A simple adaptive control strategy for discrete-time Markov processes with compact state, action and parameter spaces that guarantees near self-optimality is proposed. The approach used is based on randomization and the study of invariant measure of the joint state and Bayesian parameter estimator p
✦ LIBER ✦
Adaptive control for discrete-time Markov processes with unbounded costs: Average criterion
✍ Scribed by Evgueni I. Gordienko; J. Adolfo Minjárez-Sosa
- Publisher
- Springer
- Year
- 1998
- Tongue
- English
- Weight
- 243 KB
- Volume
- 48
- Category
- Article
- ISSN
- 0340-9422
No coin nor oath required. For personal study only.
📜 SIMILAR VOLUMES
Bayesian adaptive control of discrete-ti
✍
G.B.Di Masi; Ł. Stettner
📂
Article
📅
1998
🏛
Elsevier Science
🌐
English
⚖ 100 KB
Denumerable controlled Markov chains wit
✍
Rolando Cavazos-Cadena; Emmanuel Fernández-Gaucherand
📂
Article
📅
1996
🏛
Springer
🌐
English
⚖ 802 KB
Robustness inequality for Markov control
✍
Evgueni I. Gordienko; Francisco S. Salem
📂
Article
📅
1998
🏛
Elsevier Science
🌐
English
⚖ 387 KB
The paper discusses the robustness of discrete-time Markov control processes whose transition probabilities are known up to certain degree of accuracy. Upper bounds of increase of a discounted cost are derived when using an optimal control policy of the approximating process in order to control the
Recursive adaptive control of Markov dec
✍
Rolando Cavazos-Cadena; Onésimo Hernández-Lerma
📂
Article
📅
1991
🏛
Springer
🌐
English
⚖ 710 KB
Semi-Markov Control Processes with Unkno
✍
Fernando Luque-Vásquez; J. Adolfo Minjárez-Sosa; Luz del Carmen Rosas-Rosas
📂
Article
📅
2009
🏛
Springer
🌐
English
⚖ 485 KB
Average cost optimal policies for Markov
✍
Onésimo Hernández-Lerma; Jean B. Lasserre
📂
Article
📅
1990
🏛
Elsevier Science
🌐
English
⚖ 533 KB