0410869 20240103182245.020060210235959.9 Prague Institute of Information Theory and Automation 2002 1 s. 322JanžuraM.MikoschT. Markov decision chains mean-variance policy iteration cav_un_auth*0101196 Sladký Karel UTIA-B Department of Econometrics Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101193 Sitař Milan UTIA-B Ústav teorie informace a automatizace AV ČR, v. v. i. 12B GA402/02/1015 GA ČR cav_un_auth*0000527 GA402/01/0539 GA ČR cav_un_auth*0008959 CEZ:AV0Z1075907 We investigate how the mean-variance selection rule, originally proposed for portfolio selection problems, can work in Markovian decision models. We consider a Markov decision chain with finite state and action spaces, however, instead of average expected reward or average expected variance optimality we consider mean variance optimality, square mean variance optimality or weighted difference of average expected rewards and variances. Optimality conditions and algorithmic procedures are presented. cav_un_auth*0212933 EMS 2002 Prague CZ 19.08.2002-23.08.2002 BB E http://hdl.handle.net/11104/0130956 UTIA-B 20020083 2002 2002 Prague Institute of Information Theory and Automation Abstracts of the 24th European Meeting of Statisticians & 14th Prague Conference on Information Theory, Statistical Decision Functions and Random Processes 322 Janžura M. 340 Mikosch T. 340