Online RL in Linearly $q^π$ -Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore

11 October 2023

Papers citing "Online RL in Linearly $q^π$-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore"

1 / 1 papers shown

Title
Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^π$ -Realizability and Concentrability Volodymyr Tkachuk Gellert Weisz Csaba Szepesvári OffRL 21 0 0 27 May 2024