CaltechAUTHORS
  A Caltech Library Service

Finite-Time Analysis of Asynchronous Stochastic Approximation and Q-Learning

Qu, Guannan and Wierman, Adam (2020) Finite-Time Analysis of Asynchronous Stochastic Approximation and Q-Learning. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20200214-105555380

[img] PDF - Accepted Version
See Usage Policy.

301Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200214-105555380

Abstract

We consider a general asynchronous Stochastic Approximation (SA) scheme featuring a weighted infinity-norm contractive operator, and prove a bound on its finite-time convergence rate on a single trajectory. Additionally, we specialize the result to asynchronous


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
http://arxiv.org/abs/2002.00260arXivDiscussion Paper
Additional Information:© 2020 G. Qu & A. Wierman. to appear in Proceedings of Machine Learning Research.
Subject Keywords:Stochastic approximation, Q-learning, finite time analysis
Record Number:CaltechAUTHORS:20200214-105555380
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200214-105555380
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:101300
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:14 Feb 2020 21:04
Last Modified:14 Feb 2020 21:04

Repository Staff Only: item control page