List your company

Online KL-Regularized MDP Learning on MDPs

2Sample ComplexityOnline Iterative M-GSHF
1.91.9522.05Feb 11, 2025

Evaluation results

MethodLinks
Online Iterative M-GSHFCoverage=×2025.022—
XPOCoverage=×2025.022—
KL-LSVI-UCBCoverage=×2025.0222