Volodymyr Tkachuk

collaborators

2 papers

cs.LG2026

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

Volodymyr Tkachuk, Csaba SzepesvÃ¡ri, 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…

cs.LG2024

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

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

Trajectory Data Suffices for Statistically Efficient Policy Evaluation in Fixed-Horizon Offline RL with Linear qI¨-Realizability and Concentrability

Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear qI¨-Realizability and Concentrability

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

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