List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Hopper Medium-Replay 1T10S

93.704Average ReturnQT
14.487235.053155.61976.1849Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
QTDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1093.704
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1093.409
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1083.525
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1082.786
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1077.825
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1076.287
QTDistribution Shift=BodyMass (BM), Base Architecture=QT2024.1069.46
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1066.092
DTDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1064.216
DTDistribution Shift=JointNoise (JN), Base Architecture=DT2024.1061.87
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=DT2024.1060.393
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1052.052
REAG*DaraDistribution Shift=JointNoise (JN), Base Architecture=QT2024.1051.456
REAG*MVDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1043.985
ReinformerDistribution Shift=JointNoise (JN), Base Architecture=Reinformer2024.1041.82
REAG*DaraDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1027.238
REAG*MVDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1020.952
ReinformerDistribution Shift=BodyMass (BM), Base Architecture=Reinformer2024.1017.534