List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Walker2D Medium-Replay 1T10S

87.491Average ReturnREAG*MV
45.99556.76867.54178.314Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1087.491
QTDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1087.292
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1082.363
QTDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1082.139
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1079.795
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1076.169
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1073.708
DTDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1073.664
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1067.565
ReinformerDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1067.032
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1066.658
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1062.226
DTDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1058.255
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1055.722
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1055.438
ReinformerDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1054.801
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1050.296
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1047.591