List your company

Offline Reinforcement Learning on HalfCheetah 1T10S (Medium-Replay)

57.835ReturnH2O
2.7919617.0819831.37245.66202Oct 30, 2024

Evaluation results

MethodLinks
H2ODistribution Shift=BodyMass2024.1057.835
H2ODistribution Shift=JointNoise2024.1057.734
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1053.87
QTDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1053.763
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1053.257
D-CQLDistribution Shift=JointNoise2024.1052.991
D-MOPODistribution Shift=BodyMass2024.1052.609
MOPODistribution Shift=JointNoise2024.1051.918
CQLDistribution Shift=JointNoise2024.1051.566
D-MOPODistribution Shift=JointNoise2024.1051.258
MOPODistribution Shift=BodyMass2024.1050.429
D-BCQDistribution Shift=JointNoise2024.1049.066
IGDFDistribution Shift=JointNoise2024.1046.611
BCQDistribution Shift=JointNoise2024.1046.567
IGDFDistribution Shift=BodyMass2024.1046.365
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1042.405
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1041.359
QTDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1041.3
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1040.84
ReinformerDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1040.296
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1038.436
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1038.417
D-AWRDistribution Shift=JointNoise2024.1038.125
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1038.031
D-CQLDistribution Shift=BodyMass2024.1037.721
CQLDistribution Shift=BodyMass2024.1037.508
DFDTDistribution Shift=BodyMass2024.1036.626
DTDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1036.509
BCQDistribution Shift=BodyMass2024.1032.553
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1032.114
D-BCQDistribution Shift=BodyMass2024.1032.095
AWRDistribution Shift=JointNoise2024.1031.742
ReinformerDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1031.584
DFDTDistribution Shift=JointNoise2024.1031.193
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1027.812
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1026.995
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1024.059
DTDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1020.966
BEARDistribution Shift=JointNoise2024.1018.337
D-BEARDistribution Shift=JointNoise2024.1017.929
D-AWRDistribution Shift=BodyMass2024.1017.918
AWRDistribution Shift=BodyMass2024.1015.988
BEARDistribution Shift=BodyMass2024.107.425
D-BEARDistribution Shift=BodyMass2024.104.909