List your company

Policy Optimization on Office World MAP0

4,150Avg Training StepsQR-MAXRM
-3,363.3247,351.5998,066.5148,781.41Dec 16, 2025

Evaluation results

MethodLinks
QR-MAXRMExp=EXP02025.124,150
QR-MAXRM2025.124,150
QR-MAXExp=EXP02025.1214,483
QR-MAX2025.1214,483
R-MAXExp=EXP02025.1249,759
R-MAX2025.1249,759
PSRLExp=EXP0, posterior_samples=8 per episode2025.1288,437
PSRLposterior samples per episode=82025.1288,437
OPSRLExp=EXP0, posterior_samples=8 per episode2025.12128,188
OPSRLposterior samples per episode=82025.12128,188
UCBVI-sBExp=EXP02025.12142,015
UCBVI-sB2025.12142,015
UCBVI-BExp=EXP02025.12159,092
UCBVI-B2025.12159,092
QRMExp=EXP02025.12162,040
QRM2025.12162,040
UCBVI-HExp=EXP02025.12191,983
UCBVI-H2025.12191,983