List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on D4RL HalfCheetah Med-Expert

105.9Normalized ReturnMBOP
51.19665.39879.693.802Oct 30, 2023Feb 19, 2024Jun 11, 2024Oct 1, 2024Jan 22, 2025May 14, 2025Sep 4, 2025
Updated 5mo ago

Evaluation results

MethodLinks
MBOP2023.10105.9
TT2023.1095
TT2025.0995
WFDiffuser2025.0992.8
CQL2023.1091.6
CQL2025.0991.6
RGG+planning seeds=152023.1091.2
RGGplanning seeds=152023.1090.8
Decision Diffuser2025.0990.6
DT2023.1086.8
DT2025.0986.8
IQL2023.1086.7
IQL2025.0986.7
Diffuser2023.1079.8
MOPO2023.1063.3
BC2023.1055.2
BC2025.0955.2
MOREL2023.1053.3
MOReL2025.0953.3