List your company

Offline Reinforcement Learning on HalfCheetah Medium-Expert 1T10S

83.692Average ReturnREAG*MV
38.8430450.4865262.1373.77348Oct 30, 2024

Evaluation results

MethodLinks
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1083.692
QTDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1082.961
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1082.148
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1079.39
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1078.981
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1077.762
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1077.751
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1076.533
ReinformerDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1076.073
QTDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1071.008
DTDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1070.573
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1069.819
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1056.228
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1055.818
DTDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1054.981
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1051.357
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1046.048
ReinformerDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1040.568