List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Walker2D Medium 1T10S

84.582Average ReturnREAG*MV
70.5274474.1762277.82581.47378Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1084.582
QTDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1084.325
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1083.068
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1082.354
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1080.904
ReinformerDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1080.857
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1080.857
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1080.666
QTDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1080.621
DTDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1078.768
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1078.672
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1078.257
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1075.008
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1075.008
ReinformerDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1074.748
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1074.268
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1071.779
DTDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1071.068