The actor-critic algorithm as multi-time-scale stochastic approximation

Borkar, Vivek S and Konda, Vijaymohan R (1997) The actor-critic algorithm as multi-time-scale stochastic approximation. In: Sadhana : Academy Proceedings in Engineering Sciences, 22 (part 4). pp. 525-543.

Preview

PDF The_actor-critic_algorithm.pdf - Published Version Download (975Kb)

Abstract

The actor-critic algorithm of Barto and others for simulation-based optimization of Markov decision processes is cast as a two time Scale stochastic approximation. Convergence analysis, approximation issues and an example are studied.

Item Type:	Journal Article
Additional Information:	Copyright of this article belongs to Indian Academy of Sciences.
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation (Formerly, School of Automation)
Date Deposited:	22 Jun 2011 07:16
Last Modified:	22 Jun 2011 07:16
URI:	http://eprints.iisc.ernet.in/id/eprint/38531

Actions (login required)

View Item