Ergodic Learning Algorithms

S. Lakshmivarahan
Additional contact information
S. Lakshmivarahan: University of Oklahoma, School of Electrical Engineering and Computer Science

Chapter Chapter 2 in Learning Algorithms Theory and Applications, 1981, pp 19-65 from Springer

Abstract: Abstract This chapter presents an analysis of general non-linear reward-penalty ergodic-N R-P E algorithms. The basic property that characterizes this class of algorithms is that all the states under this class of algorithms are non-absorbing. The now classic linear reward-penalty — LER−P algorithm is a special case of this algorithm. It is well known [C1] that this LER−P algorithm is only expedient. Using the theory of Markov processes that evolve by small steps [N14] a variety of characterizations of the process p(k) k ≥ 0 such as the evolution of the mean and variance and in fact its actual sample path behavior are given. As a by-product, it is proved that there exists a proper choice of parameters and functions such that the NER−P algorithm is ε-optimal.

Keywords: Markov Process; Central Limit Theorem; Unique Zero; Jump Markov Process; Transition Probability Density (search for similar items in EconPapers)
Date: 1981
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-1-4612-5975-6_2

Ordering information: This item can be ordered from
http://www.springer.com/9781461259756

DOI: 10.1007/978-1-4612-5975-6_2

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().