Gellért Weisz

Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^π$-Realizability and Concentrability

2024 · arXiv (Cornell University)

We consider offline reinforcement learning (RL) in $H$-horizon Markov decision processes (MDPs) under the linear $q^π$-realizability assumption, where the action-value function of every policy is linear with respect to a given $d$-dimensional feature function. The …