, Training steps=1M2026.072.11
State PredictionMaximum observation delay (ΔTmax)=10, Training steps=1M2026.071.9
DUPOMaximum observation delay (ΔTmax)=10, Training steps=1M2026.071.87
State AugmentationMaximum observation delay (ΔTmax)=25, Training steps=1M2026.071.57
State AugmentationMaximum observation delay (ΔTmax)=5, Training steps=1M2026.071.43
State AugmentationMaximum observation delay (ΔTmax)=10, Training steps=1M2026.071.3
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