List your company
ResearchFormerly WizWand

Reinforcement Learning on Office World Map 1

7,312Training StepsQR-MAXRM
-11,776.64117,071.68245,920374,768.32Dec 16, 2025
Updated 8mo ago

Evaluation results

MethodLinks
QR-MAXRM2025.127,312
R-MAXRM2025.1226,776
QR-MAX2025.1231,316
R-MAX2025.12136,622
QRM2025.12137,263
Q-Learning2025.12484,528