List your company
ResearchFormerly WizWand

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

85Normalized ScoreA2PO
-617.62541.2564.875Mar 12, 2024
Updated 8mo ago

Evaluation results

MethodLinks
A2PO2024.0385
Diffusion-QL2024.0357.3
BC2024.0356.9
LAPO2024.0355.8
EQL2024.0346.9
CQL2024.0339.2
IQL2024.0337.3
BCQ2024.0328
MOPO2024.0310.7
TD3+BC2024.031.7
AWAC2024.03-0.8
CQL+AW2024.03-2.5