List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on D4RL Adroit pen-human v1 (test)

72.8Normalized ScoreDiffusion-QL
-6.7613.89534.5555.205Mar 12, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Diffusion-QL2024.0372.8
IQL2024.0371.5
A2PO2024.0368.9
LAPO2024.0368.1
MOPO2024.0354.6
EQL2024.0344.3
CQL2024.0337.5
BC2024.0334.4
BCQ2024.0312.3
AWAC2024.034.3
CQL+AW2024.03-3
TD3+BC2024.03-3.7