List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Walker2D Medium-Replay BodyMass Shift

87.491Average ReturnREAG*MV
48.808258.8508568.893578.93615Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
REAG*MVFramework=QT2024.1087.491
QTAugmentation Strategy=REAG_MV2024.1087.491
1T10SFramework=QT2024.1087.292
QTAugmentation Strategy=1T10S2024.1087.292
REAG*DaraFramework=QT2024.1076.169
QTAugmentation Strategy=REAG_Dara2024.1076.169
REAG*MVFramework=DT2024.1073.708
DTAugmentation Strategy=REAG_MV2024.1073.708
1T10SFramework=DT2024.1073.664
DTAugmentation Strategy=1T10S2024.1073.664
REAG*DaraFramework=DT2024.1067.565
DTAugmentation Strategy=REAG_Dara2024.1067.565
1T10SFramework=Reinformer2024.1067.032
ReinformerAugmentation Strategy=1T10S2024.1067.032
REAG*DaraFramework=Reinformer2024.1066.658
ReinformerAugmentation Strategy=REAG_Dara2024.1066.658
REAG*MVFramework=Reinformer2024.1050.296
ReinformerAugmentation Strategy=REAG_MV2024.1050.296