Asynchronous stochastic approximation with differential inclusions

Perkins, Steven and Leslie, David S. (2012) Asynchronous stochastic approximation with differential inclusions. Stochastic Systems, 2. pp. 409-446. ISSN 1946-5238

[img]
Preview
PDF (409-446)
409_446.pdf - Submitted Version
Available under License Creative Commons Attribution.

Download (315kB)

Abstract

The asymptotic pseudo-trajectory approach to stochastic approximation of Benaïm, Hofbauer and Sorin is extended for asynchronous stochastic approximations with a set-valued mean field. The asynchronicity of the process is incorporated into the mean field to produce convergence results which remain similar to those of an equivalent synchronous process. In addition, this allows many of the restrictive assumptions previously associated with asynchronous stochastic approximation to be removed. The framework is extended for a coupled asynchronous stochastic approximation process with set-valued mean fields. Two-timescales arguments are used here in a similar manner to the original work in this area by Borkar. The applicability of this approach is demonstrated through learning in a Markov decision process.

Item Type:
Journal Article
Journal or Publication Title:
Stochastic Systems
ID Code:
70731
Deposited By:
Deposited On:
11 Sep 2014 10:56
Refereed?:
Yes
Published?:
Published
Last Modified:
02 Jul 2020 01:37