List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Hopper Medium-Expert BodyMass Shift

77.279Average ReturnREAG*Dara
31.80543.6107555.416567.22225Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
REAG*DaraFramework=QT2024.1077.279
QTAugmentation Strategy=REAG_Dara2024.1077.279
REAG*MVFramework=QT2024.1073.952
QTAugmentation Strategy=REAG_MV2024.1073.952
REAG*DaraFramework=Reinformer2024.1073.363
ReinformerAugmentation Strategy=REAG_Dara2024.1073.363
1T10SFramework=Reinformer2024.1068.973
ReinformerAugmentation Strategy=1T10S2024.1068.973
REAG*MVFramework=Reinformer2024.1064.206
ReinformerAugmentation Strategy=REAG_MV2024.1064.206
1T10SFramework=QT2024.1061.162
QTAugmentation Strategy=1T10S2024.1061.162
REAG*MVFramework=DT2024.1052.873
DTAugmentation Strategy=REAG_MV2024.1052.873
REAG*DaraFramework=DT2024.1033.631
DTAugmentation Strategy=REAG_Dara2024.1033.631
1T10SFramework=DT2024.1033.554
DTAugmentation Strategy=1T10S2024.1033.554