A concentration bound for contractive stochastic approximation

DOI10.1016/J.SYSCONLE.2021.104947MaRDI QIDQ2242891zbMATH OpenOpenAlexFDO

Authors Vivek Borkar

Publication date 10 November 2021

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

Full work available at URL https://doi.org/10.1016/j.sysconle.2021.104947

zbMATH Keywords

concentration boundcontractive stochastic approximationmartingale concentrationreinforcement learningsample complexity

Mathematics Subject Classification ID

Dynamic programming (90C39) Stochastic systems in control theory (general) (93E03)

Recommendations

• Concentration bounds for stochastic approximations
• A stochastic contraction mapping theorem
• Corrigendum to: ``A concentration bound for contractive stochastic approximation
• A concentration bound for stochastic approximation via Alekseev's formula
• Stochastic Approximation and Large Deviations: Upper Bounds and <scp>w.p.1</scp> Convergence

Cites work

• \({\mathcal Q}\)-learning
• A concentration bound for stochastic approximation via Alekseev's formula
• Approximate dynamic programming. Solving the curses of dimensionality
• Concentration inequalities for Markov chains by Marton couplings and spectral methods
• Empirical dynamic programming
• Exponential inequalities for martingales and asymptotic properties of the free energy of directed polymers in a random environment
• scientific article; zbMATH DE number 1804127 (Why is no real title available?)
• scientific article; zbMATH DE number 5348356 (Why is no real title available?)
• scientific article; zbMATH DE number 51132 (Why is no real title available?)
• On the convergence, lock-in probability, and sample complexity of stochastic approximation
• On the Lock-in Probability of Stochastic Approximation

Cited in

(8)

• Corrigendum to: ``A concentration bound for contractive stochastic approximation
• A concentration bound for \(\operatorname{LSPE}( \lambda )\)
• Concentration bounds for stochastic approximations
• scientific article; zbMATH DE number 4113792 (Why is no real title available?)
• A concentration bound for stochastic approximation via Alekseev's formula
• Concentration of Contractive Stochastic Approximation and Reinforcement Learning
• Target Network and Truncation Overcome the Deadly Triad in \(\boldsymbol{Q}\)-Learning
• A stochastic contraction mapping theorem

This page was built for publication: A concentration bound for contractive stochastic approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2242891)