Stochastic Approximation With Iterate-Dependent Markov Noise Under Verifiable Conditions in Compact State Space With the Stability of Iterates Not Ensured

DOI10.1109/TAC.2021.3057299MaRDI QIDQ5033892zbMATH OpenFDO

Authors Prasenjit Karmakar, Shalabh Bhatnagar

Publication date 24 February 2022

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1601.02217

Mathematics Subject Classification ID

Systems theory; control (93-XX)

Recommendations

• Stability of Stochastic Approximation under Verifiable Conditions
• An Invariant Measure Approach to the Convergence of Stochastic Approximations with State Dependent Noise
• Stability and convergence of stochastic approximation procedures under Markovian structural perturbations
• Stochastic approximation with `controlled Markov' noise
• Convergence of stochastic approximation procedures with dependent noise
• Stability of Stochastic Approximations With “Controlled Markov” Noise and Temporal Difference Learning
• Convergence of Markovian stochastic approximation with discontinuous dynamics
• Almost sure convergence of stochastic approximation algorithms with non-additive noise
• scientific article; zbMATH DE number 3864328

Cited in

(2)

• Finite-sample analysis of nonlinear stochastic approximation with applications in reinforcement learning
• Dynamics of stochastic approximation with iterate-dependent Markov noise under verifiable conditions in compact state space with the stability of iterates not ensured

This page was built for publication: Stochastic Approximation With Iterate-Dependent Markov Noise Under Verifiable Conditions in Compact State Space With the Stability of Iterates Not Ensured

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5033892)