List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Hopper 1T10S (Medium)

101.244ScoreH2O
4.8276829.8588454.8979.92116Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
H2ODistribution Shift=JointNoise2024.10101.244
H2ODistribution Shift=BodyMass2024.10100.754
IGDFDistribution Shift=JointNoise2024.1078.467
IGDFDistribution Shift=BodyMass2024.1075.326
D-BCQDistribution Shift=JointNoise2024.1074.853
BCQDistribution Shift=JointNoise2024.1074.559
CQLDistribution Shift=JointNoise2024.1071.495
DFDTDistribution Shift=BodyMass2024.1066.133
D-CQLDistribution Shift=JointNoise2024.1063.611
D-AWRDistribution Shift=JointNoise2024.1061.463
DFDTDistribution Shift=JointNoise2024.1059.76
AWRDistribution Shift=JointNoise2024.1057.021
CQLDistribution Shift=BodyMass2024.1049.094
D-CQLDistribution Shift=BodyMass2024.1045.101
D-AWRDistribution Shift=BodyMass2024.1026.594
D-BCQDistribution Shift=BodyMass2024.1026.487
AWRDistribution Shift=BodyMass2024.1025.843
D-BEARDistribution Shift=BodyMass2024.1025.608
D-MOPODistribution Shift=JointNoise2024.1024.992
BCQDistribution Shift=BodyMass2024.1024.853
MOPODistribution Shift=JointNoise2024.1023.556
BEARDistribution Shift=BodyMass2024.1022.436
D-MOPODistribution Shift=BodyMass2024.1021.495
MOPODistribution Shift=BodyMass2024.1020.765
D-BEARDistribution Shift=JointNoise2024.1010.576
BEARDistribution Shift=JointNoise2024.108.536