List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on 1T10S Walker2D (Medium-Replay)

71.67Performance ScoreDFDT
-2.7971216.5356935.868555.20131Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
DFDTDistribution Shift=BodyMass2024.1071.67
DFDTDistribution Shift=JointNoise2024.1071.236
IGDFDistribution Shift=JointNoise2024.1066.834
IGDFDistribution Shift=BodyMass2024.1062.494
D-CQLDistribution Shift=BodyMass2024.1057.432
H2ODistribution Shift=BodyMass2024.1056.11
H2ODistribution Shift=JointNoise2024.1055.228
CQLDistribution Shift=BodyMass2024.1054.753
D-CQLDistribution Shift=JointNoise2024.1051.742
D-BCQDistribution Shift=BodyMass2024.1051.447
BCQDistribution Shift=BodyMass2024.1050.714
D-BCQDistribution Shift=JointNoise2024.1050.714
BCQDistribution Shift=JointNoise2024.1050.601
CQLDistribution Shift=JointNoise2024.1050.6
AWRDistribution Shift=BodyMass2024.1047.033
D-AWRDistribution Shift=JointNoise2024.1036.807
D-AWRDistribution Shift=BodyMass2024.1032.008
AWRDistribution Shift=JointNoise2024.1031.623
D-MOPODistribution Shift=JointNoise2024.1015.389
D-MOPODistribution Shift=BodyMass2024.1012.129
MOPODistribution Shift=BodyMass2024.1011.563
MOPODistribution Shift=JointNoise2024.1011.379
D-BEARDistribution Shift=BodyMass2024.101.078
BEARDistribution Shift=JointNoise2024.100.474
D-BEARDistribution Shift=JointNoise2024.100.384
BEARDistribution Shift=BodyMass2024.100.067