Remarks on Differential Inclusion limits of Stochastic Approximation

MaRDI QIDQ6428823zbMATH OpenFDO

Authors Vivek Borkar, Dhruv A. Shah

Publication date 8 March 2023

Mathematics Subject Classification ID

Stochastic approximation (62L20) Ordinary differential inclusions (34A60) Asymptotic properties of solutions to ordinary differential equations (34D05)

Abstract: For stochastic approximation algorithms with discontinuous dynamics, it is shown that under suitable distributional assumptions, the interpolated iterates track a Fillipov solution of the limiting differential inclusion. In addition, we give an alternative control theoretic approach to recent results of [7] on certain limiting empirical measures associated with the iteration.

Recommendations

• Stochastic approximation with `controlled Markov' noise
• Stochastic Approximations and Differential Inclusions
• Stochastic recursive inclusions with non-additive iterate-dependent Markov noise
• Stochastic Approximations and Differential Inclusions, Part II: Applications
• Convergence of Markovian stochastic approximation with discontinuous dynamics

Cited in

(2)

• Stochastic approximation and reinforcement learning: the interface and a little beyond
• Stochastic approximation with two time scales: the general case

This page was built for publication: Remarks on Differential Inclusion limits of Stochastic Approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6428823)