Original title:
Second Order Optimality in Transient and Discounted Markov Decision Chains
Authors:
Sladký, Karel Document type: Papers Conference/Event: Mathematical Methods in Economics 2015 /33./, Cheb (CZ), 2015-09-09 / 2015-09-11
Year:
2015
Language:
eng Abstract:
The article is devoted to second order optimality in Markov decision processes. Attention is primarily focused on the reward variance for discounted models and undiscounted transient models (i.e. where the spectral radius of the transition probability matrix is less than unity). Considering the second order optimality criteria means that in the class of policies maximizing (or minimizing) total expected discounted reward (or undiscounted reward for the transient model) we choose the policy minimizing the total variance. Explicit formulae for calculating the variances for transient and discounted models are reported along with sketches of algoritmic procedures for finding second order optimal policies.
Keywords:
discounted and transient Markov reward chains; dynamic programming; reward-variance optimality Project no.: GA13-14445S (CEP), GA15-10331S (CEP) Funding provider: GA ČR, GA ČR Host item entry: Procedings of the 33rd International Conference Mathematical Methods in Economics MME 2015, ISBN 978-80-261-0539-8