Non-Markovian Policies in Sequential Decision Problems

Non-Markovian Policies in Sequential Decision Problems. Szepesvári, C. Acta Cybernetica, 13(3):305–318, 1998.

In this article we prove the validity of the Bellman Optimality Equation and related results for sequential decision problems with a general recursive structure. The characteristic feature of our approach is that also non-Markovian policies are taken into account. The theory is motivated by some experiments with a learning robot.

@article{Szepesvari1998a,
	abstract = {In this article we prove the validity of the Bellman Optimality Equation and related results for sequential decision problems with a general recursive structure. The characteristic feature of our approach is that also non-Markovian policies are taken into account. The theory is motivated by some experiments with a learning robot.},
	author = {Szepesv{\'a}ri, Cs.},
	date-added = {2010-08-28 17:38:14 -0600},
	date-modified = {2010-09-02 13:09:16 -0600},
	journal = {Acta Cybernetica},
	keywords = {sequential decision making, theory},
	number = {3},
	pages = {305--318},
	title = {Non-Markovian Policies in Sequential Decision Problems},
	url_paper = {accyb97.ps.pdf},
	volume = {13},
	year = {1998}}

Downloads: 0