Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^{\pi }$-Realizability and Concentrability

Volodymyr Tkachuk, Gellért Weisz, Csaba Szepesvári

We consider offline reinforcement learning (RL) in $H$-horizon Markov decision processes (MDPs) under the linear $q^{\pi }$-realizability assumption, where the action-value function of…