✦ LIBER ✦

Bayesian adaptive control of discrete-time Markov processes with long-run average cost

✍ Scribed by G.B.Di Masi; Ł. Stettner

Publisher: Elsevier Science
Year: 1998
Tongue: English
Weight: 100 KB
Volume: 34
Category: Article
ISSN: 0167-6911
DOI: 10.1016/s0167-6911(97)00123-0

No coin nor oath required. For personal study only.

✦ Synopsis

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 process.

📜 SIMILAR VOLUMES

Infinite horizon risk sensitive control

Infinite horizon risk sensitive control of discrete time Markov processes with small risk

✍ G.B.Di Masi; Ł. Stettner 📂 Article 📅 2000 🏛 Elsevier Science 🌐 English ⚖ 96 KB

A control problem with risk sensitive ergodic performance criterion is considered for a discrete time Feller process. Using assumptions of uniform ergodicity and small risk factor, the existence and uniqueness of the solution to the Bellman equation is proved. Uniform approximations to such solution