This paper describes sufficient conditions for the existence of optimal policies for partially observable Markov decision processes (POMDPs) with Borel state, observation, and action sets, when the ...
Probabilistic model checking and Markov decision processes (MDPs) form two interlinked branches of formal analysis for systems operating under uncertainty. These techniques offer a mathematical ...
Lecture Notes-Monograph Series, Vol. 30, Statistics, Probability and Game Theory: Papers in Honor of David Blackwell (1996), pp. 29-43 (15 pages) This paper deals with a discrete time Markov Decision ...