List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on MuJoCo walker2d medium 1M

85.4Final ScoreMOPO
61.16867.45973.7580.041Feb 27, 2025
Updated 7mo ago

Evaluation results

MethodLinks
MOPO2025.0285.4
TD3BC2025.0284.4
COMBO2025.0283.9
CQL2025.0283.6
IQL2025.0281.1
IO2025.0271.8
Dataset2025.0262.1