Bibliografie
Abstract
Minimum variance criterion in stochastic dynamic programming. Abstract
: International Federation of Operational Research Societies 2002. IFORS 2002. Abstracts, p. 28
: UK Operational Research Society, (Edinburgh 2002)
: IFORS 2002, (Edinburgh, GB, 08.07.2002-12.07.2002)
: CEZ:AV0Z1075907
: GA402/02/1015, GA ČR, GA402/01/0539, GA ČR
: stochastic dynamic programming, Markov decision chains, mean-variance
(eng): We investigate how the minimum variance criterion can work in discrete stochastic dynamic programming. We adapt notions and notation used in Markov decision chains and in contrast to the classical models we also consider variance of the obtained total reward. Alternative definitions of the reward variance along with their mutual connections are discussed. Attention is also focused on finding policies minimizing the average reward variance on condition that the average reward is not less than a given value.
: 12B
: BB