List your company

Offline Reinforcement Learning on 1T10S HalfCheetah Medium

61.447ScoreD-MOPO
-0.4319615.6327731.697547.76223Oct 30, 2024

Evaluation results

MethodLinks
D-MOPODistribution Shift=JointNoise2024.1061.447
MOPODistribution Shift=JointNoise2024.1061.073
D-MOPODistribution Shift=BodyMass2024.1059.311
MOPODistribution Shift=BodyMass2024.1058.457
H2ODistribution Shift=JointNoise2024.1057.924
QTDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1056.213
H2ODistribution Shift=BodyMass2024.1055.566
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1055.026
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1052.394
D-BCQDistribution Shift=JointNoise2024.1052.149
BCQDistribution Shift=JointNoise2024.1050.511
D-CQLDistribution Shift=JointNoise2024.1049.284
CQLDistribution Shift=JointNoise2024.1049.046
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1048.404
ReinformerDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1048.274
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1047.833
DTDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1047.725
REAG*MVBase Algorithm=QT, Distribution Shift=Kinematic, Dataset Config=1T target, 10S source2024.1047.698
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1047.303
IGDFDistribution Shift=BodyMass2024.1047.239
IGDFDistribution Shift=JointNoise2024.1046.647
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1046.383
QTDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1044.656
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1044.149
QTFramework=Baseline, Distribution Shift=Kinematic, Dataset Config=1T target, 10S source2024.1043.968
REAG*DaraBase Algorithm=QT, Distribution Shift=Kinematic, Dataset Config=1T target, 10S source2024.1043.896
DFDTDistribution Shift=JointNoise2024.1043.76
DFDTDistribution Shift=BodyMass2024.1043.58
REAG*DaraBase Algorithm=Reinformer, Distribution Shift=Kinematic, Dataset Config=1T target, 10S source2024.1043.092
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1043.009
ReinformerFramework=Baseline, Distribution Shift=Kinematic, Dataset Config=1T target, 10S source2024.1042.929
REAG*MVBase Algorithm=Reinformer, Distribution Shift=Kinematic, Dataset Config=1T target, 10S source2024.1042.826
REAG*MVBase Algorithm=DT, Distribution Shift=Kinematic, Dataset Config=1T target, 10S source2024.1042.752
D-AWRDistribution Shift=JointNoise2024.1042.545
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1042.451
AWRDistribution Shift=BodyMass2024.1042.293
DTFramework=Baseline, Distribution Shift=Kinematic, Dataset Config=1T target, 10S source2024.1042.277
AWRDistribution Shift=JointNoise2024.1041.992
D-AWRDistribution Shift=BodyMass2024.1041.8
REAG*DaraBase Algorithm=DT, Distribution Shift=Kinematic, Dataset Config=1T target, 10S source2024.1041.257
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1040.25
DTDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1039.954
BCQDistribution Shift=BodyMass2024.1039.835
D-BCQDistribution Shift=BodyMass2024.1039.333
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1038.261
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1037.599
ReinformerDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1037.353
D-CQLDistribution Shift=BodyMass2024.1037.189
CQLDistribution Shift=BodyMass2024.1037.081
D-BEARDistribution Shift=BodyMass2024.106.009
BEARDistribution Shift=BodyMass2024.105.431
D-BEARDistribution Shift=JointNoise2024.102.901
BEARDistribution Shift=JointNoise2024.101.948