Ergodic discretized estimator learning automata with high accuracy and high adaptation rate for nonstationary environments

A novel ergodic discretized learning automaton which is epsilon-optimal is introduced. It utilizes a novel estimator learning algorithm which is based on the recent history of the environmental responses and is able to operate in nonstationary stochastic environments. The proposed automaton achieves significantly higher performance than the classical reward-penalty ergodic schemes. Extensive simulation results indicate the superiority of the proposed scheme. Furthermore, it is proved that it is epsilon-optimal in every stochastic environment.<>