A constrained optimization perspective on actor-critic algorithms and application to network routing

Prashanth, LA and Prasad, HL and Bhatnagar, Shalabh and Chandra, Prakash (2016) A constrained optimization perspective on actor-critic algorithms and application to network routing. In: SYSTEMS & CONTROL LETTERS, 92 . pp. 46-51.

PDF Sys_Con_Let_92_46_2016.pdf - Published Version Restricted to Registered users only Download (480kB) | Request a copy

Abstract

We propose a novel actor-critic algorithm with guaranteed convergence to an optimal policy for a discounted reward Markov decision process. The actor incorporates a descent direction that is motivated by the solution of a certain non-linear optimization problem. We also discuss an extension to incorporate function approximation and demonstrate the practicality of our algorithms on a network routing application. (C) 2016 Elsevier B.V. All rights reserved.

Item Type:	Journal Article
Publication:	SYSTEMS & CONTROL LETTERS
Publisher:	ELSEVIER SCIENCE BV
Additional Information:	Copy right for this article belongs to the ELSEVIER SCIENCE BV, PO BOX 211, 1000 AE AMSTERDAM, NETHERLANDS
Keywords:	Actor-critic algorithm; Reinforcement learning; Constrained optimization
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	08 Jul 2016 06:43
Last Modified:	06 Nov 2018 07:39
URI:	http://eprints.iisc.ac.in/id/eprint/54151

Actions (login required)

View Item