List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Ant expert

23.1Normalized ScoreDARA
15.50817.47919.4521.421Dec 2, 2025
Updated 8mo ago

Evaluation results

MethodLinks
DARA2025.1223.1
OTDF2025.1222.7
IQL2025.1220.7
BOSA2025.1220.5
DVDF-IGDF2025.1219
DVDF-OTDF2025.1216.8
IGDF2025.1215.8