List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on 1T10S HalfCheetah (Medium-Expert)

89.22ScoreD-AWR
-0.5028822.7905646.08469.37744Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
D-AWRDistribution Shift=JointNoise2024.1089.22
D-AWRDistribution Shift=BodyMass2024.1089.201
AWRDistribution Shift=JointNoise2024.1088.647
AWRDistribution Shift=BodyMass2024.1088.155
D-CQLDistribution Shift=JointNoise2024.1084.21
CQLDistribution Shift=JointNoise2024.1084.09
DFDTDistribution Shift=JointNoise2024.1082.476
DFDTDistribution Shift=BodyMass2024.1078.093
D-BCQDistribution Shift=JointNoise2024.1071.007
D-BCQDistribution Shift=BodyMass2024.1063.465
D-CQLDistribution Shift=BodyMass2024.1062.665
BCQDistribution Shift=JointNoise2024.1062.486
BCQDistribution Shift=BodyMass2024.1061.771
CQLDistribution Shift=BodyMass2024.1061.104
H2ODistribution Shift=JointNoise2024.1060.23
D-MOPODistribution Shift=JointNoise2024.1060.014
H2ODistribution Shift=BodyMass2024.1058.192
D-MOPODistribution Shift=BodyMass2024.1056.616
MOPODistribution Shift=JointNoise2024.1054.63
MOPODistribution Shift=BodyMass2024.1051.04
IGDFDistribution Shift=JointNoise2024.1048.192
IGDFDistribution Shift=BodyMass2024.1048.112
D-BEARDistribution Shift=JointNoise2024.108.789
BEARDistribution Shift=BodyMass2024.104.356
BEARDistribution Shift=JointNoise2024.103.195
D-BEARDistribution Shift=BodyMass2024.102.948