List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Walker2D Medium-Expert 1T10S

118.564Average ReturnREAG*MV
81.9809691.47848100.976110.47352Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=QT2024.10118.564
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.10118.218
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.10117.765
ReinformerDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.10117.36
QTDistribution Shift=JointNoise (JN), Base Architecture=QT2024.10116.149
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=QT2024.10116.115
DTDistribution Shift=JointNoise (JN), Base Architecture=DT2024.10115.746
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=DT2024.10111.236
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=DT2024.10111.06
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1094.578
QTDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1093.082
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1092.744
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1088.235
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1085.328
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1084.897
DTDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1084.43
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1083.761
ReinformerDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1083.388