Premium
Markov decision processes with a target set for minimum criteria
Author(s) -
Ohtsubo Yoshio
Publication year - 2007
Publication title -
international transactions in operational research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.032
H-Index - 52
eISSN - 1475-3995
pISSN - 0969-6016
DOI - 10.1111/j.1475-3995.2007.00610.x
Subject(s) - markov decision process , bellman equation , mathematical optimization , set (abstract data type) , function (biology) , class (philosophy) , markov process , markov chain , mathematics , value (mathematics) , computer science , time horizon , artificial intelligence , statistics , evolutionary biology , biology , programming language
We consider Markov decisions processes with a target set, where criterion function is an expectation of minimum function. We formulate the problem as an infinite horizon case with a recurrent class. We show under some conditions that an optimal value function is a unique solution to an optimality equation and there exists a stationary optimal policy. Also we give a policy improvement method.