List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Hopper Medium JointNoise Shift

109.803Average ReturnREAG*MV
67.0101278.1198189.2295100.33919Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
REAG*MVFramework=QT2024.10109.803
REAG*DaraFramework=QT2024.10109.746
REAG*MVFramework=Reinformer2024.10109.472
REAG*MVFramework=DT2024.10109.367
1T10SFramework=Reinformer2024.10109.256
REAG*DaraFramework=Reinformer2024.10109.255
1T10SFramework=QT2024.10109.056
REAG*DaraFramework=DT2024.10108.261
1T10SFramework=DT2024.10108.254
REAG*DaraFramework=DT2024.1078.325
DTAugmentation Strategy=REAG_Dara2024.1078.325
REAG*MVFramework=QT2024.1073.987
QTAugmentation Strategy=REAG_MV2024.1073.987
REAG*MVFramework=Reinformer2024.1072.346
ReinformerAugmentation Strategy=REAG_MV2024.1072.346
1T10SFramework=DT2024.1070.685
DTAugmentation Strategy=1T10S2024.1070.685
REAG*DaraFramework=Reinformer2024.1070.466
ReinformerAugmentation Strategy=REAG_Dara2024.1070.466
REAG*MVFramework=DT2024.1070.356
DTAugmentation Strategy=REAG_MV2024.1070.356
1T10SFramework=Reinformer2024.1070.34
ReinformerAugmentation Strategy=1T10S2024.1070.34
REAG*DaraFramework=QT2024.1068.709
QTAugmentation Strategy=REAG_Dara2024.1068.709
1T10SFramework=QT2024.1068.656
QTAugmentation Strategy=1T10S2024.1068.656