List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on HalfCheetah BodyMass Shift (Medium-Expert)

76.533Average ReturnREAG*Dara
39.129448.8399558.550568.26105Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
REAG*DaraFramework=QT2024.1076.533
QTAugmentation Strategy=REAG_Dara2024.1076.533
1T10SFramework=QT2024.1071.08
QTAugmentation Strategy=1T10S2024.1071.08
REAG*MVFramework=QT2024.1069.819
QTAugmentation Strategy=REAG_MV2024.1069.819
REAG*MVFramework=DT2024.1056.228
DTAugmentation Strategy=REAG_MV2024.1056.228
REAG*DaraFramework=Reinformer2024.1055.818
ReinformerAugmentation Strategy=REAG_Dara2024.1055.818
1T10SFramework=DT2024.1054.981
DTAugmentation Strategy=1T10S2024.1054.981
REAG*DaraFramework=DT2024.1051.357
DTAugmentation Strategy=REAG_Dara2024.1051.357
REAG*MVFramework=Reinformer2024.1046.048
ReinformerAugmentation Strategy=REAG_MV2024.1046.048
1T10SFramework=Reinformer2024.1040.568
ReinformerAugmentation Strategy=1T10S2024.1040.568