List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on D4RL Walker2d Medium

87.7Normalized Avg ReturnMOBILE
15.00433.87752.7571.623Oct 30, 2023Feb 22, 2024Jun 17, 2024Oct 11, 2024Feb 4, 2025May 31, 2025Sep 24, 2025
Updated 4mo ago

Evaluation results

MethodLinks
MOBILEImplementation=Original Paper2024.1187.7
WFDiffuser2025.0986.1
MOPOImplementation=Original Paper2024.1184.1
C-LAPImplementation=Reproduced2024.1182.5
Decision Diffuser2025.0982.5
RGG+planning seeds=152023.1082
RGGplanning seeds=152023.1081.7
MOBILEImplementation=Reproduced2024.1181
IQLTraining timesteps=1M, Random seeds=102025.0980.88
Diffuser2023.1079.7
PLASImplementation=Reproduced2024.1179.4
TT2023.1079
TT2025.0979
IQL2023.1078.3
IQL2025.0978.3
MOPOImplementation=Reproduced2024.1178
MOREL2023.1077.8
MOReL2025.0977.8
BC2023.1075.3
BC2025.0975.3
DT2023.1074
DT2025.0974
CQL2023.1072.5
CQL2025.0972.5
PLASImplementation=Original Paper2024.1144.6
FQL+BCTraining timesteps=1M, Random seeds=102025.0944.6
MBOP2023.1041
MOPO2023.1017.8