Avoidance of traps in stochastic approximation

DOI10.1016/S0167-6911(03)00118-XzbMATH Open1157.62479OpenAlexW2088767712MaRDI QIDQ2503522FDOQ2503522

Authors: Vivek Borkar 

Publication date: 21 September 2006

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

Full work available at URL: https://doi.org/10.1016/s0167-6911(03)00118-x

Recommendations

• Do stochastic algorithms avoid traps?
• Publication:4862190
• Stochastic Approximation and Large Deviations: Upper Bounds and <scp>w.p.1</scp> Convergence
• On the Lock-in Probability of Stochastic Approximation
• On the convergence, lock-in probability, and sample complexity of stochastic approximation

Mathematics Subject Classification ID

Stochastic approximation (62L20)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Some Pathological Traps for Stochastic Approximation
• Title not available (Why is that?)
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• Nonconvergence to unstable points in urn models and stochastic approximations
• Title not available (Why is that?)
• Do stochastic algorithms avoid traps?
• Strong convergence of a stochastic approximation algorithm
• Convergence of stochastic-approximation procedures in the case of regression equation with several roots
• On the Lock-in Probability of Stochastic Approximation

Cited In (3)

• On the convergence, lock-in probability, and sample complexity of stochastic approximation
• Title not available (Why is that?)
• Q-learning for continuous-time linear systems: A model-free infinite horizon optimal control approach

This page was built for publication: Avoidance of traps in stochastic approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2503522)