"Global Optimality without Mixing Time Oracles in Average-reward RL via ..."

Bhrij Patel et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2403.11925

access: open

type: Informal or Other Publication

metadata version: 2024-04-08

a service of  Schloss Dagstuhl - Leibniz Center for Informatics