Approximation and estimation in Markov control processes under a discounted criterion.
J. Adolfo Minjárez-SosaPublished in: Kybernetika (2004)
Keyphrases
- control system
- optimal control
- estimation algorithm
- learning algorithm
- feature selection
- data sets
- markov chain
- sufficient conditions
- error bounds
- infinite horizon
- production processes
- maximum a posteriori probability
- importance sampling
- conditional independence
- random fields
- robotic systems
- approximation algorithms
- closed form
- mobile robot