List your company
ResearchFormerly WizWand

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

113.069ScoreD-BCQ
10.2483636.9421863.63690.32982Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
D-BCQDistribution Shift=BodyMass2024.10113.069
BCQDistribution Shift=JointNoise2024.10112.926
BCQDistribution Shift=BodyMass2024.10112.343
IGDFDistribution Shift=BodyMass2024.10111.936
D-BCQDistribution Shift=JointNoise2024.10111.249
IGDFDistribution Shift=JointNoise2024.10111.226
AWRDistribution Shift=BodyMass2024.10110.324
D-AWRDistribution Shift=BodyMass2024.10109.743
D-AWRDistribution Shift=JointNoise2024.10108.915
DFDTDistribution Shift=JointNoise2024.10108.39
D-CQLDistribution Shift=JointNoise2024.10108.236
DFDTDistribution Shift=BodyMass2024.10108.086
CQLDistribution Shift=BodyMass2024.10107.187
D-CQLDistribution Shift=BodyMass2024.10105.401
AWRDistribution Shift=JointNoise2024.10104.662
CQLDistribution Shift=JointNoise2024.10104.019
H2ODistribution Shift=JointNoise2024.1095.862
H2ODistribution Shift=BodyMass2024.1083.768
D-MOPODistribution Shift=BodyMass2024.1020.741
BEARDistribution Shift=BodyMass2024.1019.799
D-MOPODistribution Shift=JointNoise2024.1019.325
MOPODistribution Shift=BodyMass2024.1018.324
D-BEARDistribution Shift=BodyMass2024.1017.491
MOPODistribution Shift=JointNoise2024.1017.429
BEARDistribution Shift=JointNoise2024.1014.225
D-BEARDistribution Shift=JointNoise2024.1014.203