ResearchBenchmarksPolicy Optimization on Office World Map 1, Exp 5Follow3,125Average Training StepsQR-MAXRM-49,552.8306,022.35661,597.51,017,172.65Dec 16, 2025Evaluation ResultsMethodMethodLinksAverage Training StepsQR-MAXRM2025.123,125QR-MAX2025.1224,222QRM2025.12225,140UCBVI-sB2025.12250,800R-MAX2025.12272,080UCBVI-B2025.12555,977UCBVI-H2025.121,320,070