Weak conditions for average optimality in Markov control processes
✍ Scribed by Onésimo Hernéandez-Lerma; Jean B. Lasserre
- Publisher
- Elsevier Science
- Year
- 1994
- Tongue
- English
- Weight
- 262 KB
- Volume
- 22
- Category
- Article
- ISSN
- 0167-6911
No coin nor oath required. For personal study only.
📜 SIMILAR VOLUMES
Semi-Markov control processes with Borel state space and Feller transition probabilities are considered. The objective of the paper is to prove coincidence of two expected average costs: the time-average and the ratio-average for stationary policies. Moreover, the optimal stationary policy is the sa
This work concerns discrete-time Markov control processes with unbounded costs and unknown disturbance distribution θ. Assuming observability of the random disturbance, we estimate θ using its empirical estimator, which, combined with a variant of the vanishing discount factor approach, yields avera