Stochastic approximation with `controlled Markov' noise

DOI10.1016/J.SYSCONLE.2005.06.005zbMATH Open1129.62407OpenAlexW1997394097MaRDI QIDQ2504641FDOQ2504641

Authors: Vivek Borkar 

Publication date: 25 September 2006

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

Full work available at URL: https://doi.org/10.1016/j.sysconle.2005.06.005

Recommendations

• Stochastic recursive inclusions with non-additive iterate-dependent Markov noise
• An Invariant Measure Approach to the Convergence of Stochastic Approximations with State Dependent Noise
• Stochastic approximation with random truncations, state-dependent noise and discontinuous dynamics
• scientific article; zbMATH DE number 1972910
• Stochastic approximation with long range dependent and heavy tailed noise

zbMATH Keywords

stochastic approximationdifferential inclusionsinvariant setscontrolled Markov noiseergodic occupation measures

Mathematics Subject Classification ID

Stochastic approximation (62L20)

Cites Work

• Markov chains and stochastic stability
• Title not available (Why is that?)
• Title not available (Why is that?)
• Stochastic Approximations and Differential Inclusions
• Selection theorems and their applications
• The value function in ergodic control of diffusion processes with partial observations

Cited In (11)

• Stochastic recursive inclusions with non-additive iterate-dependent Markov noise
• On sampling controlled stochastic approximation
• On tight bounds for function approximation error in risk-sensitive reinforcement learning
• Stochastic Approximations and Differential Inclusions, Part II: Applications
• Remarks on Differential Inclusion limits of Stochastic Approximation
• Stochastic Approximation With Iterate-Dependent Markov Noise Under Verifiable Conditions in Compact State Space With the Stability of Iterates Not Ensured
• Asynchronous stochastic approximation with differential inclusions
• Stochastic Recursive Inclusions in Two Timescales with Nonadditive Iterate-Dependent Markov Noise
• Two Time-Scale Stochastic Approximation with Controlled Markov Noise and Off-Policy Temporal-Difference Learning
• Linear stochastic approximation driven by slowly varying Markov chains
• Stochastic approximation with long range dependent and heavy tailed noise

This page was built for publication: Stochastic approximation with `controlled Markov' noise

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2504641)