"Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step ..."

Haike Xu, Tengyu Ma, Simon S. Du (2021)

Details and statistics

DOI:

access: open

type: Informal or Other Publication

metadata version: 2021-08-08

a service of  Schloss Dagstuhl - Leibniz Center for Informatics