List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on D4RL Hopper Med-Expert

114.7Normalized Average ReturnWFDiffuser
20.0644.6369.293.77Oct 30, 2023Feb 19, 2024Jun 11, 2024Oct 1, 2024Jan 22, 2025May 14, 2025Sep 4, 2025
Updated 5mo ago

Evaluation results

MethodLinks
WFDiffuser2025.09114.7
TTConfiguration=Trifle2023.10113
DD2023.10111.8
Decision Diffuser2025.09111.8
%BC2023.10110.9
TT2023.10110
TTConfiguration=base2023.10110
TT2025.09110
RGG+planning seeds=152023.10109.9
RGGplanning seeds=152023.10109.6
MOREL2023.10108.7
MOReL2025.09108.7
DT2023.10107.6
DTConfiguration=base2023.10107.6
DT2025.09107.6
Diffuser2023.10107.2
CQL2023.10105.4
CQL2023.10105.4
CQL2025.09105.4
TD3(+BC)2023.1098
IQL2023.1091.5
IQL2023.1091.5
IQL2025.0991.5
TT(+Q)Configuration=Trifle2023.1078.5
TT(+Q)Configuration=base2023.1074.7
MBOP2023.1055.1
BC2023.1052.5
BC2025.0952.5
MOPO2023.1023.7