Q-learning for risk-sensitive control

Borkar, V. S. (2002) Q-learning for risk-sensitive control Mathematics of Operations Research, 27 (2). pp. 294-311. ISSN 0364-765X

Full text not available from this repository.

Official URL: http://mor.journal.informs.org/content/27/2/294.ab...

Related URL: http://dx.doi.org/10.1287/moor.


We propose for risk-sensitive control of finite Markov chains a counterpart of the popular Q-learning algorithm for classical Markov decision processes. The algorithm is shown to converge with probability one to the desired solution. The proof technique is an adaptation of the o.d.e. approach for the analysis of stochastic approximation algorithms, with most of the work involved used for the analysis of the specific o.d.e.s that arise.

Item Type:Article
Source:Copyright of this article belongs to INFORMS.
Keywords:Markov Decision Processes; Risk-sensitive Control; Reinforcement Learning; Q-learning; Stochastic Approximation; Dynamic Programming
ID Code:81452
Deposited On:06 Feb 2012 05:04
Last Modified:06 Feb 2012 05:04

Repository Staff Only: item control page