ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Two-timescale Q-learning Algorithms with an Application to Routing in Networks

Mohan Babu, K and Bhatnagar, Shalabh (2007) Two-timescale Q-learning Algorithms with an Application to Routing in Networks. In: International Conference on Advances in Control and Optimization of Dynamical Systems, ACODS- Bangalore, Feb. 2007, Bangalore.

[img]
Preview
PDF
10.1.1.130.7691.pdf - Published Version

Download (2043Kb)
Official URL: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=1...

Abstract

We propose two variants of the Q-learning algorithm that (both) use two timescales. One of these updates Q-values of all feasible state-action pairs at each instant while the other updates Q-values of states with actions chosen according to the ‘current ’ randomized policy updates. A sketch of convergence of the algorithms is shown. Finally, numerical experiments using the proposed algorithms for routing on different network topologies are presented and performance comparisons with the regular Q-learning algorithm are shown.

Item Type: Conference Paper
Keywords: Q-learning based algorithms;Markov decision processes;two- timescale stochastic approximation;simultaneous perturbation stochastic approximation (SPSA);normalized Hadamard matrices
Department/Centre: Division of Electrical Sciences > Computer Science & Automation (Formerly, School of Automation)
Date Deposited: 17 Oct 2011 05:22
Last Modified: 17 Oct 2011 05:22
URI: http://eprints.iisc.ernet.in/id/eprint/41467

Actions (login required)

View Item View Item