Minimising a threshold probability in discounted Markov decision processes (Q2367616)
From MaRDI portal
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Minimising a threshold probability in discounted Markov decision processes |
scientific article |
Statements
Minimising a threshold probability in discounted Markov decision processes (English)
0 references
26 August 1993
0 references
The paper deals with a discrete time Markov decision process with finite state and action sets. The goal is to find a policy which maximizes the probability that the total discounted reward is greater than a given level. The author derives the optimality equation, proves the existence of an optimal stationary policy, and describes policy and value iteration algorithms for this problem.
0 references
threshold probability
0 references
discrete time Markov decision process
0 references
finite state and action sets
0 references
total discounted reward
0 references
optimality equation
0 references
existence of an optimal stationary policy
0 references
policy and value iteration algorithms
0 references
