List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Walker2D Medium BodyMass Shift

94.578Average ReturnREAG*Dara
77.6041682.0108386.417590.82417Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
REAG*DaraFramework=QT2024.1094.578
1T10SFramework=QT2024.1093.082
REAG*MVFramework=QT2024.1092.744
REAG*MVFramework=DT2024.1088.235
REAG*DaraFramework=DT2024.1085.328
REAG*MVFramework=Reinformer2024.1084.897
REAG*MVFramework=QT2024.1084.582
QTAugmentation Strategy=REAG_MV2024.1084.582
1T10SFramework=DT2024.1084.43
1T10SFramework=QT2024.1084.325
QTAugmentation Strategy=1T10S2024.1084.325
REAG*DaraFramework=Reinformer2024.1083.761
1T10SFramework=Reinformer2024.1083.388
REAG*DaraFramework=QT2024.1083.068
QTAugmentation Strategy=REAG_Dara2024.1083.068
REAG*MVFramework=Reinformer2024.1082.354
ReinformerAugmentation Strategy=REAG_MV2024.1082.354
REAG*MVFramework=DT2024.1080.857
1T10SFramework=Reinformer2024.1080.857
DTAugmentation Strategy=REAG_MV2024.1080.857
ReinformerAugmentation Strategy=1T10S2024.1080.857
REAG*DaraFramework=Reinformer2024.1080.666
ReinformerAugmentation Strategy=REAG_Dara2024.1080.666
1T10SFramework=DT2024.1078.768
DTAugmentation Strategy=1T10S2024.1078.768
REAG*DaraFramework=DT2024.1078.257
DTAugmentation Strategy=REAG_Dara2024.1078.257