"VOQL: Towards Optimal Regret in Model-free RL with Nonlinear Function ..."

Alekh Agarwal, Yujia Jin, Tong Zhang (2022)

Details and statistics

DOI: 10.48550/ARXIV.2212.06069

access: open

type: Informal or Other Publication

metadata version: 2023-02-08

a service of  Schloss Dagstuhl - Leibniz Center for Informatics