List your company
ResearchFormerly WizWand

Reinforcement Learning on Office World Map 2

16,240Training StepsQR-MAXRM
-22,212.48237,341.76496,896756,450.24Dec 16, 2025
Updated 8mo ago

Evaluation results

MethodLinks
QR-MAXRM2025.1216,240
R-MAXRM2025.1260,058
QR-MAX2025.1269,494
QRM2025.12282,943
R-MAX2025.12307,805
Q-Learning2025.12977,552