A reinforcement learning neural network for adaptive control of Markov chains

Santharam, G and Sastry, PS (1997) A reinforcement learning neural network for adaptive control of Markov chains. In: Ieee Transactions On Systems, Man, And Cybernetics—Part A: Systems And Humans, 27 (5). pp. 588-600.

PDF a_R.pdf - Published Version Restricted to Registered users only Download (586kB) | Request a copy

Abstract

In this paper we consider the problem of reinforcement learning in a dynamically changing environment. In this context, we study the problem of adaptive control of finite-state Markov chains with a finite number of controls, The transition and payoff structures are unknown, The objective is to find an optimal policy which maximizes the expected total discounted payoff over the infinite horizon, A stochastic neural network model is suggested for the controller. The parameters of the neural nee, which determine a random control strategy, are updated at each instant using a simple learning scheme, This learning scheme involves estimation of some relevant parameters using an adaptive critic, It is proved that the controller asymptotically chooses an optimal action in each state of the Markov chain with a high probability.

Item Type:	Journal Article
Publication:	Ieee Transactions On Systems, Man, And Cybernetics—Part A: Systems And Humans
Publisher:	Ieee-Inst Electrical Electronics Engineers
Additional Information:	Copyright of this article belongs to Ieee-Inst Electrical Electronics Engineers.
Keywords:	Adaptive critic;automata;generalized learning;reinforcement learning
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	11 Feb 2010 06:49
Last Modified:	19 Sep 2010 05:01
URI:	http://eprints.iisc.ac.in/id/eprint/18406

Actions (login required)

View Item