Loading [a11y]/accessibility-menu.js
On the mean-square rate of convergence of temporal-difference learning algorithms | IEEE Conference Publication | IEEE Xplore

On the mean-square rate of convergence of temporal-difference learning algorithms


Abstract:

In this paper, the mean-square rate of convergence of temporal-difference learning algorithms is analyzed. The analysis is carried out for the case of discounted cost fun...Show More

Abstract:

In this paper, the mean-square rate of convergence of temporal-difference learning algorithms is analyzed. The analysis is carried out for the case of discounted cost function associated with a Markov chain with a finite dimensional state-space. Under mild conditions, it is shown that these algorithms converge at the rate O(n/sup -1/2/). The results are illustrated with examples related to random coefficient autoregression models and M/G/1 queues.
Date of Conference: 08-10 May 2002
Date Added to IEEE Xplore: 07 November 2002
Print ISBN:0-7803-7298-0
Print ISSN: 0743-1619
Conference Location: Anchorage, AK, USA

References

References is not available for this document.