List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Hopper Medium 1T10S

78.325Average ReturnREAG*Dara
32.2862844.2386456.19168.14336Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1078.325
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1073.987
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1072.346
DTDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1070.685
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1070.466
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1070.356
ReinformerDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1070.34
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1068.709
QTDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1068.656
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1062.226
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1059.085
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1051.796
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1051.771
ReinformerDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1051.357
QTDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1049.516
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1039.435
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1037.787
DTDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1034.057