Identification of optimal policies in Markov decision processes

Sladký, Karel. "Identification of optimal policies in Markov decision processes." Kybernetika 46.3 (2010): 558-570. <http://eudml.org/doc/196935>.

@article{Sladký2010,
abstract = {In this note we focus attention on identifying optimal policies and on elimination suboptimal policies minimizing optimality criteria in discrete-time Markov decision processes with finite state space and compact action set. We present unified approach to value iteration algorithms that enables to generate lower and upper bounds on optimal values, as well as on the current policy. Using the modified value iterations it is possible to eliminate suboptimal actions and to identify an optimal policy or nearly optimal policies in a finite number of steps without knowing precise values of the performance function.},
author = {Sladký, Karel},
journal = {Kybernetika},
keywords = {finite state Markov decision processes; discounted and average costs; elimination of suboptimal policies; finite state Markov decision processes; discounted and average costs; elimination of suboptimal policies},
language = {eng},
number = {3},
pages = {558-570},
publisher = {Institute of Information Theory and Automation AS CR},
title = {Identification of optimal policies in Markov decision processes},
url = {http://eudml.org/doc/196935},
volume = {46},
year = {2010},
}

TY - JOUR
AU - Sladký, Karel
TI - Identification of optimal policies in Markov decision processes
JO - Kybernetika
PY - 2010
PB - Institute of Information Theory and Automation AS CR
VL - 46
IS - 3
SP - 558
EP - 570
AB - In this note we focus attention on identifying optimal policies and on elimination suboptimal policies minimizing optimality criteria in discrete-time Markov decision processes with finite state space and compact action set. We present unified approach to value iteration algorithms that enables to generate lower and upper bounds on optimal values, as well as on the current policy. Using the modified value iterations it is possible to eliminate suboptimal actions and to identify an optimal policy or nearly optimal policies in a finite number of steps without knowing precise values of the performance function.
LA - eng
KW - finite state Markov decision processes; discounted and average costs; elimination of suboptimal policies; finite state Markov decision processes; discounted and average costs; elimination of suboptimal policies
UR - http://eudml.org/doc/196935
ER -