List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Hopper Medium-Expert 1T10S

109.803Average ReturnREAG*MV
30.5040451.0912771.678592.26573Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=QT2024.10109.803
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=QT2024.10109.746
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.10109.472
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=DT2024.10109.367
ReinformerDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.10109.256
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.10109.255
QTDistribution Shift=JointNoise (JN), Base Architecture=QT2024.10109.056
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=DT2024.10108.261
DTDistribution Shift=JointNoise (JN), Base Architecture=DT2024.10108.254
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1077.279
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1073.952
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1073.363
ReinformerDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1068.973
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1064.206
QTDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1061.162
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1052.873
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1033.631
DTDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1033.554