List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Hopper Medium BodyMass Shift

82.786Average ReturnREAG*Dara
14.9239232.5419650.1667.77804Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
REAG*DaraFramework=QT2024.1082.786
REAG*MVFramework=QT2024.1076.287
1T10SFramework=QT2024.1069.46
REAG*MVFramework=DT2024.1066.092
1T10SFramework=DT2024.1064.216
REAG*DaraFramework=QT2024.1062.262
QTAugmentation Strategy=REAG_Dara2024.1062.262
REAG*DaraFramework=DT2024.1060.393
REAG*MVFramework=Reinformer2024.1059.085
ReinformerAugmentation Strategy=REAG_MV2024.1059.085
REAG*MVFramework=QT2024.1051.796
QTAugmentation Strategy=REAG_MV2024.1051.796
REAG*DaraFramework=Reinformer2024.1051.771
ReinformerAugmentation Strategy=REAG_Dara2024.1051.771
1T10SFramework=Reinformer2024.1051.357
ReinformerAugmentation Strategy=1T10S2024.1051.357
1T10SFramework=QT2024.1049.516
QTAugmentation Strategy=1T10S2024.1049.516
REAG*MVFramework=DT2024.1039.435
DTAugmentation Strategy=REAG_MV2024.1039.435
REAG*DaraFramework=DT2024.1037.787
DTAugmentation Strategy=REAG_Dara2024.1037.787
1T10SFramework=DT2024.1034.057
DTAugmentation Strategy=1T10S2024.1034.057
REAG*DaraFramework=Reinformer2024.1027.238
REAG*MVFramework=Reinformer2024.1020.952
1T10SFramework=Reinformer2024.1017.534