Statistical inference of the value function for reinforcement learning in infinite-horizon settings

DOI10.1111/rssb.12465MaRDI QIDQ6600840

Chengchun Shi, Sheng Zhang, Wen-Bin Lu, Rui Song

Publication date: 10 September 2024

Published in: Journal of the Royal Statistical Society. Series B. Statistical Methodology (Search for Journal in Brave)

zbMATH Keywords

confidence intervalreinforcement learningvalue functioninfinite horizonsbidirectional asymptotics

Mathematics Subject Classification ID

Statistics (62-XX)

Related Items (2)

Deep spectral Q-learning with application to mobile health ⋮ Reinforcement Learning in Latent Heterogeneous Environments

This page was built for publication: Statistical inference of the value function for reinforcement learning in infinite-horizon settings