Narrow search
Showing 1 - 4 of 4
Cover Image
Blackwell optimality in the class of all policies in Markov decision chains with a Borel state space and unbounded rewards
Hordijk, Arie; Yushkevich, Alexander A. - In: Mathematical Methods of Operations Research 50 (1999) 3, pp. 421-448
This paper is the second part of our study of Blackwell optimal policies in Markov decision chains with a Borel state space and unbounded rewards. We prove that a stationary policy is Blackwell optimal in the class of all history-dependent policies if it is Blackwell optimal in the class of...
Persistent link: https://www.econbiz.de/10010999684
Cover Image
Blackwell optimality in the class of stationary policies in Markov decision chains with a Borel state space and unbounded rewards
Hordijk, Arie; Yushkevich, Alexander A. - In: Mathematical Methods of Operations Research 49 (1999) 1, pp. 1-39
This paper is the first part of a study of Blackwell optimal policies in Markov decision chains with a Borel state space and unbounded rewards. We prove here the existence of deterministic stationary policies which are Blackwell optimal in the class of all, in general randomized, stationary...
Persistent link: https://www.econbiz.de/10010950017
Cover Image
Blackwell optimality in the class of stationary policies in Markov decision chains with a Borel state space and unbounded rewards
Hordijk, Arie; Yushkevich, Alexander A. - In: Computational Statistics 49 (1999) 1, pp. 1-39
This paper is the first part of a study of Blackwell optimal policies in Markov decision chains with a Borel state space and unbounded rewards. We prove here the existence of deterministic stationary policies which are Blackwell optimal in the class of all, in general randomized, stationary...
Persistent link: https://www.econbiz.de/10010759232
Cover Image
Blackwell optimality in the class of all policies in Markov decision chains with a Borel state space and unbounded rewards
Hordijk, Arie; Yushkevich, Alexander A. - In: Computational Statistics 50 (1999) 3, pp. 421-448
This paper is the second part of our study of Blackwell optimal policies in Markov decision chains with a Borel state space and unbounded rewards. We prove that a stationary policy is Blackwell optimal in the class of all history-dependent policies if it is Blackwell optimal in the class of...
Persistent link: https://www.econbiz.de/10010759278