Approximation solution and suboptimality for discounted semi-markov decision problems with countable state space

Autor:	V. Nollau, D. Hudak
Rok vydání:	2004
Předmět:	Mathematical optimization Control and Optimization Markov kernel Markov chain Applied Mathematics Bellman equation State space Countable set Partially observable Markov decision process Function (mathematics) Management Science and Operations Research Decision problem Mathematics
Zdroj:	Optimization. 53:339-353
ISSN:	1029-4945 0233-1934
DOI:	10.1080/02331930410001720932
Popis:	In this article we consider the approximate solution for semi-Markov decision problems with infinite horizon, countable state space, discounted cost function and finite action space. We present converging sequences of lower and upper bounds for the value function and, moreover, we derive a method for exclusion of suboptimal actions.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::8c9d2fc4701816113596767f532633e1 https://doi.org/10.1080/02331930410001720932 Zobrazit plný text záznamu