A concentration bound for LSPE( )

DOI10.1016/J.SYSCONLE.2022.105418MaRDI QIDQ2677709zbMATH OpenOpenAlexFDO

Authors Siddharth Chandak, Vivek Borkar, Harsh Dolhare

Publication date 5 January 2023

Published in Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2111.02644

zbMATH Keywords

\(\operatorname{LSPE}( \lambda )\)concentration boundpolicy evaluationreinforcement learning

Mathematics Subject Classification ID

Stochastic systems in control theory (general) (93E03)

Abstract: The popular LSPE($lambda$) algorithm for policy evaluation is revisited to derive a concentration bound that gives high probability performance guarantees from some time on.

Cites work

• A concentration bound for contractive stochastic approximation
• A concentration bound for stochastic approximation via Alekseev's formula
• A finite time analysis of temporal difference learning with linear function approximation
• Concentration bounds for temporal difference learning with linear function approximation: the case of batch data and uniform sampling
• Concentration inequalities for Markov chains by Marton couplings and spectral methods
• Convergence Results for Some Temporal Difference Methods Based on Least Squares
• Fast projection methods for minimal design problems in linear system theory
• Finite-sample analysis of least-squares policy iteration
• scientific article; zbMATH DE number 5957196 (Why is no real title available?)
• scientific article; zbMATH DE number 6159604 (Why is no real title available?)
• Least squares policy evaluation algorithms with linear function approximation
• On the convergence, lock-in probability, and sample complexity of stochastic approximation
• On the Lock-in Probability of Stochastic Approximation

This page was built for publication: A concentration bound for \(\operatorname{LSPE}( \lambda )\)

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2677709)