List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on D4RL Walker2d Med-Replay

82.6Normalized Average ReturnTT
6.78426.46746.1565.833Oct 30, 2023Feb 19, 2024Jun 11, 2024Oct 1, 2024Jan 22, 2025May 14, 2025Sep 4, 2025
Updated 5mo ago

Evaluation results

MethodLinks
TT2023.1082.6
TT2025.0982.6
RGGplanning seeds=152023.1078.3
RGG+planning seeds=152023.1077.5
CQL2023.1077.2
CQL2025.0977.2
WFDiffuser2025.0976.3
Decision Diffuser2025.0975
IQL2023.1073.9
IQL2025.0973.9
DT2023.1066.6
DT2025.0966.6
Diffuser2023.1061.2
MOREL2023.1049.8
MOReL2025.0949.8
MOPO2023.1039
BC2023.1026
BC2025.0926
MBOP2023.109.7