Bayesian adaptive control of discrete-ti
β
G.B.Di Masi; Ε. Stettner
π
Article
π
1998
π
Elsevier Science
π
English
β 100 KB
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