Trajectory Data Suffices for Statistically Efficient Policy Evaluation in Fixed-Horizon Offline RL with Linear $q^{\ddot{I}}€$-Realizability and Concentrability

Volodymyr Tkachuk, Csaba Szepesvári, Xiaoqi Tan

We study finite-horizon offline reinforcement learning (RL) with function approximation for both policy evaluation and policy optimization. Prior work established that statisticall…