List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on 1T10S Hopper (Medium-Replay)

98.988ScoreH2O
-2.0448824.1848150.414576.64419Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
H2ODistribution Shift=JointNoise2024.1098.988
H2ODistribution Shift=BodyMass2024.1097.538
IGDFDistribution Shift=BodyMass2024.1095.655
IGDFDistribution Shift=JointNoise2024.1095.23
DFDTDistribution Shift=BodyMass2024.1074.72
DFDTDistribution Shift=JointNoise2024.1074.72
D-CQLDistribution Shift=BodyMass2024.1068.163
CQLDistribution Shift=BodyMass2024.1066.455
BCQDistribution Shift=JointNoise2024.1065.103
BCQDistribution Shift=BodyMass2024.1064.519
D-BCQDistribution Shift=JointNoise2024.1064.519
D-BCQDistribution Shift=BodyMass2024.1064.168
D-AWRDistribution Shift=JointNoise2024.1063.937
D-CQLDistribution Shift=JointNoise2024.1063.178
CQLDistribution Shift=JointNoise2024.1061.302
AWRDistribution Shift=BodyMass2024.1055.607
D-AWRDistribution Shift=BodyMass2024.1044.883
AWRDistribution Shift=JointNoise2024.1037.821
BEARDistribution Shift=BodyMass2024.106.282
D-MOPODistribution Shift=JointNoise2024.106.147
D-BEARDistribution Shift=JointNoise2024.105.637
MOPODistribution Shift=BodyMass2024.105.504
MOPODistribution Shift=JointNoise2024.105.498
D-MOPODistribution Shift=BodyMass2024.105.482
D-BEARDistribution Shift=BodyMass2024.102.619
BEARDistribution Shift=JointNoise2024.101.841