A generalized learning algorithm for an automaton operating in a multiteacher environment

Learning algorithms for an automaton operating in a multiteacher environmen t are considered. These algorithms are classified based on the number of ac tions given as inputs to the environments and the number of responses (outp uts) obtained from the environments. In this paper, we present a general cl ass of learning algorithm for multi-input multi-output (MIMO) models. We sh ow that the proposed learning algorithm is absolutely expedient and E-optim al in the sense of average penalty. The proposed learning algorithm is a ge neralization of Baba's GAE algorithm [16] and has applications in solving, in a parallel manner, multi-objective optimization problems in which each o bjective function is disturbed by noise [20].